kunthawat/moreminimore-marketing
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Base code

Browse Source
This commit is contained in:
Kunthawat Greethong
2026-01-08 22:39:53 +07:00
parent 697115c61a
commit c35fa52117
2169 changed files with 626670 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

940
docs-site/docs/features/image-studio/api-reference.md Normal file
View File

@@ -0,0 +1,940 @@
# Image Studio API Reference
Complete API documentation for Image Studio, including all endpoints, request/response models, authentication, and usage examples.
## Base URL
All Image Studio endpoints are prefixed with `/api/image-studio`
## Authentication
All endpoints require authentication via Bearer token:
```http
Authorization: Bearer YOUR_ACCESS_TOKEN
```
The token is obtained through the standard ALwrity authentication flow. See [Authentication Guide](../api/authentication.md) for details.
## API Architecture
```mermaid
graph TB
Client[Client Application] --> API[Image Studio API]
API --> Create[Create Studio]
API --> Edit[Edit Studio]
API --> Upscale[Upscale Studio]
API --> Control[Control Studio]
API --> Social[Social Optimizer]
API --> Templates[Templates]
API --> Providers[Providers]
Create --> Manager[ImageStudioManager]
Edit --> Manager
Upscale --> Manager
Control --> Manager
Social --> Manager
Manager --> Stability[Stability AI]
Manager --> WaveSpeed[WaveSpeed AI]
Manager --> HuggingFace[HuggingFace]
Manager --> Gemini[Gemini]
style Client fill:#e3f2fd
style API fill:#e1f5fe
style Manager fill:#f3e5f5
```
## Endpoint Categories
### Create Studio
- [Generate Image](#generate-image)
- [Get Templates](#get-templates)
- [Search Templates](#search-templates)
- [Recommend Templates](#recommend-templates)
- [Get Providers](#get-providers)
- [Estimate Cost](#estimate-cost)
### Edit Studio
- [Process Edit](#process-edit)
- [Get Edit Operations](#get-edit-operations)
### Upscale Studio
- [Upscale Image](#upscale-image)
### Control Studio
- [Process Control](#process-control)
- [Get Control Operations](#get-control-operations)
### Social Optimizer
- [Optimize for Social](#optimize-for-social)
- [Get Platform Formats](#get-platform-formats)
### Platform Specifications
- [Get Platform Specs](#get-platform-specs)
### Health Check
- [Health Check](#health-check)
---
## Create Studio Endpoints
### Generate Image
Generate one or more images from text prompts.
**Endpoint**: `POST /api/image-studio/create`
**Request Body**:
```json
{
"prompt": "Modern minimalist workspace with laptop",
"template_id": "linkedin_post",
"provider": "auto",
"model": null,
"width": null,
"height": null,
"aspect_ratio": null,
"style_preset": "photographic",
"quality": "standard",
"negative_prompt": "blurry, low quality",
"guidance_scale": null,
"steps": null,
"seed": null,
"num_variations": 1,
"enhance_prompt": true,
"use_persona": false,
"persona_id": null
}
```
**Request Fields**:
| Field | Type | Required | Description |
|-------|------|----------|-------------|
| `prompt` | string | Yes | Image generation prompt |
| `template_id` | string | No | Template ID to use |
| `provider` | string | No | Provider: auto, stability, wavespeed, huggingface, gemini |
| `model` | string | No | Specific model to use |
| `width` | integer | No | Image width in pixels |
| `height` | integer | No | Image height in pixels |
| `aspect_ratio` | string | No | Aspect ratio (e.g., '1:1', '16:9') |
| `style_preset` | string | No | Style preset |
| `quality` | string | No | Quality: draft, standard, premium (default: standard) |
| `negative_prompt` | string | No | Negative prompt |
| `guidance_scale` | float | No | Guidance scale |
| `steps` | integer | No | Number of inference steps |
| `seed` | integer | No | Random seed |
| `num_variations` | integer | No | Number of variations (1-10, default: 1) |
| `enhance_prompt` | boolean | No | Enhance prompt with AI (default: true) |
| `use_persona` | boolean | No | Use persona for brand consistency (default: false) |
| `persona_id` | string | No | Persona ID |
**Response**:
```json
{
"success": true,
"request": {
"prompt": "Modern minimalist workspace with laptop",
"enhanced_prompt": "Modern minimalist workspace with laptop, professional photography, high quality",
"template_id": "linkedin_post",
"template_name": "LinkedIn Post",
"provider": "wavespeed",
"model": "ideogram-v3-turbo",
"dimensions": "1200x628",
"quality": "standard"
},
"results": [
{
"image_base64": "iVBORw0KGgoAAAANS...",
"width": 1200,
"height": 628,
"provider": "wavespeed",
"model": "ideogram-v3-turbo",
"variation": 1
}
],
"total_generated": 1,
"total_failed": 0
}
```
**Response Fields**:
| Field | Type | Description |
|-------|------|-------------|
| `success` | boolean | Operation success status |
| `request` | object | Request details with applied settings |
| `results` | array | Generated images with base64 data |
| `total_generated` | integer | Number of successfully generated images |
| `total_failed` | integer | Number of failed generations |
**Error Responses**:
- `400 Bad Request`: Invalid request parameters
- `401 Unauthorized`: Authentication required
- `500 Internal Server Error`: Generation failed
---
### Get Templates
Get available image templates, optionally filtered by platform or category.
**Endpoint**: `GET /api/image-studio/templates`
**Query Parameters**:
| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `platform` | string | No | Filter by platform (instagram, facebook, twitter, etc.) |
| `category` | string | No | Filter by category (social_media, blog_content, etc.) |
**Example Request**:
```http
GET /api/image-studio/templates?platform=instagram
```
**Response**:
```json
{
"templates": [
{
"id": "instagram_feed_square",
"name": "Instagram Feed Post (Square)",
"category": "social_media",
"platform": "instagram",
"aspect_ratio": {
"ratio": "1:1",
"width": 1080,
"height": 1080,
"label": "Square"
},
"description": "Perfect for Instagram feed posts",
"recommended_provider": "ideogram",
"style_preset": "photographic",
"quality": "premium",
"use_cases": ["Product showcase", "Lifestyle posts", "Brand content"]
}
],
"total": 4
}
```
---
### Search Templates
Search templates by query string.
**Endpoint**: `GET /api/image-studio/templates/search`
**Query Parameters**:
| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `query` | string | Yes | Search query |
**Example Request**:
```http
GET /api/image-studio/templates/search?query=linkedin
```
**Response**: Same format as Get Templates
---
### Recommend Templates
Get template recommendations based on use case.
**Endpoint**: `GET /api/image-studio/templates/recommend`
**Query Parameters**:
| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `use_case` | string | Yes | Use case description |
| `platform` | string | No | Optional platform filter |
**Example Request**:
```http
GET /api/image-studio/templates/recommend?use_case=product+showcase&platform=instagram
```
**Response**: Same format as Get Templates
---
### Get Providers
Get available AI providers and their capabilities.
**Endpoint**: `GET /api/image-studio/providers`
**Response**:
```json
{
"providers": {
"stability": {
"name": "Stability AI",
"models": ["ultra", "core", "sd3.5-large"],
"capabilities": ["generation", "editing", "upscaling"],
"max_resolution": "2048x2048",
"cost_range": "3-8 credits"
},
"wavespeed": {
"name": "WaveSpeed AI",
"models": ["ideogram-v3-turbo", "qwen-image"],
"capabilities": ["generation"],
"max_resolution": "1024x1024",
"cost_range": "1-6 credits"
}
}
}
```
---
### Estimate Cost
Estimate cost for image generation operations.
**Endpoint**: `POST /api/image-studio/estimate-cost`
**Request Body**:
```json
{
"provider": "wavespeed",
"model": "ideogram-v3-turbo",
"operation": "generate",
"num_images": 1,
"width": 1200,
"height": 628
}
```
**Request Fields**:
| Field | Type | Required | Description |
|-------|------|----------|-------------|
| `provider` | string | Yes | Provider name |
| `model` | string | No | Model name |
| `operation` | string | No | Operation type (default: generate) |
| `num_images` | integer | No | Number of images (default: 1) |
| `width` | integer | No | Image width |
| `height` | integer | No | Image height |
**Response**:
```json
{
"estimated_cost": 5,
"currency": "credits",
"provider": "wavespeed",
"model": "ideogram-v3-turbo",
"operation": "generate",
"num_images": 1
}
```
---
## Edit Studio Endpoints
### Process Edit
Perform Edit Studio operations on images.
**Endpoint**: `POST /api/image-studio/edit/process`
**Request Body**:
```json
{
"image_base64": "data:image/png;base64,iVBORw0KGgo...",
"operation": "remove_background",
"prompt": null,
"negative_prompt": null,
"mask_base64": null,
"search_prompt": null,
"select_prompt": null,
"background_image_base64": null,
"lighting_image_base64": null,
"expand_left": 0,
"expand_right": 0,
"expand_up": 0,
"expand_down": 0,
"provider": null,
"model": null,
"style_preset": null,
"guidance_scale": null,
"steps": null,
"seed": null,
"output_format": "png",
"options": {}
}
```
**Request Fields**:
| Field | Type | Required | Description |
|-------|------|----------|-------------|
| `image_base64` | string | Yes | Primary image (base64 or data URL) |
| `operation` | string | Yes | Operation: remove_background, inpaint, outpaint, search_replace, search_recolor, general_edit |
| `prompt` | string | No | Primary prompt/instruction |
| `negative_prompt` | string | No | Negative prompt |
| `mask_base64` | string | No | Optional mask image (base64) |
| `search_prompt` | string | No | Search prompt for replace operations |
| `select_prompt` | string | No | Select prompt for recolor operations |
| `background_image_base64` | string | No | Reference background image |
| `lighting_image_base64` | string | No | Reference lighting image |
| `expand_left` | integer | No | Outpaint expansion left (pixels) |
| `expand_right` | integer | No | Outpaint expansion right (pixels) |
| `expand_up` | integer | No | Outpaint expansion up (pixels) |
| `expand_down` | integer | No | Outpaint expansion down (pixels) |
| `provider` | string | No | Explicit provider override |
| `model` | string | No | Explicit model override |
| `style_preset` | string | No | Style preset |
| `guidance_scale` | float | No | Guidance scale |
| `steps` | integer | No | Inference steps |
| `seed` | integer | No | Random seed |
| `output_format` | string | No | Output format (default: png) |
| `options` | object | No | Advanced provider-specific options |
**Response**:
```json
{
"success": true,
"operation": "remove_background",
"provider": "stability",
"image_base64": "data:image/png;base64,iVBORw0KGgo...",
"width": 1200,
"height": 628,
"metadata": {
"operation": "remove_background",
"processing_time": 2.5
}
}
```
---
### Get Edit Operations
Get metadata for all available Edit Studio operations.
**Endpoint**: `GET /api/image-studio/edit/operations`
**Response**:
```json
{
"operations": {
"remove_background": {
"label": "Remove Background",
"description": "Isolate the main subject",
"provider": "stability",
"fields": {
"prompt": false,
"mask": false,
"negative_prompt": false,
"search_prompt": false,
"select_prompt": false,
"background": false,
"lighting": false,
"expansion": false
}
},
"inpaint": {
"label": "Inpaint & Fix",
"description": "Edit specific regions using prompts and optional masks",
"provider": "stability",
"fields": {
"prompt": true,
"mask": true,
"negative_prompt": true,
"search_prompt": false,
"select_prompt": false,
"background": false,
"lighting": false,
"expansion": false
}
}
}
}
```
---
## Upscale Studio Endpoints
### Upscale Image
Upscale an image using AI-powered upscaling.
**Endpoint**: `POST /api/image-studio/upscale`
**Request Body**:
```json
{
"image_base64": "data:image/png;base64,iVBORw0KGgo...",
"mode": "conservative",
"target_width": null,
"target_height": null,
"preset": "print",
"prompt": "High fidelity upscale preserving original details"
}
```
**Request Fields**:
| Field | Type | Required | Description |
|-------|------|----------|-------------|
| `image_base64` | string | Yes | Image to upscale (base64 or data URL) |
| `mode` | string | No | Mode: fast, conservative, creative, auto (default: auto) |
| `target_width` | integer | No | Target width in pixels |
| `target_height` | integer | No | Target height in pixels |
| `preset` | string | No | Named preset: web, print, social |
| `prompt` | string | No | Prompt for conservative/creative modes |
**Response**:
```json
{
"success": true,
"mode": "conservative",
"image_base64": "data:image/png;base64,iVBORw0KGgo...",
"width": 3072,
"height": 2048,
"metadata": {
"preset": "print",
"original_width": 768,
"original_height": 512,
"upscale_factor": 4.0
}
}
```
---
## Control Studio Endpoints
### Process Control
Perform Control Studio operations (sketch-to-image, style transfer, etc.).
**Endpoint**: `POST /api/image-studio/control/process`
**Request Body**:
```json
{
"control_image_base64": "data:image/png;base64,iVBORw0KGgo...",
"operation": "sketch",
"prompt": "Modern office interior",
"style_image_base64": null,
"negative_prompt": null,
"control_strength": 0.8,
"fidelity": null,
"style_strength": null,
"composition_fidelity": null,
"change_strength": null,
"aspect_ratio": null,
"style_preset": null,
"seed": null,
"output_format": "png"
}
```
**Request Fields**:
| Field | Type | Required | Description |
|-------|------|----------|-------------|
| `control_image_base64` | string | Yes | Control image (sketch/structure/style) |
| `operation` | string | Yes | Operation: sketch, structure, style, style_transfer |
| `prompt` | string | Yes | Text prompt for generation |
| `style_image_base64` | string | No | Style reference image (for style_transfer) |
| `negative_prompt` | string | No | Negative prompt |
| `control_strength` | float | No | Control strength 0.0-1.0 (for sketch/structure) |
| `fidelity` | float | No | Style fidelity 0.0-1.0 (for style operation) |
| `style_strength` | float | No | Style strength 0.0-1.0 (for style_transfer) |
| `composition_fidelity` | float | No | Composition fidelity 0.0-1.0 (for style_transfer) |
| `change_strength` | float | No | Change strength 0.0-1.0 (for style_transfer) |
| `aspect_ratio` | string | No | Aspect ratio (for style operation) |
| `style_preset` | string | No | Style preset |
| `seed` | integer | No | Random seed |
| `output_format` | string | No | Output format (default: png) |
**Response**:
```json
{
"success": true,
"operation": "sketch",
"provider": "stability",
"image_base64": "data:image/png;base64,iVBORw0KGgo...",
"width": 1024,
"height": 1024,
"metadata": {
"operation": "sketch",
"control_strength": 0.8
}
}
```
---
### Get Control Operations
Get metadata for all available Control Studio operations.
**Endpoint**: `GET /api/image-studio/control/operations`
**Response**: Similar format to Edit Operations
---
## Social Optimizer Endpoints
### Optimize for Social
Optimize an image for multiple social media platforms.
**Endpoint**: `POST /api/image-studio/social/optimize`
**Request Body**:
```json
{
"image_base64": "data:image/png;base64,iVBORw0KGgo...",
"platforms": ["instagram", "facebook", "linkedin"],
"format_names": {
"instagram": "Feed Post (Square)",
"facebook": "Feed Post",
"linkedin": "Post"
},
"show_safe_zones": false,
"crop_mode": "smart",
"focal_point": null,
"output_format": "png"
}
```
**Request Fields**:
| Field | Type | Required | Description |
|-------|------|----------|-------------|
| `image_base64` | string | Yes | Source image (base64 or data URL) |
| `platforms` | array | Yes | List of platforms to optimize for |
| `format_names` | object | No | Specific format per platform |
| `show_safe_zones` | boolean | No | Include safe zone overlay (default: false) |
| `crop_mode` | string | No | Crop mode: smart, center, fit (default: smart) |
| `focal_point` | object | No | Focal point for smart crop (x, y as 0-1) |
| `output_format` | string | No | Output format: png or jpg (default: png) |
**Response**:
```json
{
"success": true,
"results": [
{
"platform": "instagram",
"format": "Feed Post (Square)",
"image_base64": "data:image/png;base64,iVBORw0KGgo...",
"width": 1080,
"height": 1080
},
{
"platform": "facebook",
"format": "Feed Post",
"image_base64": "data:image/png;base64,iVBORw0KGgo...",
"width": 1200,
"height": 630
}
],
"total_optimized": 2
}
```
---
### Get Platform Formats
Get available formats for a specific social media platform.
**Endpoint**: `GET /api/image-studio/social/platforms/{platform}/formats`
**Path Parameters**:
| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `platform` | string | Yes | Platform name (instagram, facebook, etc.) |
**Response**:
```json
{
"formats": [
{
"name": "Feed Post (Square)",
"width": 1080,
"height": 1080,
"ratio": "1:1",
"safe_zone": {
"top": 0.15,
"bottom": 0.15,
"left": 0.1,
"right": 0.1
},
"file_type": "PNG",
"max_size_mb": 5.0
}
]
}
```
---
## Platform Specifications Endpoints
### Get Platform Specs
Get specifications and requirements for a specific platform.
**Endpoint**: `GET /api/image-studio/platform-specs/{platform}`
**Path Parameters**:
| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `platform` | string | Yes | Platform name |
**Response**:
```json
{
"name": "Instagram",
"formats": [
{
"name": "Feed Post (Square)",
"ratio": "1:1",
"size": "1080x1080"
}
],
"file_types": ["JPG", "PNG"],
"max_file_size": "30MB"
}
```
---
## Health Check
### Health Check
Check Image Studio service health.
**Endpoint**: `GET /api/image-studio/health`
**Response**:
```json
{
"status": "healthy",
"service": "image_studio",
"version": "1.0.0",
"modules": {
"create_studio": "available",
"templates": "available",
"providers": "available"
}
}
```
---
## Error Handling
### Error Response Format
All errors follow this format:
```json
{
"detail": "Error message description"
}
```
### HTTP Status Codes
- `200 OK`: Successful request
- `400 Bad Request`: Invalid request parameters
- `401 Unauthorized`: Authentication required
- `404 Not Found`: Resource not found
- `500 Internal Server Error`: Server error
### Common Error Scenarios
**Invalid Image Format**:
```json
{
"detail": "Invalid base64 image payload"
}
```
**Missing Required Field**:
```json
{
"detail": "Prompt is required for inpainting"
}
```
**Provider Error**:
```json
{
"detail": "Image generation failed: Provider error message"
}
```
**Authentication Error**:
```json
{
"detail": "Authenticated user required for image operations."
}
```
---
## Rate Limiting
Image Studio API follows standard ALwrity rate limiting:
- **Rate Limits**: Based on subscription tier
- **Headers**: Rate limit information in response headers
- **Retry**: Use exponential backoff for rate limit errors
See [Rate Limiting Guide](../api/rate-limiting.md) for details.
---
## Best Practices
### Image Encoding
- **Base64 Format**: All images should be base64 encoded
- **Data URLs**: Support for `data:image/png;base64,...` format
- **Size Limits**: Recommended under 10MB for best performance
- **Format**: PNG or JPG supported
### Request Optimization
1. **Use Templates**: Templates optimize settings automatically
2. **Batch Operations**: Generate multiple variations in one request
3. **Estimate Costs**: Use cost estimation before large operations
4. **Error Handling**: Implement retry logic for transient errors
### Response Handling
1. **Base64 Images**: Decode base64 images in responses
2. **Metadata**: Use metadata for tracking and organization
3. **Error Messages**: Display user-friendly error messages
4. **Progress**: For long operations, implement polling if needed
---
## Code Examples
### Python Example
```python
import requests
import base64
# Generate Image
url = "https://api.alwrity.com/api/image-studio/create"
headers = {
"Authorization": "Bearer YOUR_TOKEN",
"Content-Type": "application/json"
}
data = {
"prompt": "Modern office workspace",
"template_id": "linkedin_post",
"quality": "standard"
}
response = requests.post(url, json=data, headers=headers)
result = response.json()
# Decode image
image_data = base64.b64decode(result["results"][0]["image_base64"])
with open("generated_image.png", "wb") as f:
f.write(image_data)
```
### JavaScript Example
```javascript
// Generate Image
const response = await fetch('https://api.alwrity.com/api/image-studio/create', {
method: 'POST',
headers: {
'Authorization': 'Bearer YOUR_TOKEN',
'Content-Type': 'application/json'
},
body: JSON.stringify({
prompt: 'Modern office workspace',
template_id: 'linkedin_post',
quality: 'standard'
})
});
const result = await response.json();
// Display image
const img = document.createElement('img');
img.src = `data:image/png;base64,${result.results[0].image_base64}`;
document.body.appendChild(img);
```
### cURL Example
```bash
curl -X POST https://api.alwrity.com/api/image-studio/create \
-H "Authorization: Bearer YOUR_TOKEN" \
-H "Content-Type: application/json" \
-d '{
"prompt": "Modern office workspace",
"template_id": "linkedin_post",
"quality": "standard"
}'
```
---
## Related Documentation
- [Create Studio Guide](create-studio.md) - User guide for image generation
- [Edit Studio Guide](edit-studio.md) - User guide for image editing
- [Upscale Studio Guide](upscale-studio.md) - User guide for upscaling
- [Social Optimizer Guide](social-optimizer.md) - User guide for social optimization
- [Providers Guide](providers.md) - Provider selection guide
- [Cost Guide](cost-guide.md) - Cost management guide
- [Implementation Overview](implementation-overview.md) - Technical architecture
---
*For authentication details, see the [API Authentication Guide](../api/authentication.md). For rate limiting, see the [Rate Limiting Guide](../api/rate-limiting.md).*

323
docs-site/docs/features/image-studio/asset-library.md Normal file
View File

@@ -0,0 +1,323 @@
# Asset Library User Guide
Asset Library is a unified content archive that tracks all AI-generated content across all ALwrity modules. This guide covers search, filtering, organization, and bulk operations.
## Overview
Asset Library automatically tracks and organizes all content generated by ALwrity tools, including images, videos, audio, and text. It provides powerful search, filtering, and organization features to help you manage your content efficiently.
### Key Features
- **Unified Archive**: All ALwrity content in one place
- **Advanced Search**: Search by ID, model, keywords, and more
- **Multiple Filters**: Filter by type, module, date, status
- **Favorites**: Mark and organize favorite assets
- **Grid & List Views**: Choose your preferred view
- **Bulk Operations**: Download, delete, or share multiple assets
- **Usage Tracking**: Monitor asset usage and performance
## Getting Started
### Accessing Asset Library
1. Navigate to **Image Studio** from the main dashboard
2. Click on **Asset Library** or go directly to `/image-studio/asset-library`
3. View all your generated content
### Basic Workflow
1. **Browse Assets**: View all your generated content
2. **Search/Filter**: Find specific assets using search and filters
3. **Organize**: Mark favorites, create collections
4. **Download**: Download individual or multiple assets
5. **Manage**: Delete unused assets, track usage
## Search & Filtering
### Search Options
**ID Search**:
- Search by asset ID
- Useful for finding specific assets
- Partial ID matching supported
**Model Search**:
- Search by AI model used
- Find assets generated with specific models
- Example: "ideogram-v3-turbo", "stability-ultra"
**General Search**:
- Search across all asset metadata
- Searches titles, descriptions, prompts
- Keyword-based matching
### Filtering Options
**Type Filter**:
- **All Assets**: Show everything
- **Images**: Image files only
- **Videos**: Video files only
- **Audio**: Audio files only
- **Text**: Text content only
- **Favorites**: Only favorited assets
**Status Filter**:
- **All**: All statuses
- **Completed**: Successfully generated
- **Processing**: Currently being generated
- **Failed**: Generation failed
- **Pending**: Queued for generation
**Date Filter**:
- Filter by creation date
- Select specific date
- Useful for finding recent or old assets
**Module Filter**:
- Filter by source module
- Image Studio, Story Writer, Blog Writer, etc.
- Find assets from specific tools
## Views
### List View
**Features**:
- Detailed table layout
- All metadata visible
- Easy sorting and filtering
- Compact information display
**Best For**:
- Finding specific assets
- Viewing detailed information
- Bulk operations
- Data analysis
### Grid View
**Features**:
- Visual card-based layout
- Image previews
- Quick actions
- Visual browsing
**Best For**:
- Visual content browsing
- Quick asset selection
- Creative workflows
- Portfolio review
## Organization Features
### Favorites
**Marking Favorites**:
1. Click the favorite icon on any asset
2. Asset is added to favorites
3. Filter by "Favorites" to see only favorited assets
**Use Cases**:
- Mark best-performing assets
- Organize campaign assets
- Create quick access lists
- Build content libraries
### Collections (Coming Soon)
Future feature for organizing assets into collections:
- Create custom collections
- Organize by campaign, project, or theme
- Share collections with team
- Collection-based filtering
### Tags (Coming Soon)
Future feature for AI-powered tagging:
- Automatic tagging
- Manual tag addition
- Tag-based search
- Tag filtering
## Bulk Operations
### Bulk Download
**How to Use**:
1. Select multiple assets using checkboxes
2. Click "Download" button
3. All selected assets download
**Use Cases**:
- Download campaign assets
- Export content libraries
- Backup important assets
- Share with team
### Bulk Delete
**How to Use**:
1. Select multiple assets
2. Click "Delete" button
3. Confirm deletion
4. Selected assets are removed
**Use Cases**:
- Clean up unused assets
- Remove failed generations
- Free up storage
- Organize content
### Bulk Share (Coming Soon)
Future feature for sharing multiple assets:
- Share collections
- Generate shareable links
- Team collaboration
- Client sharing
## Asset Information
### Metadata Display
Each asset shows:
- **ID**: Unique asset identifier
- **Model**: AI model used for generation
- **Status**: Generation status
- **Type**: Asset type (image, video, audio, text)
- **Source Module**: Which ALwrity tool created it
- **Created Date**: When asset was generated
- **Cost**: Credits used for generation
- **Dimensions**: Image/video dimensions (if applicable)
### Status Indicators
**Completed**:
- Green checkmark
- Successfully generated
- Ready to use
**Processing**:
- Orange hourglass
- Currently being generated
- Wait for completion
**Failed**:
- Red error icon
- Generation failed
- May need retry
**Pending**:
- Gray icon
- Queued for generation
- Waiting to process
## Usage Tracking
### Download Tracking
- Tracks how many times assets are downloaded
- Useful for identifying popular content
- Helps understand content performance
### Share Tracking
- Tracks how many times assets are shared
- Monitors content distribution
- Useful for analytics
### Usage Analytics (Coming Soon)
Future feature for detailed analytics:
- Usage statistics
- Performance metrics
- Content insights
- Trend analysis
## Integration
### Automatic Tracking
Assets are automatically tracked from:
- **Image Studio**: All generated and edited images
- **Story Writer**: Scene images, audio, videos
- **Blog Writer**: Generated images
- **LinkedIn Writer**: Generated content
- **Other Modules**: All ALwrity tools
### Manual Upload (Coming Soon)
Future feature for manual asset upload:
- Upload external assets
- Organize all content in one place
- Unified content management
## Best Practices
### Organization
1. **Use Favorites**: Mark important assets
2. **Regular Cleanup**: Delete unused assets
3. **Search Effectively**: Use filters to find assets
4. **Track Usage**: Monitor popular content
### Workflow
1. **Generate Content**: Create assets in various modules
2. **Review in Library**: Check all assets in one place
3. **Organize**: Mark favorites, create collections
4. **Download**: Export when needed
5. **Clean Up**: Remove unused assets regularly
### Search Tips
1. **Use Specific Terms**: More specific searches work better
2. **Combine Filters**: Use multiple filters together
3. **Search by Model**: Find assets from specific AI models
4. **Date Ranges**: Use date filter for recent content
## Troubleshooting
### Common Issues
**Assets Not Appearing**:
- Check filters - may be filtering out assets
- Verify generation completed successfully
- Check source module integration
- Refresh the page
**Search Not Working**:
- Try different search terms
- Check spelling
- Use filters instead of search
- Clear search and try again
**Slow Loading**:
- Large asset libraries may load slowly
- Use filters to reduce results
- Check internet connection
- Pagination helps with large lists
**Missing Metadata**:
- Some older assets may have limited metadata
- New assets have complete information
- Check asset creation date
### Getting Help
- Check filtering options if assets are missing
- Review the [Workflow Guide](workflow-guide.md) for common workflows
- See [Implementation Overview](implementation-overview.md) for technical details
## Next Steps
After organizing assets in Asset Library:
1. **Use Assets**: Download and use in your projects
2. **Share**: Share assets with team or clients
3. **Analyze**: Review usage and performance
4. **Create More**: Generate new content in Image Studio modules
---
*For technical details, see the [Implementation Overview](implementation-overview.md). For API usage, see the [API Reference](api-reference.md).*

375
docs-site/docs/features/image-studio/control-studio.md Normal file
View File

@@ -0,0 +1,375 @@
# Control Studio Guide (Planned)
Control Studio will provide advanced generation controls for fine-grained image creation. This guide covers the planned features and capabilities.
## Status
**Current Status**: 🚧 Planned for future release
**Priority**: Medium - Advanced user feature
**Estimated Release**: Coming soon
## Overview
Control Studio enables precise control over image generation through sketch inputs, structure control, and style transfer. This module is designed for advanced users who need fine-grained control over the generation process.
### Key Planned Features
- **Sketch-to-Image**: Generate images from sketches
- **Structure Control**: Control image structure and composition
- **Style Transfer**: Apply styles to images
- **Style Control**: Fine-tune style application
- **Multi-Control**: Combine multiple control methods
---
## Sketch-to-Image
### Overview
Generate images from hand-drawn or digital sketches with precise control over how closely the output follows the sketch.
### Planned Features
#### Sketch Input
- **Upload Sketch**: Upload hand-drawn or digital sketches
- **Format Support**: PNG, JPG, SVG
- **Sketch Types**: Line art, rough sketches, detailed drawings
- **Preprocessing**: Automatic sketch enhancement
#### Control Strength
- **Strength Slider**: Adjust how closely image follows sketch (0.0-1.0)
- **Low Strength**: More creative interpretation
- **High Strength**: Strict adherence to sketch
- **Balanced**: Default balanced setting
#### Style Options
- **Style Presets**: Apply styles to sketches
- **Color Control**: Control color application
- **Detail Enhancement**: Enhance sketch details
- **Realistic Rendering**: Photorealistic output
### Use Cases
#### Concept Visualization
- Transform rough sketches into polished images
- Visualize design concepts
- Rapid prototyping
- Client presentations
#### Artistic Creation
- Enhance artistic sketches
- Apply styles to drawings
- Create finished artwork
- Artistic experimentation
#### Product Design
- Product concept visualization
- Design iteration
- Prototype visualization
- Design communication
### Workflow (Planned)
1. **Upload Sketch**: Select sketch image
2. **Enter Prompt**: Describe desired output
3. **Set Control Strength**: Adjust sketch adherence
4. **Choose Style**: Select style preset (optional)
5. **Generate**: Create image from sketch
6. **Refine**: Adjust settings and regenerate if needed
---
## Structure Control
### Overview
Control image structure, composition, and layout while generating new content.
### Planned Features
#### Structure Input
- **Structure Image**: Upload structure reference
- **Depth Maps**: Use depth information
- **Edge Detection**: Automatic edge detection
- **Composition Control**: Control image composition
#### Control Parameters
- **Structure Strength**: How closely to follow structure (0.0-1.0)
- **Detail Level**: Amount of detail to preserve
- **Composition Preservation**: Maintain original composition
- **Layout Control**: Control element placement
### Use Cases
#### Composition Control
- Maintain specific layouts
- Control element placement
- Preserve spatial relationships
- Design consistency
#### Depth Control
- Control depth information
- 3D-like effects
- Layered compositions
- Spatial relationships
---
## Style Transfer
### Overview
Apply artistic styles to images while maintaining content structure.
### Planned Features
#### Style Input
- **Style Image**: Upload style reference image
- **Style Library**: Pre-built style library
- **Custom Styles**: Upload custom style images
- **Style Categories**: Artistic, photographic, abstract styles
#### Transfer Control
- **Style Strength**: Intensity of style application (0.0-1.0)
- **Content Preservation**: Maintain original content
- **Style Blending**: Blend multiple styles
- **Selective Application**: Apply to specific areas
#### Style Options
- **Artistic Styles**: Painting, drawing, illustration styles
- **Photographic Styles**: Film, vintage, modern styles
- **Abstract Styles**: Abstract art, patterns, textures
- **Custom Styles**: Your own style references
### Use Cases
#### Artistic Transformation
- Apply artistic styles to photos
- Create artistic interpretations
- Style experimentation
- Creative projects
#### Brand Consistency
- Apply brand styles consistently
- Maintain visual identity
- Style matching
- Brand asset creation
#### Creative Projects
- Artistic exploration
- Style mixing
- Creative experimentation
- Unique visual effects
### Workflow (Planned)
1. **Upload Content Image**: Select image to style
2. **Upload Style Image**: Select style reference
3. **Set Style Strength**: Adjust application intensity
4. **Configure Options**: Set additional parameters
5. **Generate**: Apply style to image
6. **Refine**: Adjust and regenerate if needed
---
## Style Control
### Overview
Fine-tune style application with advanced control parameters.
### Planned Features
#### Style Parameters
- **Fidelity**: How closely to match style (0.0-1.0)
- **Composition Fidelity**: Preserve composition (0.0-1.0)
- **Change Strength**: Amount of change (0.0-1.0)
- **Aspect Ratio**: Control output aspect ratio
#### Advanced Options
- **Style Presets**: Pre-configured style settings
- **Selective Styling**: Apply to specific regions
- **Style Blending**: Combine multiple styles
- **Quality Control**: Output quality settings
### Use Cases
#### Precise Styling
- Fine-tune style application
- Control style intensity
- Maintain specific elements
- Professional styling
#### Style Experimentation
- Test different style settings
- Find optimal parameters
- Creative exploration
- Style optimization
---
## Multi-Control Combinations
### Overview
Combine multiple control methods for advanced image generation.
### Planned Features
#### Control Combinations
- **Sketch + Style**: Apply style to sketch
- **Structure + Style**: Control structure and style
- **Multiple Sketches**: Combine multiple sketch inputs
- **Layered Control**: Layer multiple control methods
#### Combination Options
- **Control Weights**: Weight different controls
- **Priority Settings**: Set control priorities
- **Blending Modes**: Blend control methods
- **Advanced Parameters**: Fine-tune combinations
### Use Cases
#### Complex Generation
- Multi-control image creation
- Advanced creative projects
- Professional image generation
- Complex visual effects
---
## Integration with Other Modules
### Complete Workflow
Control Studio will integrate with other Image Studio modules:
1. **Create Studio**: Generate base images
2. **Control Studio**: Apply advanced controls
3. **Edit Studio**: Refine controlled images
4. **Upscale Studio**: Enhance resolution
5. **Social Optimizer**: Optimize for platforms
### Use Case Examples
#### Brand Asset Creation
1. Create base image in Create Studio
2. Apply brand style in Control Studio
3. Refine in Edit Studio
4. Upscale in Upscale Studio
5. Optimize in Social Optimizer
#### Artistic Projects
1. Upload sketch
2. Apply artistic style
3. Control structure and composition
4. Refine details
5. Export final artwork
---
## Technical Details (Planned)
### Providers
#### Stability AI
- **Control Endpoints**: Stability AI control methods
- **Sketch Control**: Sketch-to-image endpoints
- **Structure Control**: Structure control endpoints
- **Style Control**: Style transfer endpoints
### Backend Architecture (Planned)
- **ControlStudioService**: Main service for control operations
- **Control Processing**: Control method processing
- **Parameter Management**: Control parameter handling
- **Multi-Control Logic**: Combination logic
### Frontend Components (Planned)
- **ControlStudio.tsx**: Main interface
- **SketchUploader**: Sketch upload component
- **StyleSelector**: Style selection interface
- **ControlSliders**: Parameter adjustment controls
- **PreviewViewer**: Real-time preview
- **StyleLibrary**: Style library browser
---
## Cost Considerations (Estimated)
### Control Operations
- **Base Cost**: Similar to Create Studio operations
- **Complexity Impact**: More complex controls may cost more
- **Provider**: Uses Stability AI (existing endpoints)
- **Estimated**: 3-6 credits per operation
### Cost Factors
- **Control Type**: Different controls have different costs
- **Complexity**: More complex operations cost more
- **Quality**: Higher quality settings may cost more
- **Combinations**: Multi-control may have additional costs
---
## Best Practices (Planned)
### For Sketch-to-Image
1. **Clear Sketches**: Use clear, well-defined sketches
2. **Appropriate Strength**: Match strength to sketch quality
3. **Detailed Prompts**: Provide detailed generation prompts
4. **Test Settings**: Experiment with different strengths
5. **Iterate**: Refine based on results
### For Style Transfer
1. **High-Quality Styles**: Use high-quality style references
2. **Match Content**: Choose styles that match content
3. **Control Strength**: Adjust strength for desired effect
4. **Test Combinations**: Try different style combinations
5. **Preserve Important Elements**: Use selective application
### For Structure Control
1. **Clear Structure**: Use clear structure references
2. **Appropriate Strength**: Balance structure and creativity
3. **Content Matching**: Match content to structure
4. **Test Parameters**: Experiment with settings
5. **Iterate**: Refine based on results
---
## Roadmap
### Phase 1: Basic Controls
- Sketch-to-image
- Basic style transfer
- Structure control
- Simple parameter controls
### Phase 2: Advanced Controls
- Advanced style transfer
- Multi-control combinations
- Style library
- Enhanced parameters
### Phase 3: Refinement
- Performance optimization
- UI improvements
- Advanced features
- Integration enhancements
---
## Getting Updates
Control Studio is currently in planning. To stay updated:
- Check the [Modules Guide](modules.md) for status updates
- Review the [Implementation Overview](implementation-overview.md) for technical progress
- Monitor release notes for availability announcements
---
*Control Studio features are planned for future release. For currently available features, see [Create Studio](create-studio.md), [Edit Studio](edit-studio.md), [Upscale Studio](upscale-studio.md), [Social Optimizer](social-optimizer.md), and [Asset Library](asset-library.md).*

285
docs-site/docs/features/image-studio/cost-guide.md Normal file
View File

@@ -0,0 +1,285 @@
# Image Studio Cost Guide
Image Studio uses a credit-based system for all operations. This guide explains the cost structure, estimation, and optimization strategies.
## Credit System Overview
### How Credits Work
- **Credits**: Virtual currency for Image Studio operations
- **Subscription Tiers**: Different credit allocations per plan
- **Operation Costs**: Each operation consumes credits
- **Pre-Flight Validation**: See costs before executing
- **Transparent Pricing**: Clear cost display for all operations
### Credit Allocation
Credits are allocated based on your subscription tier:
- **Free Tier**: Limited credits for testing
- **Basic Tier**: Standard credit allocation
- **Pro Tier**: Higher credit allocation
- **Enterprise Tier**: Unlimited or very high allocation
## Operation Costs
### Create Studio Costs
#### By Provider
**Stability AI**:
- **Ultra**: 8 credits (highest quality)
- **Core**: 3 credits (standard quality)
- **SD3.5**: Varies (artistic content)
**WaveSpeed**:
- **Ideogram V3**: 5-6 credits (photorealistic)
- **Qwen**: 1-2 credits (fast generation)
**HuggingFace**:
- **FLUX**: Free tier available, then varies
**Gemini**:
- **Imagen**: Free tier available, then varies
#### By Quality Level
- **Draft**: 1-2 credits (fast, low cost)
- **Standard**: 3-5 credits (balanced)
- **Premium**: 6-8 credits (highest quality)
#### Additional Costs
- **Variations**: Each variation adds to base cost
- **Batch Generation**: Cost = base cost × number of variations
- **Dimensions**: Larger images may cost slightly more
### Edit Studio Costs
#### By Operation
- **Remove Background**: 2-3 credits
- **Inpaint**: 3-4 credits
- **Outpaint**: 4-5 credits
- **Search & Replace**: 4-5 credits
- **Search & Recolor**: 4-5 credits
- **Replace Background & Relight**: 5-6 credits
- **General Edit**: 3-5 credits
#### Cost Factors
- **Operation Complexity**: More complex operations cost more
- **Image Size**: Larger images may cost slightly more
- **Provider**: Different providers have different costs
### Upscale Studio Costs
#### By Mode
- **Fast (4x)**: 2 credits (~1 second)
- **Conservative 4K**: 6 credits (preserve style)
- **Creative 4K**: 6 credits (enhance style)
#### Cost Factors
- **Mode Selection**: Different modes have different costs
- **Image Size**: Larger source images may cost slightly more
- **Quality Preset**: Presets don't affect cost
### Social Optimizer Costs
- **Included**: Part of standard Image Studio features
- **No Additional Cost**: Platform optimization is included
- **Efficient**: Batch processing is cost-effective
### Asset Library Costs
- **Free**: No cost for asset management
- **Storage**: Included in subscription
- **Operations**: Only generation/editing operations cost credits
## Cost Estimation
### Pre-Flight Validation
Before any operation, Image Studio shows:
- **Estimated Cost**: Credits required
- **Subscription Check**: Validates your tier
- **Credit Balance**: Shows available credits
- **Cost Breakdown**: Detailed cost information
### Estimation Accuracy
- **Create Studio**: Very accurate (known provider costs)
- **Edit Studio**: Accurate (operation-based costs)
- **Upscale Studio**: Accurate (mode-based costs)
- **Batch Operations**: Cost = base × quantity
### Viewing Estimates
1. **Before Generation**: Cost shown in Create Studio
2. **Before Editing**: Cost shown in Edit Studio
3. **Before Upscaling**: Cost shown in Upscale Studio
4. **Operation Button**: Shows cost estimate
## Cost Optimization Strategies
### For Create Studio
1. **Use Draft for Testing**: Test concepts with low-cost Draft quality
2. **Batch Efficiently**: Generate multiple variations in one request
3. **Choose Appropriate Quality**: Don't use Premium for quick previews
4. **Use Templates**: Templates optimize for cost-effectiveness
5. **Provider Selection**: Use cost-effective providers when appropriate
### For Edit Studio
1. **Edit Strategically**: Only edit when necessary
2. **Combine Operations**: Plan edits to minimize operations
3. **Use Masks Efficiently**: Precise masks reduce need for re-editing
4. **Test First**: Use low-cost operations for testing
### For Upscale Studio
1. **Upscale Selectively**: Only upscale best images
2. **Use Fast Mode**: Fast mode for quick previews
3. **Choose Mode Wisely**: Don't use Creative if Conservative is sufficient
4. **Batch Upscaling**: Process multiple images efficiently
### General Strategies
1. **Plan Ahead**: Estimate costs before starting
2. **Iterate Efficiently**: Test with low-cost options first
3. **Reuse Assets**: Don't regenerate similar content
4. **Monitor Usage**: Track costs in Asset Library
5. **Optimize Workflows**: Use efficient workflow patterns
## Cost Examples
### Example 1: Social Media Campaign
**Scenario**: Create 5 images for Instagram, edit 3, optimize for 3 platforms
**Costs**:
- Create 5 images (Standard): 5 × 4 = 20 credits
- Edit 3 images (Remove Background): 3 × 3 = 9 credits
- Social Optimizer: 0 credits (included)
- **Total**: 29 credits
### Example 2: Blog Featured Image
**Scenario**: Create featured image, upscale, optimize for social
**Costs**:
- Create 1 image (Premium): 6 credits
- Upscale (Conservative): 6 credits
- Social Optimizer: 0 credits (included)
- **Total**: 12 credits
### Example 3: Product Photography
**Scenario**: Create product image, remove background, create 3 color variations
**Costs**:
- Create 1 image (Premium): 6 credits
- Remove Background: 3 credits
- Search & Recolor (3 variations): 3 × 4 = 12 credits
- **Total**: 21 credits
### Example 4: Content Library
**Scenario**: Generate 20 images (Draft), edit 10 favorites, upscale 5 best
**Costs**:
- Create 20 images (Draft): 20 × 2 = 40 credits
- Edit 10 images (various): 10 × 4 = 40 credits
- Upscale 5 images (Fast): 5 × 2 = 10 credits
- **Total**: 90 credits
## Subscription Tiers
### Free Tier
- **Credits**: Limited allocation
- **Best For**: Testing, learning, low-volume
- **Limitations**: Rate limits, basic features
### Basic Tier
- **Credits**: Standard allocation
- **Best For**: Regular use, standard content
- **Features**: Full access to all modules
### Pro Tier
- **Credits**: Higher allocation
- **Best For**: Professional use, high-volume
- **Features**: Premium quality, priority processing
### Enterprise Tier
- **Credits**: Unlimited or very high
- **Best For**: Enterprise, agencies, high-volume
- **Features**: All features, priority support
## Cost Monitoring
### Asset Library Tracking
- **Cost Display**: See cost for each asset
- **Usage Tracking**: Monitor total costs
- **Performance Analysis**: Track cost per asset type
- **Optimization Insights**: Identify cost-saving opportunities
### Best Practices
1. **Regular Review**: Check costs regularly
2. **Identify Patterns**: Find cost-saving patterns
3. **Optimize Workflows**: Adjust workflows based on costs
4. **Plan Budget**: Allocate credits for campaigns
## Cost Optimization Tips
### Quick Wins
1. **Use Draft Quality**: For testing and iterations
2. **Batch Operations**: Process multiple items together
3. **Reuse Assets**: Don't regenerate similar content
4. **Choose Providers Wisely**: Use cost-effective providers
5. **Edit Strategically**: Only edit when necessary
### Advanced Strategies
1. **Workflow Optimization**: Use efficient workflow patterns
2. **Quality Matching**: Match quality to use case
3. **Provider Selection**: Choose providers based on cost/quality
4. **Template Usage**: Use templates for optimization
5. **Asset Reuse**: Build library for future use
## Troubleshooting Costs
### Common Issues
**High Costs**:
- Review quality levels used
- Check number of variations
- Consider using Draft for testing
- Optimize workflows
**Unexpected Costs**:
- Check operation costs before executing
- Review batch operation costs
- Verify subscription tier
- Check credit balance
**Cost Estimation Issues**:
- Verify operation selection
- Check provider costs
- Review quality level
- Confirm batch quantities
## Next Steps
- See [Create Studio Guide](create-studio.md) for generation costs
- Check [Workflow Guide](workflow-guide.md) for cost-efficient workflows
- Review [Providers Guide](providers.md) for provider costs
---
*For technical details, see the [Implementation Overview](implementation-overview.md). For API usage, see the [API Reference](api-reference.md).*

385
docs-site/docs/features/image-studio/create-studio.md Normal file
View File

@@ -0,0 +1,385 @@
# Create Studio User Guide
Create Studio enables you to generate high-quality images from text prompts using multiple AI providers. This guide covers everything you need to know to create stunning visuals for your marketing campaigns.
## Overview
Create Studio is your primary tool for AI-powered image generation. It supports multiple providers, platform templates, style presets, and batch generation to help you create professional visuals quickly and efficiently.
### Key Features
- **Multi-Provider AI**: Access to Stability AI, WaveSpeed, HuggingFace, and Gemini
- **Platform Templates**: Pre-configured templates for Instagram, LinkedIn, Facebook, and more
- **Style Presets**: 40+ built-in styles for different visual aesthetics
- **Batch Generation**: Create 1-10 variations in a single request
- **Cost Estimation**: See costs before generating
- **Prompt Enhancement**: AI-powered prompt improvement
## Getting Started
### Accessing Create Studio
1. Navigate to **Image Studio** from the main dashboard
2. Click on **Create Studio** or go directly to `/image-generator`
3. You'll see the Create Studio interface with prompt input and controls
### Basic Workflow
1. **Enter Your Prompt**: Describe the image you want to create
2. **Select Template** (optional): Choose a platform template for automatic sizing
3. **Choose Quality Level**: Select Draft, Standard, or Premium
4. **Generate**: Click the generate button and wait for results
5. **Review & Download**: View results and download your favorites
## Provider Selection
Create Studio supports multiple AI providers, each with different strengths:
### Stability AI
**Models Available**:
- **Ultra**: Highest quality (8 credits) - Best for premium content
- **Core**: Fast and affordable (3 credits) - Best for standard content
- **SD3.5**: Advanced Stable Diffusion 3.5 (varies) - Best for artistic content
**Best For**:
- Professional photography style
- Detailed artistic images
- High-quality marketing materials
- When you need maximum control
### WaveSpeed Ideogram V3
**Model**: `ideogram-v3-turbo`
**Best For**:
- Photorealistic images
- Images with text (superior text rendering)
- Social media content
- Premium quality visuals
**Advantages**:
- Excellent text rendering in images
- Photorealistic quality
- Fast generation
### WaveSpeed Qwen
**Model**: `qwen-image`
**Best For**:
- Quick iterations
- High-volume content
- Draft generation
- Cost-effective production
**Advantages**:
- Ultra-fast generation (2-3 seconds)
- Low cost
- Good quality for quick previews
### HuggingFace FLUX
**Model**: `black-forest-labs/FLUX.1-Krea-dev`
**Best For**:
- Diverse artistic styles
- Experimental content
- Free tier usage
- Creative variations
### Gemini Imagen
**Model**: `imagen-3.0-generate-001`
**Best For**:
- Google ecosystem integration
- General purpose generation
- Free tier usage
### Auto Selection
When set to "Auto", Create Studio automatically selects the best provider based on:
- **Quality Level**: Draft → Qwen/HuggingFace, Standard → Core/Ideogram, Premium → Ideogram/Ultra
- **Template Recommendations**: Templates can suggest specific providers
- **User Preferences**: Your previous selections
## Platform Templates
Templates automatically configure dimensions, aspect ratios, and provider settings for specific platforms.
### Available Templates
#### Instagram (4 templates)
- **Feed Post (Square)**: 1080x1080 (1:1) - Standard Instagram posts
- **Feed Post (Portrait)**: 1080x1350 (4:5) - Vertical posts
- **Story**: 1080x1920 (9:16) - Instagram Stories
- **Reel Cover**: 1080x1920 (9:16) - Reel thumbnails
#### LinkedIn (4 templates)
- **Post**: 1200x628 (1.91:1) - Standard LinkedIn posts
- **Post (Square)**: 1080x1080 (1:1) - Square posts
- **Article**: 1200x627 (2:1) - Article cover images
- **Company Cover**: 1128x191 (4:1) - Company page banners
#### Facebook (4 templates)
- **Feed Post**: 1200x630 (1.91:1) - Standard feed posts
- **Feed Post (Square)**: 1080x1080 (1:1) - Square posts
- **Story**: 1080x1920 (9:16) - Facebook Stories
- **Cover Photo**: 820x312 (16:9) - Page cover photos
#### Twitter/X (3 templates)
- **Post**: 1200x675 (16:9) - Standard tweets
- **Card**: 1200x600 (2:1) - Twitter cards
- **Header**: 1500x500 (3:1) - Profile headers
#### Other Platforms
- **YouTube**: Thumbnails, Channel Art
- **Pinterest**: Pins, Story Pins
- **TikTok**: Video thumbnails
- **Blog**: Featured images, Headers
- **Email**: Banners, Product images
- **Website**: Hero images, Banners
### Using Templates
1. **Click Template Selector**: Open the template selection panel
2. **Filter by Platform**: Select a platform to see relevant templates
3. **Search Templates**: Use the search bar to find specific templates
4. **Select Template**: Click on a template to apply it
5. **Auto-Configuration**: Dimensions, aspect ratio, and provider are automatically set
### Template Benefits
- **Automatic Sizing**: No need to calculate dimensions manually
- **Platform Optimization**: Optimized for each platform's requirements
- **Provider Recommendations**: Templates suggest the best provider
- **Style Guidance**: Templates include style recommendations
## Quality Levels
Create Studio offers three quality levels that balance speed, cost, and quality:
### Draft
- **Speed**: Fastest (2-5 seconds)
- **Cost**: Lowest (1-2 credits)
- **Providers**: Qwen, HuggingFace
- **Use Case**: Quick previews, iterations, high-volume content
### Standard
- **Speed**: Medium (5-15 seconds)
- **Cost**: Moderate (3-5 credits)
- **Providers**: Stability Core, Ideogram V3
- **Use Case**: Most marketing content, social media posts
### Premium
- **Speed**: Slower (15-30 seconds)
- **Cost**: Highest (6-8 credits)
- **Providers**: Ideogram V3, Stability Ultra
- **Use Case**: Premium campaigns, print materials, featured content
## Writing Effective Prompts
### Prompt Structure
A good prompt includes:
1. **Subject**: What you want to see
2. **Style**: Visual style or aesthetic
3. **Details**: Specific elements, colors, mood
4. **Quality Descriptors**: Professional, high quality, detailed
### Example Prompts
**Basic**:
```
Modern minimalist workspace with laptop
```
**Enhanced**:
```
Modern minimalist workspace with laptop, natural lighting, professional photography, high quality, detailed, clean background
```
**Style-Specific**:
```
Futuristic cityscape at sunset, cinematic lighting, dramatic clouds, 4K quality, professional photography
```
### Prompt Enhancement
Create Studio can automatically enhance your prompts:
- **Enable Prompt Enhancement**: Toggle on in advanced options
- **Style Integration**: Automatically adds style-specific descriptors
- **Quality Boosters**: Adds quality and detail descriptors
### Negative Prompts
Use negative prompts to exclude unwanted elements:
- **Common Exclusions**: "blurry, low quality, distorted, watermark"
- **Style Exclusions**: "cartoon, illustration" (if you want photography)
- **Content Exclusions**: "text, logo, watermark"
## Advanced Options
### Provider Settings
**Manual Provider Selection**:
- Override auto-selection
- Choose specific provider and model
- Useful for testing or specific requirements
**Model Selection**:
- Select specific model within a provider
- Useful for fine-tuning results
### Generation Parameters
**Guidance Scale** (Provider-specific):
- Controls how closely the image follows the prompt
- Higher = more adherence to prompt
- Typical range: 4-10
**Steps** (Provider-specific):
- Number of inference steps
- Higher = better quality but slower
- Typical range: 20-50
**Seed**:
- Random seed for reproducibility
- Same seed + same prompt = same result
- Useful for variations and consistency
### Style Presets
Available style presets:
- **Photographic**: Professional photography style
- **Digital Art**: Digital art, vibrant colors
- **Cinematic**: Film-like, dramatic lighting
- **3D Model**: 3D render style
- **Anime**: Anime/manga style
- **Line Art**: Clean line art
## Batch Generation
Create multiple variations in one request:
### How to Use
1. **Set Variations**: Use the slider to select 1-10 variations
2. **Generate**: All variations are created in one request
3. **Review**: Compare all variations side-by-side
4. **Select**: Choose your favorites
### Use Cases
- **A/B Testing**: Generate multiple options for testing
- **Content Libraries**: Build collections quickly
- **Iterations**: Explore different interpretations
- **Time Saving**: Generate multiple images at once
### Cost Considerations
- Each variation consumes credits
- Batch generation is more cost-effective than individual requests
- Cost is displayed before generation
## Cost Estimation
### Pre-Flight Validation
Before generating, Create Studio shows:
- **Estimated Cost**: Credits required
- **Subscription Check**: Validates your subscription tier
- **Credit Balance**: Shows available credits
### Cost Factors
- **Provider**: Different providers have different costs
- **Quality Level**: Premium costs more than Draft
- **Dimensions**: Larger images may cost more
- **Variations**: Each variation adds to the cost
### Cost Optimization Tips
1. **Use Draft for Iterations**: Test ideas with low-cost Draft quality
2. **Batch Efficiently**: Generate multiple variations in one request
3. **Choose Appropriate Quality**: Don't use Premium for quick previews
4. **Template Optimization**: Templates optimize for cost-effectiveness
## Best Practices
### For Social Media
1. **Use Templates**: Templates ensure correct dimensions
2. **Standard Quality**: Usually sufficient for social media
3. **Batch Generate**: Create multiple options for A/B testing
4. **Text Considerations**: Use Ideogram V3 if you need text in images
### For Marketing Materials
1. **Premium Quality**: Use for important campaigns
2. **Detailed Prompts**: Include specific details about brand, style, mood
3. **Negative Prompts**: Exclude unwanted elements
4. **Consistent Seeds**: Use seeds for brand consistency
### For Content Libraries
1. **Batch Generation**: Generate multiple variations efficiently
2. **Draft First**: Test concepts with Draft quality
3. **Template Variety**: Use different templates for diversity
4. **Organize Results**: Save favorites to Asset Library
### Prompt Writing Tips
1. **Be Specific**: Include details about style, mood, composition
2. **Use Quality Descriptors**: "high quality", "professional", "detailed"
3. **Include Lighting**: "natural lighting", "dramatic lighting", "soft lighting"
4. **Specify Style**: "photographic", "cinematic", "minimalist"
5. **Avoid Ambiguity**: Clear, specific descriptions work best
## Troubleshooting
### Common Issues
**Low Quality Results**:
- Try Premium quality level
- Use a different provider (try Ideogram V3 or Stability Ultra)
- Enhance your prompt with quality descriptors
- Increase guidance scale or steps
**Images Don't Match Prompt**:
- Be more specific in your prompt
- Use negative prompts to exclude unwanted elements
- Try a different provider
- Adjust guidance scale
**Slow Generation**:
- Use Draft quality for faster results
- Try Qwen or HuggingFace providers
- Reduce image dimensions
- Check your internet connection
**High Costs**:
- Use Draft quality for iterations
- Reduce number of variations
- Choose cost-effective providers (Qwen, HuggingFace)
- Use templates for optimization
### Getting Help
- Check the [Providers Guide](providers.md) for provider-specific tips
- Review the [Cost Guide](cost-guide.md) for cost optimization
- See [Workflow Guide](workflow-guide.md) for end-to-end workflows
## Next Steps
After generating images in Create Studio:
1. **Edit**: Use [Edit Studio](edit-studio.md) to refine images
2. **Upscale**: Use [Upscale Studio](upscale-studio.md) to enhance resolution
3. **Optimize**: Use [Social Optimizer](social-optimizer.md) for platform-specific exports
4. **Organize**: Save to [Asset Library](asset-library.md) for easy access
---
*For technical details, see the [Implementation Overview](implementation-overview.md). For API usage, see the [API Reference](api-reference.md).*

404
docs-site/docs/features/image-studio/edit-studio.md Normal file
View File

@@ -0,0 +1,404 @@
# Edit Studio User Guide
Edit Studio provides AI-powered image editing capabilities to enhance, modify, and transform your images. This guide covers all available operations and how to use them effectively.
## Overview
Edit Studio enables you to perform professional-grade image editing using AI. From simple background removal to complex object replacement, Edit Studio makes advanced editing accessible without design software expertise.
### Key Features
- **7 Editing Operations**: Remove background, inpaint, outpaint, search & replace, search & recolor, relight, and general edit
- **Mask Editor**: Visual mask creation for precise control
- **Multiple Inputs**: Support for base images, masks, backgrounds, and lighting references
- **Real-time Preview**: See results before finalizing
- **Provider Flexibility**: Uses Stability AI and HuggingFace for different operations
## Getting Started
### Accessing Edit Studio
1. Navigate to **Image Studio** from the main dashboard
2. Click on **Edit Studio** or go directly to `/image-editor`
3. Upload your base image to begin editing
### Basic Workflow
1. **Upload Base Image**: Select the image you want to edit
2. **Choose Operation**: Select from available editing operations
3. **Configure Settings**: Add prompts, masks, or reference images as needed
4. **Apply Edit**: Click "Apply Edit" to process
5. **Review Results**: Compare original and edited versions
6. **Download**: Save your edited image
## Available Operations
### 1. Remove Background
**Purpose**: Isolate the main subject by removing the background.
**When to Use**:
- Product photography
- Creating transparent PNGs
- Isolating subjects for compositing
- Social media graphics
**How to Use**:
1. Upload your base image
2. Select "Remove Background" operation
3. Click "Apply Edit"
4. The background is automatically removed
**Tips**:
- Works best with clear subject-background separation
- High contrast images produce better results
- Complex backgrounds may require manual cleanup
### 2. Inpaint & Fix
**Purpose**: Edit specific regions by filling or replacing areas using prompts and optional masks.
**When to Use**:
- Remove unwanted objects
- Fix imperfections
- Fill in missing areas
- Replace specific elements
**How to Use**:
1. Upload your base image
2. Select "Inpaint & Fix" operation
3. **Create Mask** (optional but recommended):
- Click "Open Mask Editor"
- Draw over areas you want to edit
- Save the mask
4. **Enter Prompt**: Describe what you want in the edited area
- Example: "clean white wall" or "blue sky with clouds"
5. **Negative Prompt** (optional): Describe what to avoid
6. Click "Apply Edit"
**Mask Tips**:
- Precise masks produce better results
- Include some surrounding area for natural blending
- Use the brush tool for detailed masking
**Prompt Examples**:
- "Remove person, replace with empty space"
- "Fix scratch on car door"
- "Add window to wall"
- "Remove text watermark"
### 3. Outpaint
**Purpose**: Extend the canvas in any direction with AI-generated content.
**When to Use**:
- Extend images beyond original boundaries
- Create wider compositions
- Fix cropped images
- Add context around subjects
**How to Use**:
1. Upload your base image
2. Select "Outpaint" operation
3. **Set Expansion**:
- Use sliders for Left, Right, Up, Down (0-512 pixels)
- Set expansion for each direction
4. **Negative Prompt** (optional): Exclude unwanted elements
5. Click "Apply Edit"
**Expansion Tips**:
- Start with small expansions (50-100px) for best results
- Large expansions may require multiple passes
- Consider the image content when expanding
- Use negative prompts to guide the expansion
**Use Cases**:
- Extend landscape photos
- Add more space around products
- Create wider social media images
- Fix accidentally cropped images
### 4. Search & Replace
**Purpose**: Locate objects via search prompt and replace them with new content. Optional mask for precise control.
**When to Use**:
- Replace objects in images
- Swap products in photos
- Change elements while maintaining context
- Update outdated content
**How to Use**:
1. Upload your base image
2. Select "Search & Replace" operation
3. **Search Prompt**: Describe what to find and replace
- Example: "red car" to find a red car
4. **Prompt**: Describe the replacement
- Example: "blue car" to replace with a blue car
5. **Mask** (optional): Use mask editor for precise region selection
6. Click "Apply Edit"
**Prompt Examples**:
- Search: "old phone", Replace: "modern smartphone"
- Search: "winter trees", Replace: "spring trees with flowers"
- Search: "wooden table", Replace: "glass table"
**Tips**:
- Be specific in search prompts
- Use masks for better precision
- Consider lighting and perspective in replacements
### 5. Search & Recolor
**Purpose**: Select elements via prompt and recolor them. Optional mask for exact region selection.
**When to Use**:
- Change colors of specific objects
- Create color variations
- Match brand colors
- Experiment with color schemes
**How to Use**:
1. Upload your base image
2. Select "Search & Recolor" operation
3. **Select Prompt**: Describe what to recolor
- Example: "red dress" or "blue car"
4. **Prompt**: Describe the new color
- Example: "green dress" or "yellow car"
5. **Mask** (optional): Use mask editor for precise selection
6. Click "Apply Edit"
**Prompt Examples**:
- Select: "red shirt", Recolor: "blue shirt"
- Select: "green grass", Recolor: "autumn brown grass"
- Select: "white wall", Recolor: "beige wall"
**Tips**:
- Be specific about what to recolor
- Consider lighting and shadows
- Use masks for complex selections
### 6. Replace Background & Relight
**Purpose**: Swap backgrounds and adjust lighting using reference images.
**When to Use**:
- Change photo backgrounds
- Match lighting between subjects and backgrounds
- Create composite images
- Professional product photography
**How to Use**:
1. Upload your base image (subject)
2. Select "Replace Background & Relight" operation
3. **Upload Background Image**: Reference image for new background
4. **Upload Lighting Image** (optional): Reference for lighting style
5. Click "Apply Edit"
**Tips**:
- Use high-quality background images
- Match perspective and angle when possible
- Lighting reference helps create realistic composites
- Consider subject-background compatibility
### 7. General Edit / Prompt-based Edit
**Purpose**: Make general edits to images using natural language prompts. Optional mask for targeted editing.
**When to Use**:
- General image modifications
- Style changes
- Atmosphere adjustments
- Creative transformations
**How to Use**:
1. Upload your base image
2. Select "General Edit" operation
3. **Enter Prompt**: Describe the desired changes
- Example: "make it more vibrant and colorful"
- Example: "add warm sunset lighting"
- Example: "convert to black and white with high contrast"
4. **Mask** (optional): Use mask editor to target specific areas
5. **Negative Prompt** (optional): Exclude unwanted changes
6. Click "Apply Edit"
**Prompt Examples**:
- "Add dramatic lighting with shadows"
- "Make colors more saturated and vibrant"
- "Convert to vintage film style"
- "Add fog and atmosphere"
- "Enhance details and sharpness"
**Tips**:
- Be descriptive in your prompts
- Use masks for localized edits
- Combine with negative prompts for better control
## Mask Editor
The Mask Editor is a powerful tool for precise editing control. It allows you to visually define areas to edit.
### Accessing the Mask Editor
1. Select an operation that supports masks (Inpaint, Search & Replace, Search & Recolor, General Edit)
2. Click "Open Mask Editor" button
3. The mask editor opens in a dialog
### Using the Mask Editor
**Drawing Masks**:
- **Brush Tool**: Paint over areas you want to edit
- **Eraser Tool**: Remove mask areas
- **Brush Size**: Adjust brush size for precision
- **Zoom**: Zoom in/out for detailed work
**Mask Tips**:
- **Precise Masks**: Draw exactly over areas to edit
- **Soft Edges**: Include some surrounding area for natural blending
- **Multiple Passes**: You can refine masks after seeing results
- **Save Masks**: Masks can be reused for similar edits
**When to Use Masks**:
- **Inpaint**: Define areas to fill or replace
- **Search & Replace**: Target specific regions
- **Search & Recolor**: Select exact elements to recolor
- **General Edit**: Apply edits to specific areas only
## Image Uploads
Edit Studio supports multiple image inputs:
### Base Image
- **Required**: Always needed
- **Purpose**: The main image to edit
- **Formats**: JPG, PNG
- **Size**: Recommended under 10MB for best performance
### Mask Image
- **Optional**: For operations that support masks
- **Purpose**: Define areas to edit
- **Creation**: Use Mask Editor or upload existing mask
- **Format**: PNG with transparency
### Background Image
- **Optional**: For Replace Background & Relight
- **Purpose**: Reference for new background
- **Tips**: Match perspective and lighting when possible
### Lighting Image
- **Optional**: For Replace Background & Relight
- **Purpose**: Reference for lighting style
- **Tips**: Use images with desired lighting characteristics
## Advanced Options
### Negative Prompts
Use negative prompts to exclude unwanted elements or effects:
**Common Negative Prompts**:
- "blurry, low quality, distorted"
- "watermark, text, logo"
- "oversaturated, unrealistic colors"
- "artifacts, noise, compression"
**Operation-Specific**:
- **Outpaint**: "people, buildings, text" (to avoid adding unwanted elements)
- **Inpaint**: "blurry edges, artifacts" (to ensure clean fills)
- **General Edit**: "oversaturated, unrealistic" (to maintain natural look)
### Provider Settings
**Stability AI** (default for most operations):
- High quality results
- Reliable performance
- Good for professional editing
**HuggingFace** (for general edits):
- Alternative provider
- Good for creative edits
- Free tier available
## Best Practices
### For Product Photography
1. **Remove Background**: Use for clean product isolation
2. **Replace Background**: Use for different scene contexts
3. **Inpaint**: Remove unwanted elements or reflections
4. **Search & Replace**: Swap product variations
### For Social Media
1. **Remove Background**: Create transparent PNGs for graphics
2. **Outpaint**: Extend images for different aspect ratios
3. **Search & Recolor**: Match brand colors
4. **General Edit**: Apply consistent style across images
### For Photo Editing
1. **Inpaint**: Remove unwanted objects or people
2. **Outpaint**: Fix cropped images
3. **Search & Replace**: Update outdated elements
4. **General Edit**: Enhance overall image quality
### Prompt Writing Tips
1. **Be Specific**: Clear, detailed prompts work best
2. **Use Context**: Reference surrounding elements
3. **Consider Style**: Match the existing image style
4. **Test Iteratively**: Refine prompts based on results
### Mask Creation Tips
1. **Precision**: Draw exactly over target areas
2. **Soft Edges**: Include some surrounding area
3. **Multiple Objects**: Create separate masks for different objects
4. **Refinement**: Adjust masks after seeing initial results
## Troubleshooting
### Common Issues
**Poor Quality Results**:
- Try a different operation
- Use more specific prompts
- Create precise masks
- Adjust negative prompts
**Unwanted Changes**:
- Use negative prompts to exclude elements
- Create more precise masks
- Be more specific in prompts
- Try a different operation
**Mask Not Working**:
- Ensure mask covers the correct area
- Check mask format (should be PNG with transparency)
- Verify operation supports masks
- Try recreating the mask
**Slow Processing**:
- Large images take longer
- Complex operations require more time
- Check your internet connection
- Try reducing image size
### Getting Help
- Check operation-specific tips above
- Review the [Workflow Guide](workflow-guide.md) for common workflows
- See [Implementation Overview](implementation-overview.md) for technical details
## Next Steps
After editing images in Edit Studio:
1. **Upscale**: Use [Upscale Studio](upscale-studio.md) to enhance resolution
2. **Optimize**: Use [Social Optimizer](social-optimizer.md) for platform-specific exports
3. **Organize**: Save to [Asset Library](asset-library.md) for easy access
4. **Create More**: Use [Create Studio](create-studio.md) to generate new images
---
*For technical details, see the [Implementation Overview](implementation-overview.md). For API usage, see the [API Reference](api-reference.md).*

517
docs-site/docs/features/image-studio/implementation-overview.md Normal file
View File

@@ -0,0 +1,517 @@
# Image Studio Implementation Overview
This document provides a technical overview of the Image Studio implementation, including architecture, backend services, frontend components, and data flow.
## Architecture Overview
Image Studio follows a modular architecture with clear separation between backend services, API endpoints, and frontend components.
```mermaid
graph TB
subgraph "Frontend"
UI[Image Studio UI Components]
Hooks[React Hooks]
end
subgraph "API Layer"
Router[Image Studio Router]
Auth[Authentication Middleware]
end
subgraph "Service Layer"
Manager[ImageStudioManager]
Create[CreateStudioService]
Edit[EditStudioService]
Upscale[UpscaleStudioService]
Social[SocialOptimizerService]
Control[ControlStudioService]
end
subgraph "Providers"
Stability[Stability AI]
WaveSpeed[WaveSpeed AI]
HuggingFace[HuggingFace]
Gemini[Gemini]
end
subgraph "Storage"
Assets[Asset Library]
Files[File Storage]
end
UI --> Hooks
Hooks --> Router
Router --> Auth
Auth --> Manager
Manager --> Create
Manager --> Edit
Manager --> Upscale
Manager --> Social
Manager --> Control
Create --> Stability
Create --> WaveSpeed
Create --> HuggingFace
Create --> Gemini
Edit --> Stability
Upscale --> Stability
Manager --> Assets
Create --> Files
Edit --> Files
Upscale --> Files
```
## Backend Architecture
### Service Layer
#### ImageStudioManager
**Location**: `backend/services/image_studio/studio_manager.py`
The main orchestration service that coordinates all Image Studio operations.
**Responsibilities**:
- Initialize all module services
- Route requests to appropriate services
- Provide unified interface for all operations
- Manage templates and platform specifications
- Cost estimation and validation
**Key Methods**:
- `create_image()`: Delegate to CreateStudioService
- `edit_image()`: Delegate to EditStudioService
- `upscale_image()`: Delegate to UpscaleStudioService
- `optimize_for_social()`: Delegate to SocialOptimizerService
- `get_templates()`: Retrieve available templates
- `get_platform_formats()`: Get platform-specific formats
- `estimate_cost()`: Calculate operation costs
#### CreateStudioService
**Location**: `backend/services/image_studio/create_service.py`
Handles image generation with multi-provider support.
**Features**:
- Provider selection (auto or manual)
- Template-based generation
- Prompt enhancement
- Batch generation (1-10 variations)
- Quality level mapping
- Persona support
**Provider Support**:
- Stability AI (Ultra, Core, SD3.5)
- WaveSpeed (Ideogram V3, Qwen)
- HuggingFace (FLUX models)
- Gemini (Imagen)
#### EditStudioService
**Location**: `backend/services/image_studio/edit_service.py`
Manages image editing operations.
**Operations**:
- Remove background
- Inpaint & Fix
- Outpaint
- Search & Replace
- Search & Recolor
- General Edit
**Features**:
- Optional mask support
- Multiple input handling (base, mask, background, lighting)
- Provider abstraction
- Operation metadata
#### UpscaleStudioService
**Location**: `backend/services/image_studio/upscale_service.py`
Handles image upscaling operations.
**Modes**:
- Fast 4x upscale
- Conservative 4K upscale
- Creative 4K upscale
**Features**:
- Quality presets
- Optional prompt support
- Provider-specific optimization
#### SocialOptimizerService
**Location**: `backend/services/image_studio/social_optimizer_service.py`
Optimizes images for social media platforms.
**Features**:
- Platform format specifications
- Smart cropping algorithms
- Safe zone visualization
- Batch export
- Image processing with PIL
**Supported Platforms**:
- Instagram, Facebook, Twitter, LinkedIn, YouTube, Pinterest, TikTok
#### ControlStudioService
**Location**: `backend/services/image_studio/control_service.py`
Advanced generation controls (planned).
**Planned Features**:
- Sketch-to-image
- Style transfer
- Structure control
### Template System
**Location**: `backend/services/image_studio/templates.py`
**Components**:
- `TemplateManager`: Manages template loading and retrieval
- `ImageTemplate`: Template data structure
- `Platform`: Platform enumeration
- `TemplateCategory`: Category enumeration
**Template Structure**:
- Platform-specific dimensions
- Aspect ratios
- Style recommendations
- Provider suggestions
- Quality settings
### API Layer
#### Image Studio Router
**Location**: `backend/routers/image_studio.py`
**Endpoints**:
##### Create Studio
- `POST /api/image-studio/create` - Generate images
- `GET /api/image-studio/templates` - Get templates
- `GET /api/image-studio/templates/search` - Search templates
- `GET /api/image-studio/templates/recommend` - Get recommendations
- `GET /api/image-studio/providers` - Get available providers
##### Edit Studio
- `POST /api/image-studio/edit` - Edit images
- `GET /api/image-studio/edit/operations` - List available operations
##### Upscale Studio
- `POST /api/image-studio/upscale` - Upscale images
##### Social Optimizer
- `POST /api/image-studio/social/optimize` - Optimize for social platforms
- `GET /api/image-studio/social/platforms/{platform}/formats` - Get platform formats
##### Utility
- `POST /api/image-studio/estimate-cost` - Estimate operation costs
- `GET /api/image-studio/platform-specs/{platform}` - Get platform specifications
- `GET /api/image-studio/health` - Health check
**Authentication**:
- All endpoints require authentication via `get_current_user` middleware
- User ID validation for all operations
**Error Handling**:
- Comprehensive error messages
- Provider fallback logic
- Retry mechanisms
- Logging for debugging
## Frontend Architecture
### Component Structure
```
frontend/src/components/ImageStudio/
├── ImageStudioLayout.tsx # Shared layout wrapper
├── ImageStudioDashboard.tsx # Main dashboard
├── CreateStudio.tsx # Image generation
├── EditStudio.tsx # Image editing
├── UpscaleStudio.tsx # Image upscaling
├── SocialOptimizer.tsx # Social optimization
├── AssetLibrary.tsx # Asset management
├── TemplateSelector.tsx # Template selection
├── ImageResultsGallery.tsx # Results display
├── EditImageUploader.tsx # Image upload
├── ImageMaskEditor.tsx # Mask creation
├── EditOperationsToolbar.tsx # Operation selection
├── EditResultViewer.tsx # Edit results
├── CostEstimator.tsx # Cost calculation
└── ui/ # Shared UI components
├── GlassyCard.tsx
├── SectionHeader.tsx
├── StatusChip.tsx
├── LoadingSkeleton.tsx
└── AsyncStatusBanner.tsx
```
### Shared Components
#### ImageStudioLayout
**Purpose**: Consistent layout wrapper for all Image Studio modules
**Features**:
- Unified navigation
- Consistent styling
- Responsive design
- Glassmorphic theme
#### Shared UI Components
- **GlassyCard**: Glassmorphic card component
- **SectionHeader**: Consistent section headers
- **StatusChip**: Status indicators
- **LoadingSkeleton**: Loading states
- **AsyncStatusBanner**: Async operation status
### React Hooks
#### useImageStudio
**Location**: `frontend/src/hooks/useImageStudio.ts`
**Functions**:
- `generateImage()`: Create images
- `processEdit()`: Edit images
- `processUpscale()`: Upscale images
- `optimizeForSocial()`: Optimize for social platforms
- `getPlatformFormats()`: Get platform formats
- `loadEditOperations()`: Load available edit operations
- `estimateCost()`: Estimate operation costs
**State Management**:
- Loading states
- Error handling
- Result caching
- Cost tracking
#### useContentAssets
**Location**: `frontend/src/hooks/useContentAssets.ts`
**Functions**:
- `getAssets()`: Fetch assets with filters
- `toggleFavorite()`: Mark/unmark favorites
- `deleteAsset()`: Delete assets
- `trackUsage()`: Track asset usage
- `refetch()`: Refresh asset list
## Data Flow
### Image Generation Flow
```mermaid
sequenceDiagram
participant User
participant Frontend
participant API
participant Manager
participant Service
participant Provider
participant Storage
User->>Frontend: Enter prompt, select template
Frontend->>API: POST /api/image-studio/create
API->>Manager: create_image(request)
Manager->>Service: generate(request)
Service->>Service: Select provider
Service->>Service: Enhance prompt (optional)
Service->>Provider: Generate image
Provider-->>Service: Image result
Service->>Storage: Save to asset library
Service-->>Manager: Return result
Manager-->>API: Return response
API-->>Frontend: Return image data
Frontend->>User: Display results
```
### Image Editing Flow
```mermaid
sequenceDiagram
participant User
participant Frontend
participant API
participant Manager
participant Service
participant Provider
participant Storage
User->>Frontend: Upload image, select operation
Frontend->>API: POST /api/image-studio/edit
API->>Manager: edit_image(request)
Manager->>Service: process_edit(request)
Service->>Service: Validate operation
Service->>Service: Prepare inputs (mask, background, etc.)
Service->>Provider: Execute edit operation
Provider-->>Service: Edited image
Service->>Storage: Save to asset library
Service-->>Manager: Return result
Manager-->>API: Return response
API-->>Frontend: Return edited image
Frontend->>User: Display results
```
### Social Optimization Flow
```mermaid
sequenceDiagram
participant User
participant Frontend
participant API
participant Manager
participant Service
participant Storage
User->>Frontend: Upload image, select platforms
Frontend->>API: POST /api/image-studio/social/optimize
API->>Manager: optimize_for_social(request)
Manager->>Service: optimize_image(request)
Service->>Service: Load platform formats
Service->>Service: Process each platform
Service->>Service: Resize and crop
Service->>Service: Apply safe zones (optional)
Service->>Storage: Save optimized images
Service-->>Manager: Return results
Manager-->>API: Return response
API-->>Frontend: Return optimized images
Frontend->>User: Display results grid
```
## Provider Integration
### Stability AI
- **Endpoints**: Multiple endpoints for generation, editing, upscaling
- **Authentication**: API key based
- **Rate Limiting**: Credit-based system
- **Error Handling**: Retry logic with exponential backoff
### WaveSpeed AI
- **Endpoints**: Image generation (Ideogram V3, Qwen)
- **Authentication**: API key based
- **Rate Limiting**: Request-based
- **Error Handling**: Standard HTTP error responses
### HuggingFace
- **Endpoints**: FLUX model inference
- **Authentication**: API token based
- **Rate Limiting**: Free tier limits
- **Error Handling**: Standard HTTP error responses
### Gemini
- **Endpoints**: Imagen generation
- **Authentication**: API key based
- **Rate Limiting**: Quota-based
- **Error Handling**: Standard HTTP error responses
## Asset Management
### Content Asset Service
**Location**: `backend/services/content_asset_service.py`
**Features**:
- Automatic asset tracking
- Search and filtering
- Favorites management
- Usage tracking
- Bulk operations
### Asset Tracking
**Location**: `backend/utils/asset_tracker.py`
**Integration Points**:
- Image Studio: All generated/edited images
- Story Writer: Scene images, audio, videos
- Blog Writer: Generated images
- Other modules: All ALwrity tools
## Cost Management
### Cost Estimation
- Pre-flight validation before operations
- Real-time cost calculation
- Credit system integration
- Subscription tier validation
### Credit System
- Operations consume credits based on complexity
- Provider-specific credit costs
- Quality level affects credit consumption
- Batch operations aggregate costs
## Error Handling
### Backend Error Handling
- Comprehensive error messages
- Provider fallback logic
- Retry mechanisms
- Detailed logging
### Frontend Error Handling
- User-friendly error messages
- Retry options
- Error state management
- Graceful degradation
## Performance Optimization
### Backend
- Async operations for long-running tasks
- Caching for templates and platform specs
- Connection pooling for providers
- Efficient image processing
### Frontend
- Lazy loading of components
- Image optimization
- Result caching
- Debounced search
## Security
### Authentication
- All endpoints require authentication
- User ID validation
- Subscription checks
### Data Protection
- Secure API key storage
- Base64 encoding for images
- File validation
- Size limits
## Testing
### Backend Testing
- Unit tests for services
- Integration tests for API endpoints
- Provider mock testing
- Error scenario testing
### Frontend Testing
- Component unit tests
- Hook testing
- Integration tests
- E2E tests for workflows
## Deployment
### Backend
- FastAPI application
- Environment-based configuration
- Docker containerization
- Health check endpoints
### Frontend
- React application
- Build optimization
- CDN deployment
- Route configuration
---
*For API reference, see [API Reference](api-reference.md). For module-specific guides, see the individual module documentation.*

432
docs-site/docs/features/image-studio/modules.md Normal file
View File

@@ -0,0 +1,432 @@
# Image Studio Modules
Image Studio consists of 7 core modules that provide a complete image workflow from creation to optimization. This guide provides detailed information about each module, their features, and current implementation status.
## Module Overview
| Module | Status | Route | Description |
|--------|-------|-------|-------------|
| **Create Studio** | ✅ Live | `/image-generator` | Generate images from text prompts |
| **Edit Studio** | ✅ Live | `/image-editor` | AI-powered image editing |
| **Upscale Studio** | ✅ Live | `/image-upscale` | Enhance image resolution |
| **Social Optimizer** | ✅ Live | `/image-studio/social-optimizer` | Optimize for social platforms |
| **Asset Library** | ✅ Live | `/image-studio/asset-library` | Unified content archive |
| **Transform Studio** | 🚧 Planned | - | Convert images to videos/avatars |
| **Control Studio** | 🚧 Planned | - | Advanced generation controls |
---
## 1. Create Studio ✅
**Status**: Fully implemented and live
**Route**: `/image-generator`
### Overview
Create Studio enables you to generate high-quality images from text prompts using multiple AI providers. It includes platform templates, style presets, and batch generation capabilities.
### Key Features
#### Multi-Provider Support
- **Stability AI**: Ultra (highest quality), Core (fast & affordable), SD3.5 (advanced)
- **WaveSpeed Ideogram V3**: Photorealistic images with superior text rendering
- **WaveSpeed Qwen**: Ultra-fast generation (2-3 seconds)
- **HuggingFace**: FLUX models for diverse styles
- **Gemini**: Google's Imagen models
#### Platform Templates
- **Instagram**: Feed posts (square, portrait), Stories, Reels
- **LinkedIn**: Post images, article covers, company banners
- **Facebook**: Feed posts, Stories, cover photos
- **Twitter/X**: Post images, header images
- **YouTube**: Thumbnails, channel art
- **Pinterest**: Pins, board covers
- **TikTok**: Video thumbnails
- **Blog**: Featured images, article headers
- **Email**: Newsletter headers, promotional images
- **Website**: Hero images, section backgrounds
#### Style Presets
40+ built-in styles including:
- Photographic
- Digital Art
- 3D Model
- Anime
- Cinematic
- Oil Painting
- Watercolor
- And many more...
#### Advanced Features
- **Batch Generation**: Create 1-10 variations in one request
- **Prompt Enhancement**: AI-powered prompt improvement
- **Cost Estimation**: See costs before generating
- **Quality Levels**: Draft, Standard, Premium
- **Advanced Controls**: Guidance scale, steps, seed for fine-tuning
- **Persona Support**: Generate content aligned with brand personas
### Use Cases
- Social media campaign visuals
- Blog post featured images
- Product photography
- Marketing materials
- Brand assets
- Content library building
### Backend Components
- `CreateStudioService`: Generation logic
- `ImageStudioManager`: Orchestration
- Template system with platform specifications
### Frontend Components
- `CreateStudio.tsx`: Main interface
- `TemplateSelector.tsx`: Template selection
- `ImageResultsGallery.tsx`: Results display
- `CostEstimator.tsx`: Cost calculation
---
## 2. Edit Studio ✅
**Status**: Fully implemented and live
**Route**: `/image-editor`
### Overview
Edit Studio provides AI-powered image editing capabilities including background operations, object manipulation, and conversational editing.
### Available Operations
#### Background Operations
- **Remove Background**: Extract subjects with transparent backgrounds
- **Replace Background**: Change backgrounds with proper lighting
- **Relight**: Adjust lighting to match new backgrounds
#### Object Manipulation
- **Erase**: Remove unwanted objects from images
- **Inpaint**: Fill or replace specific areas with AI
- **Outpaint**: Expand images beyond original boundaries
- **Search & Replace**: Replace objects using text prompts
- **Search & Recolor**: Change colors using text prompts
#### General Editing
- **General Edit**: Prompt-based editing with optional mask support
- **Mask Editor**: Visual mask creation for precise control
### Key Features
- **Reusable Mask Editor**: Create and reuse masks across operations
- **Optional Masking**: Use masks for `general_edit`, `search_replace`, `search_recolor`
- **Multiple Input Support**: Base image, mask, background, and lighting references
- **Real-time Preview**: See results before applying
- **Operation-Specific Fields**: Dynamic UI based on selected operation
### Use Cases
- Remove unwanted objects
- Change backgrounds
- Fix imperfections
- Add or modify elements
- Adjust colors
- Extend image canvas
### Backend Components
- `EditStudioService`: Editing logic
- Stability AI integration
- HuggingFace integration
### Frontend Components
- `EditStudio.tsx`: Main interface
- `ImageMaskEditor.tsx`: Mask creation tool
- `EditImageUploader.tsx`: Image upload interface
- `EditOperationsToolbar.tsx`: Operation selection
---
## 3. Upscale Studio ✅
**Status**: Fully implemented and live
**Route**: `/image-upscale`
### Overview
Upscale Studio enhances image resolution using AI-powered upscaling with multiple modes and quality presets.
### Upscaling Modes
#### Fast Upscale
- **Speed**: ~1 second
- **Quality**: 4x upscaling
- **Use Case**: Quick previews, web display
- **Cost**: 2 credits
#### Conservative Upscale
- **Quality**: 4K resolution
- **Style**: Preserves original style
- **Use Case**: Professional printing, high-quality display
- **Cost**: 6 credits
- **Optional Prompt**: Guide the upscaling process
#### Creative Upscale
- **Quality**: 4K resolution
- **Style**: Enhances and improves style
- **Use Case**: Artistic enhancement, style improvement
- **Cost**: 6 credits
- **Optional Prompt**: Guide creative enhancements
### Key Features
- **Quality Presets**: Web, print, social media optimizations
- **Side-by-Side Comparison**: Before/after preview with synchronized zoom
- **Prompt Support**: Optional prompts for conservative/creative modes
- **Real-time Preview**: See results immediately
- **Metadata Display**: View upscaling details
### Use Cases
- Enhance low-resolution images
- Prepare images for printing
- Improve image quality for display
- Upscale product photos
- Enhance social media images
### Backend Components
- `UpscaleStudioService`: Upscaling logic
- Stability AI upscaling endpoints
### Frontend Components
- `UpscaleStudio.tsx`: Main interface
- Comparison viewer with zoom
---
## 4. Social Optimizer ✅
**Status**: Fully implemented and live
**Route**: `/image-studio/social-optimizer`
### Overview
Social Optimizer automatically resizes and optimizes images for all major social media platforms with smart cropping and safe zone visualization.
### Supported Platforms
- **Instagram**: Feed posts (square, portrait), Stories, Reels
- **Facebook**: Feed posts, Stories, cover photos
- **Twitter/X**: Post images, header images
- **LinkedIn**: Post images, article covers, company banners
- **YouTube**: Thumbnails, channel art
- **Pinterest**: Pins, board covers
- **TikTok**: Video thumbnails
### Key Features
#### Platform Formats
- **Multiple Formats per Platform**: Choose from various format options
- **Automatic Sizing**: Platform-specific dimensions
- **Format Selection**: Pick the best format for your content
#### Crop Modes
- **Smart Crop**: Preserve important content with intelligent cropping
- **Center Crop**: Crop from center
- **Fit**: Fit with padding
#### Safe Zones
- **Visual Overlays**: Display text-safe areas
- **Platform-Specific**: Safe zones tailored to each platform
- **Toggle Display**: Show/hide safe zones
#### Batch Export
- **Multi-Platform**: Generate optimized versions for multiple platforms
- **Single Source**: One image → all platforms
- **Individual Downloads**: Download specific formats
- **Bulk Download**: Download all optimized images at once
### Use Cases
- Social media campaigns
- Multi-platform content distribution
- Brand consistency across platforms
- Time-saving batch optimization
### Backend Components
- `SocialOptimizerService`: Optimization logic
- Platform format specifications
- Image processing and resizing
### Frontend Components
- `SocialOptimizer.tsx`: Main interface
- Platform selector
- Format selection
- Results grid
---
## 5. Asset Library ✅
**Status**: Fully implemented and live
**Route**: `/image-studio/asset-library`
### Overview
Asset Library is a unified content archive that tracks all AI-generated content (images, videos, audio, text) across all ALwrity modules.
### Key Features
#### Search & Filtering
- **Advanced Search**: Search by ID, model, keywords
- **Type Filtering**: Filter by image, video, audio, text
- **Module Filtering**: Filter by source module (Image Studio, Story Writer, Blog Writer, etc.)
- **Status Filtering**: Filter by completion status
- **Date Filtering**: Filter by creation date
- **Favorites Filter**: Show only favorited assets
#### Organization
- **Favorites**: Mark and organize favorite assets
- **Collections**: Organize assets into collections (coming soon)
- **Tags**: AI-powered tagging (coming soon)
- **Version History**: Track asset versions (coming soon)
#### Views
- **Grid View**: Visual card-based layout
- **List View**: Detailed table layout with all metadata
- **Toggle Views**: Switch between grid and list views
#### Bulk Operations
- **Bulk Download**: Download multiple assets at once
- **Bulk Delete**: Delete multiple assets
- **Bulk Share**: Share multiple assets (coming soon)
#### Usage Tracking
- **Download Count**: Track asset downloads
- **Share Count**: Track asset shares
- **Usage Analytics**: Monitor asset performance
#### Asset Information
- **Metadata Display**: View provider, model, cost, generation time
- **Status Indicators**: Visual status chips (completed, processing, failed)
- **Source Module**: Identify which ALwrity tool created the asset
- **Creation Date**: Timestamp of asset creation
### Integration
Assets are automatically tracked from:
- **Image Studio**: All generated and edited images
- **Story Writer**: Scene images, audio, videos
- **Blog Writer**: Generated images
- **LinkedIn Writer**: Generated content
- **Other Modules**: All ALwrity tools
### Use Cases
- Organize campaign assets
- Find previously generated content
- Track content usage
- Manage brand assets
- Archive content library
### Backend Components
- `ContentAssetService`: Asset management
- Database models for asset storage
- Search and filtering logic
### Frontend Components
- `AssetLibrary.tsx`: Main interface
- Search and filter controls
- Grid and list views
- Bulk operation tools
---
## 6. Transform Studio 🚧
**Status**: Planned for future release
### Overview
Transform Studio will enable conversion of images into videos, creation of talking avatars, and generation of 3D models.
### Planned Features
#### Image-to-Video
- **WaveSpeed WAN 2.5**: Convert static images to dynamic videos
- **Resolutions**: 480p, 720p, 1080p
- **Duration**: Up to 10 seconds
- **Audio Support**: Add audio/voiceover
- **Social Optimization**: Optimize for social platforms
#### Make Avatar
- **Hunyuan Avatar**: Create talking avatars from photos
- **Audio-Driven**: Lip-sync with audio input
- **Duration**: Up to 2 minutes
- **Emotion Control**: Adjust avatar expressions
- **Resolutions**: 480p, 720p
#### Image-to-3D
- **Stable Fast 3D**: Generate 3D models from images
- **Export Formats**: Standard 3D formats
- **Quality Options**: Multiple quality levels
### Use Cases
- Product showcases
- Social media videos
- Explainer videos
- Personal branding
- Marketing campaigns
---
## 7. Control Studio 🚧
**Status**: Planned for future release
### Overview
Control Studio will provide advanced generation controls for fine-grained image creation.
### Planned Features
#### Sketch-to-Image
- **Control Strength**: Adjust how closely the image follows the sketch
- **Style Transfer**: Apply styles to sketches
- **Multiple Sketches**: Combine multiple control inputs
#### Style Transfer
- **Style Library**: Pre-built style library
- **Custom Styles**: Upload custom style images
- **Strength Control**: Adjust style application intensity
#### Structure Control
- **Pose Control**: Control human poses
- **Depth Control**: Control depth information
- **Edge Control**: Control edge detection
### Use Cases
- Precise image generation
- Style consistency
- Brand-aligned visuals
- Advanced creative control
---
## Module Dependencies
### Infrastructure
- **ImageStudioManager**: Orchestrates all modules
- **Shared UI Components**: Consistent interface across modules
- **Cost Estimation**: Unified cost calculation
- **Authentication**: User validation for all operations
### Data Flow
1. User selects module
2. Module-specific UI loads
3. User provides input (prompt, image, settings)
4. Pre-flight validation (cost, subscription)
5. Operation executes
6. Results displayed
7. Asset saved to Asset Library (if applicable)
---
## Module Status Summary
### ✅ Implemented (5/7)
- Create Studio
- Edit Studio
- Upscale Studio
- Social Optimizer
- Asset Library
### 🚧 Planned (2/7)
- Transform Studio
- Control Studio
---
*For detailed guides on each module, see the module-specific documentation: [Create Studio](create-studio.md), [Edit Studio](edit-studio.md), [Upscale Studio](upscale-studio.md), [Social Optimizer](social-optimizer.md), [Asset Library](asset-library.md).*

225
docs-site/docs/features/image-studio/overview.md Normal file
View File

@@ -0,0 +1,225 @@
# Image Studio Overview
The ALwrity Image Studio is a comprehensive AI-powered image creation, editing, and optimization platform designed specifically for digital marketers and content creators. It provides a unified hub for all image-related operations, from generation to social media optimization, making professional visual content creation accessible to everyone.
## What is Image Studio?
Image Studio is ALwrity's centralized platform that consolidates all image operations into one seamless workflow. It combines existing AI capabilities (Stability AI, HuggingFace, Gemini) with new WaveSpeed AI features to provide a complete image creation, editing, and optimization solution.
### Key Benefits
- **Unified Platform**: All image operations in one place - no need to switch between multiple tools
- **Complete Workflow**: Create → Edit → Upscale → Optimize → Export in a single interface
- **Multi-Provider AI**: Access to Stability AI, WaveSpeed (Ideogram V3, Qwen), HuggingFace, and Gemini
- **Social Media Ready**: One-click optimization for all major platforms
- **Professional Quality**: Enterprise-grade results without the complexity
- **Cost-Effective**: Subscription-based pricing with transparent cost estimation
## Target Users
### Primary: Digital Marketers & Content Creators
- Need professional visuals for campaigns
- Require platform-optimized content
- Want to scale content production
- Value time and cost efficiency
### Secondary: Solopreneurs & Small Businesses
- Can't afford dedicated designers
- Need DIY professional images
- Require consistent brand visuals
- Want to reduce content creation costs
### Tertiary: Content Teams & Agencies
- Manage multiple client campaigns
- Need batch processing capabilities
- Require asset organization
- Want collaborative workflows
## Core Modules
Image Studio consists of **7 core modules** that cover the complete image workflow:
### 1. **Create Studio** ✅
Generate stunning images from text prompts using multiple AI providers. Features include platform templates, style presets, batch generation, and cost estimation.
**Status**: Fully implemented and live
**Route**: `/image-generator`
### 2. **Edit Studio** ✅
AI-powered image editing with operations like background removal, inpainting, outpainting, object replacement, and color transformation. Includes a reusable mask editor.
**Status**: Fully implemented and live
**Route**: `/image-editor`
### 3. **Upscale Studio** ✅
Enhance image resolution with fast 4x upscaling, conservative 4K upscaling, and creative 4K upscaling. Includes quality presets and side-by-side comparison.
**Status**: Fully implemented and live
**Route**: `/image-upscale`
### 4. **Social Optimizer** ✅
Optimize images for all major social platforms (Instagram, Facebook, Twitter, LinkedIn, YouTube, Pinterest, TikTok) with smart cropping, safe zones, and batch export.
**Status**: Fully implemented and live
**Route**: `/image-studio/social-optimizer`
### 5. **Asset Library** ✅
Unified content archive for all ALwrity tools. Features include search, filtering, favorites, bulk operations, and usage tracking across all generated content.
**Status**: Fully implemented and live
**Route**: `/image-studio/asset-library`
### 6. **Transform Studio** 🚧
Convert images into videos, create talking avatars, and generate 3D models. Features include image-to-video, make avatar, and image-to-3D capabilities.
**Status**: Planned for future release
### 7. **Control Studio** 🚧
Advanced generation controls including sketch-to-image, style transfer, and structure control. Provides fine-grained control over image generation.
**Status**: Planned for future release
## Key Features
### AI-Powered Generation
- **Multi-Provider Support**: Stability AI (Ultra/Core/SD3), WaveSpeed (Ideogram V3, Qwen), HuggingFace, Gemini
- **Platform Templates**: Pre-configured templates for Instagram, LinkedIn, Facebook, Twitter, and more
- **Style Presets**: 40+ built-in styles (photographic, digital-art, 3d-model, etc.)
- **Batch Generation**: Create 1-10 variations in a single request
- **Prompt Enhancement**: AI-powered prompt improvement for better results
### Professional Editing
- **Background Operations**: Remove, replace, or relight backgrounds
- **Object Manipulation**: Erase, inpaint, outpaint, search & replace, search & recolor
- **Mask Editor**: Visual mask creation for precise editing control
- **Conversational Editing**: Natural language image modifications
### Quality Enhancement
- **Fast Upscaling**: 4x upscaling in ~1 second
- **4K Upscaling**: Conservative and creative modes for different use cases
- **Quality Presets**: Web, print, and social media optimizations
- **Comparison Tools**: Side-by-side before/after previews
### Social Media Optimization
- **Platform Formats**: Automatic sizing for all major platforms
- **Smart Cropping**: Preserve important content with intelligent cropping
- **Safe Zones**: Visual overlays for text-safe areas
- **Batch Export**: Generate optimized versions for multiple platforms simultaneously
### Asset Management
- **Unified Archive**: All generated content in one place
- **Advanced Search**: Filter by type, module, date, status, and more
- **Favorites**: Mark and organize favorite assets
- **Bulk Operations**: Download, delete, or share multiple assets at once
- **Usage Tracking**: Monitor asset usage and performance
## How It Works
### Complete Workflow
```mermaid
flowchart TD
A[Start: Idea or Prompt] --> B[Create Studio]
B --> C{Need Editing?}
C -->|Yes| D[Edit Studio]
C -->|No| E{Need Upscaling?}
D --> E
E -->|Yes| F[Upscale Studio]
E -->|No| G{Social Media?}
F --> G
G -->|Yes| H[Social Optimizer]
G -->|No| I[Asset Library]
H --> I
I --> J[Export & Use]
style A fill:#e3f2fd
style B fill:#e8f5e8
style D fill:#fff3e0
style F fill:#fce4ec
style H fill:#f1f8e9
style I fill:#e0f2f1
style J fill:#f3e5f5
```
### Typical Use Cases
#### 1. Social Media Campaign
1. **Create**: Generate campaign visuals using platform templates
2. **Edit**: Remove backgrounds or adjust colors
3. **Optimize**: Export for Instagram, Facebook, LinkedIn simultaneously
4. **Organize**: Save to Asset Library for easy access
#### 2. Blog Post Images
1. **Create**: Generate featured images with blog post templates
2. **Upscale**: Enhance resolution for high-quality display
3. **Optimize**: Resize for social media sharing
4. **Track**: Monitor usage in Asset Library
#### 3. Product Photography
1. **Create**: Generate product images with specific styles
2. **Edit**: Remove backgrounds or add product variations
3. **Transform**: Convert to video for product showcases (coming soon)
4. **Export**: Optimize for e-commerce platforms
## Technical Architecture
### Backend Services
- **ImageStudioManager**: Main orchestration service
- **CreateStudioService**: Image generation logic
- **EditStudioService**: Image editing operations
- **UpscaleStudioService**: Resolution enhancement
- **SocialOptimizerService**: Platform optimization
- **ContentAssetService**: Asset management
### Frontend Components
- **ImageStudioLayout**: Shared layout wrapper
- **CreateStudio**: Image generation interface
- **EditStudio**: Image editing interface
- **UpscaleStudio**: Upscaling interface
- **SocialOptimizer**: Social media optimization
- **AssetLibrary**: Asset management interface
### API Endpoints
- `POST /api/image-studio/create` - Generate images
- `POST /api/image-studio/edit` - Edit images
- `POST /api/image-studio/upscale` - Upscale images
- `POST /api/image-studio/social/optimize` - Optimize for social media
- `GET /api/content-assets/` - Access asset library
## Getting Started
### Quick Start
1. Navigate to Image Studio from the main dashboard
2. Choose a module based on your needs (Create, Edit, Upscale, etc.)
3. Follow the module-specific guides for detailed instructions
4. Access your generated assets in the Asset Library
### Next Steps
- Read the [Modules Guide](modules.md) for detailed module information
- Check the [Implementation Overview](implementation-overview.md) for technical details
- Explore module-specific guides for Create, Edit, Upscale, Social Optimizer, and Asset Library
- Review the [Workflow Guide](workflow-guide.md) for end-to-end workflows
## Cost Management
Image Studio uses a credit-based system with transparent cost estimation:
- **Pre-Flight Validation**: See costs before generating
- **Credit System**: Operations consume credits based on complexity
- **Cost Estimation**: Real-time cost calculation for all operations
- **Subscription Tiers**: Different credit allocations per plan
For detailed cost information, see the [Cost Guide](cost-guide.md).
## Support & Resources
- **Documentation**: Comprehensive guides for each module
- **API Reference**: Complete API documentation
- **Provider Guide**: When to use each AI provider
- **Template Library**: Available templates and presets
- **Best Practices**: Tips for optimal results
---
*For more information, explore the module-specific documentation or check the [API Reference](api-reference.md).*

360
docs-site/docs/features/image-studio/providers.md Normal file
View File

@@ -0,0 +1,360 @@
# Image Studio Providers Guide
Image Studio supports multiple AI providers, each with unique strengths. This guide helps you choose the right provider for your needs.
## Provider Overview
Image Studio integrates with four major AI providers:
- **Stability AI**: Professional-grade generation and editing
- **WaveSpeed**: Photorealistic and fast generation
- **HuggingFace**: Diverse styles and free tier
- **Gemini**: Google's Imagen models
## Stability AI
### Overview
Stability AI provides professional-grade image generation and editing with multiple model options.
### Available Models
#### Stability Ultra
- **Quality**: Highest quality generation
- **Cost**: 8 credits
- **Speed**: 15-30 seconds
- **Best For**: Premium campaigns, print materials, featured content
#### Stability Core
- **Quality**: Fast and affordable
- **Cost**: 3 credits
- **Speed**: 5-15 seconds
- **Best For**: Standard content, social media, general use
#### SD3.5 Large
- **Quality**: Advanced Stable Diffusion 3.5
- **Cost**: Varies
- **Speed**: 10-20 seconds
- **Best For**: Artistic content, creative projects
### Strengths
- **Professional Quality**: Enterprise-grade results
- **Editing Capabilities**: Full editing suite (25+ operations)
- **Reliability**: Consistent, high-quality output
- **Control**: Advanced parameters (guidance, steps, seed)
### Use Cases
- Professional marketing materials
- High-quality social media content
- Print-ready images
- Detailed product photography
- Brand assets
### When to Choose
- You need highest quality
- Professional/business use
- Detailed, realistic images
- Editing operations needed
---
## WaveSpeed
### Overview
WaveSpeed provides two models: Ideogram V3 for photorealistic images and Qwen for fast generation.
### Ideogram V3 Turbo
#### Characteristics
- **Quality**: Photorealistic with superior text rendering
- **Cost**: 5-6 credits
- **Speed**: 10-20 seconds
- **Best For**: Social media, blog images, marketing content
#### Strengths
- **Text in Images**: Best text rendering among all providers
- **Photorealistic**: Highly realistic images
- **Style**: Modern, professional aesthetic
- **Consistency**: Reliable results
#### Use Cases
- Social media posts with text
- Blog featured images
- Marketing materials
- Product showcases
- Brand content
#### When to Choose
- You need text in images
- Photorealistic quality required
- Social media content
- Modern, professional style
### Qwen Image
#### Characteristics
- **Quality**: Good quality, fast generation
- **Cost**: 1-2 credits
- **Speed**: 2-3 seconds (ultra-fast)
- **Best For**: Quick iterations, high-volume content, drafts
#### Strengths
- **Speed**: Fastest generation
- **Cost-Effective**: Lowest cost option
- **Good Quality**: Decent results for speed
- **Iterations**: Perfect for testing concepts
#### Use Cases
- Quick previews
- High-volume content
- Draft generation
- Concept testing
- Rapid iterations
#### When to Choose
- Speed is priority
- Testing concepts
- High-volume needs
- Cost optimization
---
## HuggingFace
### Overview
HuggingFace provides FLUX models with diverse artistic styles and free tier access.
### Available Models
#### FLUX.1-Krea-dev
- **Quality**: Diverse artistic styles
- **Cost**: Free tier available
- **Speed**: 10-20 seconds
- **Best For**: Creative projects, artistic content, experimentation
### Strengths
- **Free Tier**: No cost for basic usage
- **Diverse Styles**: Wide range of artistic styles
- **Creative**: Good for experimental content
- **Accessibility**: Easy to use
### Use Cases
- Creative projects
- Artistic content
- Experimental generation
- Free tier usage
- Diverse style needs
### When to Choose
- You want free tier access
- Creative/artistic content
- Experimentation
- Diverse style requirements
---
## Gemini
### Overview
Google's Gemini provides Imagen models with good general-purpose generation.
### Available Models
#### Imagen 3.0
- **Quality**: Good general quality
- **Cost**: Free tier available
- **Speed**: 10-20 seconds
- **Best For**: General purpose, Google ecosystem integration
### Strengths
- **Free Tier**: No cost for basic usage
- **Google Integration**: Works with Google services
- **General Purpose**: Good for various use cases
- **Reliability**: Consistent results
### Use Cases
- General purpose generation
- Google ecosystem integration
- Free tier usage
- Standard content needs
### When to Choose
- You need free tier access
- Google ecosystem integration
- General purpose content
- Standard quality sufficient
---
## Provider Comparison
### Quality Comparison
| Provider | Quality Level | Best For |
|----------|--------------|----------|
| **Stability Ultra** | Highest | Premium campaigns, print |
| **Ideogram V3** | Very High | Photorealistic, text in images |
| **Stability Core** | High | Standard content |
| **SD3.5** | High | Artistic content |
| **FLUX** | Medium-High | Creative/artistic |
| **Imagen** | Medium-High | General purpose |
| **Qwen** | Medium | Fast iterations |
### Speed Comparison
| Provider | Speed | Use Case |
|----------|-------|----------|
| **Qwen** | 2-3 seconds | Fastest, quick previews |
| **Stability Core** | 5-15 seconds | Fast standard generation |
| **Ideogram V3** | 10-20 seconds | Balanced quality/speed |
| **Stability Ultra** | 15-30 seconds | Highest quality |
| **FLUX/Imagen** | 10-20 seconds | Standard generation |
### Cost Comparison
| Provider | Cost (Credits) | Value |
|----------|---------------|-------|
| **Qwen** | 1-2 | Best value for speed |
| **HuggingFace** | Free tier | Best for free usage |
| **Gemini** | Free tier | Good free option |
| **Stability Core** | 3 | Good value for quality |
| **Ideogram V3** | 5-6 | Premium quality |
| **Stability Ultra** | 8 | Highest quality |
## Provider Selection Guide
### By Use Case
#### Social Media Content
- **Primary**: Ideogram V3 (text in images, photorealistic)
- **Alternative**: Stability Core (fast, reliable)
- **Budget**: Qwen (fast, cost-effective)
#### Blog Featured Images
- **Primary**: Ideogram V3 or Stability Core
- **Alternative**: Stability Ultra (premium quality)
- **Budget**: HuggingFace or Gemini (free tier)
#### Product Photography
- **Primary**: Stability Ultra (highest quality)
- **Alternative**: Ideogram V3 (photorealistic)
- **Budget**: Stability Core (good quality)
#### Marketing Materials
- **Primary**: Stability Ultra or Ideogram V3
- **Alternative**: Stability Core
- **Budget**: Qwen for iterations, Premium for final
#### Creative/Artistic
- **Primary**: SD3.5 or FLUX
- **Alternative**: Stability Core with style presets
- **Budget**: HuggingFace (free tier)
### By Quality Level
#### Draft Quality
- **Recommended**: Qwen, HuggingFace, Gemini
- **Use**: Quick previews, iterations, testing
#### Standard Quality
- **Recommended**: Stability Core, Ideogram V3
- **Use**: Most content, social media, general use
#### Premium Quality
- **Recommended**: Stability Ultra, Ideogram V3
- **Use**: Important campaigns, print, featured content
### By Budget
#### Free Tier
- **Options**: HuggingFace, Gemini
- **Limitations**: Rate limits, basic features
- **Best For**: Testing, learning, low-volume
#### Cost-Effective
- **Options**: Qwen, Stability Core
- **Balance**: Good quality at lower cost
- **Best For**: High-volume, standard content
#### Premium
- **Options**: Stability Ultra, Ideogram V3
- **Investment**: Higher cost, highest quality
- **Best For**: Important campaigns, professional use
## Auto Selection
When set to "Auto", Create Studio selects providers based on:
### Quality-Based Selection
- **Draft**: Qwen, HuggingFace
- **Standard**: Stability Core, Ideogram V3
- **Premium**: Ideogram V3, Stability Ultra
### Template Recommendations
- Templates can suggest specific providers
- Based on platform and use case
- Optimized for best results
### User Preferences
- Learns from your selections
- Adapts to your workflow
- Optimizes for your needs
## Best Practices
### Provider Selection
1. **Start with Auto**: Let system choose initially
2. **Test Providers**: Try different providers for same prompt
3. **Match to Use Case**: Choose based on specific needs
4. **Consider Cost**: Balance quality and cost
5. **Iterate Efficiently**: Use fast providers for testing
### Quality Management
1. **Draft First**: Test with fast, low-cost providers
2. **Upgrade for Final**: Use premium providers for final versions
3. **Compare Results**: Test multiple providers
4. **Learn Preferences**: Note which providers work best for you
### Cost Optimization
1. **Use Free Tier**: HuggingFace/Gemini for testing
2. **Fast Iterations**: Qwen for quick previews
3. **Standard for Most**: Stability Core for general use
4. **Premium Selectively**: Ultra only for important content
## Troubleshooting
### Provider-Specific Issues
**Stability AI**:
- Slower but highest quality
- Best for professional use
- Good editing capabilities
**WaveSpeed Ideogram V3**:
- Best for text in images
- Photorealistic results
- Good for social media
**WaveSpeed Qwen**:
- Fastest generation
- Good for iterations
- Cost-effective
**HuggingFace**:
- Free tier available
- Diverse styles
- Good for experimentation
**Gemini**:
- Free tier available
- Google integration
- General purpose
## Next Steps
- See [Create Studio Guide](create-studio.md) for provider usage
- Check [Cost Guide](cost-guide.md) for cost details
- Review [Workflow Guide](workflow-guide.md) for provider selection in workflows
---
*For technical details, see the [Implementation Overview](implementation-overview.md). For API usage, see the [API Reference](api-reference.md).*

283
docs-site/docs/features/image-studio/social-optimizer.md Normal file
View File

@@ -0,0 +1,283 @@
# Social Optimizer User Guide
Social Optimizer automatically resizes and optimizes images for all major social media platforms. This guide covers platform formats, crop modes, and batch export functionality.
## Overview
Social Optimizer eliminates the manual work of resizing images for different platforms. Upload one image and get optimized versions for Instagram, Facebook, LinkedIn, Twitter, YouTube, Pinterest, and TikTok - all in one click.
### Key Features
- **7 Platform Support**: Instagram, Facebook, Twitter, LinkedIn, YouTube, Pinterest, TikTok
- **Multiple Formats per Platform**: Choose from various format options
- **Smart Cropping**: Preserve important content with intelligent cropping
- **Safe Zones**: Visual overlays for text-safe areas
- **Batch Export**: Generate optimized versions for multiple platforms simultaneously
- **Individual Downloads**: Download specific formats as needed
## Getting Started
### Accessing Social Optimizer
1. Navigate to **Image Studio** from the main dashboard
2. Click on **Social Optimizer** or go directly to `/image-studio/social-optimizer`
3. Upload your source image to begin
### Basic Workflow
1. **Upload Source Image**: Select the image you want to optimize
2. **Select Platforms**: Choose one or more platforms
3. **Choose Formats**: Select specific formats for each platform
4. **Set Options**: Configure crop mode and safe zones
5. **Optimize**: Click "Optimize Images" to process
6. **Review Results**: View optimized images in grid
7. **Download**: Download individual or all optimized images
## Supported Platforms
### Instagram
**Available Formats**:
- **Feed Post (Square)**: 1080x1080 (1:1) - Standard square posts
- **Feed Post (Portrait)**: 1080x1350 (4:5) - Vertical posts
- **Story**: 1080x1920 (9:16) - Instagram Stories
- **Reel**: 1080x1920 (9:16) - Reel covers
**Best For**: Visual content, product showcases, brand posts
### Facebook
**Available Formats**:
- **Feed Post**: 1200x630 (1.91:1) - Standard feed posts
- **Feed Post (Square)**: 1080x1080 (1:1) - Square posts
- **Story**: 1080x1920 (9:16) - Facebook Stories
- **Cover Photo**: 820x312 (16:9) - Page cover photos
**Best For**: Business pages, community posts, announcements
### Twitter/X
**Available Formats**:
- **Post**: 1200x675 (16:9) - Standard tweets
- **Card**: 1200x600 (2:1) - Twitter cards
- **Header**: 1500x500 (3:1) - Profile headers
**Best For**: News, updates, engagement posts
### LinkedIn
**Available Formats**:
- **Post**: 1200x628 (1.91:1) - Standard LinkedIn posts
- **Post (Square)**: 1080x1080 (1:1) - Square posts
- **Article**: 1200x627 (2:1) - Article cover images
- **Company Cover**: 1128x191 (4:1) - Company page banners
**Best For**: Professional content, B2B marketing, thought leadership
### YouTube
**Available Formats**:
- **Thumbnail**: 1280x720 (16:9) - Video thumbnails
- **Channel Art**: 2560x1440 (16:9) - Channel banners
**Best For**: Video content, channel branding
### Pinterest
**Available Formats**:
- **Pin**: 1000x1500 (2:3) - Standard pins
- **Story Pin**: 1080x1920 (9:16) - Pinterest Stories
**Best For**: Visual discovery, product showcases, tutorials
### TikTok
**Available Formats**:
- **Video Cover**: 1080x1920 (9:16) - Video thumbnails
**Best For**: Short-form video content, trends
## Crop Modes
Social Optimizer offers three crop modes to handle different aspect ratios:
### Smart Crop
**Purpose**: Preserve important content with intelligent cropping
**How It Works**:
- Analyzes image composition
- Identifies important elements
- Crops to preserve focal points
- Maintains visual balance
**When to Use**:
- Images with clear subjects
- Product photography
- Portraits
- When content preservation is priority
**Best For**: Most use cases, especially when you want to preserve important elements
### Center Crop
**Purpose**: Crop from the center of the image
**How It Works**:
- Crops from image center
- Maintains aspect ratio
- Simple and predictable
**When to Use**:
- Centered compositions
- Symmetrical images
- When center content is most important
**Best For**: Centered subjects, symmetrical designs
### Fit
**Purpose**: Fit image with padding if needed
**How It Works**:
- Fits entire image within dimensions
- Adds padding if aspect ratios don't match
- Preserves full image content
**When to Use**:
- When you need the full image
- Complex compositions
- When padding is acceptable
**Best For**: Images where full content is essential
## Safe Zones
Safe zones indicate areas where text will be visible and not cut off on different platforms.
### What Are Safe Zones?
Safe zones are visual overlays that show:
- **Text-Safe Areas**: Where text will be visible
- **Platform-Specific**: Different zones for each platform
- **Visual Guides**: Help you position important content
### Using Safe Zones
1. **Enable Safe Zones**: Toggle "Show Safe Zones" option
2. **View Overlays**: See safe zone boundaries on optimized images
3. **Position Content**: Ensure important elements are within safe zones
4. **Text Placement**: Place text within safe zones for visibility
### Platform-Specific Safe Zones
Each platform has different safe zone requirements:
- **Instagram Stories**: Top 25%, bottom 15% safe zones
- **Facebook Stories**: Similar to Instagram
- **YouTube Thumbnails**: Center area for text
- **Pinterest Pins**: Top and bottom safe zones
## Batch Export
Generate optimized versions for multiple platforms in one operation:
### How to Use
1. **Select Multiple Platforms**: Check boxes for desired platforms
2. **Choose Formats**: Select formats for each platform
3. **Set Options**: Configure crop mode and safe zones
4. **Optimize**: Click "Optimize Images"
5. **Review Grid**: See all optimized images in grid view
6. **Download All**: Use "Download All" button for bulk download
### Use Cases
- **Multi-Platform Campaigns**: One image for all platforms
- **Time Saving**: Generate all sizes at once
- **Consistency**: Same image across platforms
- **Efficiency**: Single operation for multiple exports
## Best Practices
### For Multi-Platform Campaigns
1. **Start with High Resolution**: Use high-quality source images
2. **Select All Platforms**: Generate for all relevant platforms
3. **Use Smart Crop**: Preserve important content
4. **Enable Safe Zones**: Ensure text visibility
5. **Review All Formats**: Check each optimized version
### For Platform-Specific Content
1. **Choose Single Platform**: Focus on one platform
2. **Select Best Format**: Choose format that matches content
3. **Optimize Crop Mode**: Use appropriate crop mode
4. **Test Display**: Verify on actual platform
### For Product Photography
1. **Use Smart Crop**: Preserve product details
2. **Enable Safe Zones**: Keep products visible
3. **Multiple Formats**: Generate for different use cases
4. **High Quality Source**: Start with high-resolution images
### For Social Media Posts
1. **Batch Export**: Generate for all platforms at once
2. **Consistent Branding**: Use same image across platforms
3. **Format Selection**: Choose formats that match content type
4. **Safe Zones**: Ensure text and branding are visible
## Troubleshooting
### Common Issues
**Images Look Cropped Wrong**:
- Try different crop mode (Smart vs Center vs Fit)
- Check source image composition
- Adjust crop mode based on content
- Use Fit mode if full image is needed
**Text Gets Cut Off**:
- Enable safe zones to see text-safe areas
- Reposition content within safe zones
- Use Fit mode to preserve full image
- Check platform-specific requirements
**Quality Issues**:
- Use high-resolution source images
- Check optimized image dimensions
- Verify platform requirements
- Consider upscaling source image first
**Slow Processing**:
- Multiple platforms take longer
- Large source images increase processing time
- Check internet connection
- Processing is typically fast (<10 seconds)
### Getting Help
- Check platform-specific tips above
- Review the [Workflow Guide](workflow-guide.md) for common workflows
- See [Implementation Overview](implementation-overview.md) for technical details
## Cost Considerations
Social Optimizer is included in Image Studio operations:
- **No Additional Cost**: Part of standard Image Studio features
- **Efficient Processing**: Optimized for performance
- **Batch Savings**: Process multiple platforms in one operation
## Next Steps
After optimizing images in Social Optimizer:
1. **Download**: Save optimized images
2. **Organize**: Save to [Asset Library](asset-library.md) for easy access
3. **Use**: Upload to your social media platforms
4. **Track**: Monitor performance across platforms
---
*For technical details, see the [Implementation Overview](implementation-overview.md). For API usage, see the [API Reference](api-reference.md).*

334
docs-site/docs/features/image-studio/templates.md Normal file
View File

@@ -0,0 +1,334 @@
# Image Studio Templates Guide
Templates automatically configure dimensions, aspect ratios, and provider settings for specific platforms and use cases. This guide covers all available templates and how to use them effectively.
## Overview
Templates eliminate the need to manually calculate dimensions and configure settings. Simply select a template, and Image Studio automatically sets up everything for optimal results on your target platform.
### Key Benefits
- **Automatic Sizing**: No manual dimension calculations
- **Platform Optimization**: Optimized for each platform's requirements
- **Provider Recommendations**: Templates suggest best providers
- **Style Guidance**: Templates include style recommendations
- **Time Saving**: Quick setup for common use cases
## Template System
### How Templates Work
1. **Select Template**: Choose from available templates
2. **Auto-Configuration**: Dimensions, aspect ratio, and settings are applied
3. **Provider Suggestion**: Best provider is recommended
4. **Generate**: Create images with optimal settings
### Template Components
Each template includes:
- **Dimensions**: Width and height in pixels
- **Aspect Ratio**: Platform-appropriate aspect ratio
- **Provider Recommendation**: Suggested AI provider
- **Style Preset**: Recommended style (if applicable)
- **Use Cases**: When to use this template
## Platform Templates
### Instagram Templates
#### Feed Post (Square)
- **Dimensions**: 1080x1080 (1:1)
- **Use Case**: Standard Instagram feed posts
- **Best For**: Product showcases, brand posts, general content
- **Provider**: Ideogram V3 or Stability Core
#### Feed Post (Portrait)
- **Dimensions**: 1080x1350 (4:5)
- **Use Case**: Vertical Instagram posts
- **Best For**: Portraits, tall products, vertical compositions
- **Provider**: Ideogram V3 or Stability Core
#### Story
- **Dimensions**: 1080x1920 (9:16)
- **Use Case**: Instagram Stories
- **Best For**: Vertical content, announcements, behind-the-scenes
- **Provider**: Ideogram V3
- **Note**: Consider safe zones for text
#### Reel Cover
- **Dimensions**: 1080x1920 (9:16)
- **Use Case**: Instagram Reel thumbnails
- **Best For**: Video thumbnails, engaging visuals
- **Provider**: Ideogram V3
### LinkedIn Templates
#### Post
- **Dimensions**: 1200x628 (1.91:1)
- **Use Case**: Standard LinkedIn feed posts
- **Best For**: Professional content, B2B marketing, thought leadership
- **Provider**: Ideogram V3 or Stability Core
#### Post (Square)
- **Dimensions**: 1080x1080 (1:1)
- **Use Case**: Square LinkedIn posts
- **Best For**: Visual content, infographics, brand posts
- **Provider**: Ideogram V3
#### Article
- **Dimensions**: 1200x627 (2:1)
- **Use Case**: LinkedIn article cover images
- **Best For**: Article headers, long-form content
- **Provider**: Stability Core or Ideogram V3
#### Company Cover
- **Dimensions**: 1128x191 (4:1)
- **Use Case**: LinkedIn company page banners
- **Best For**: Company branding, page headers
- **Provider**: Stability Core
- **Note**: Very wide format, consider text placement
### Facebook Templates
#### Feed Post
- **Dimensions**: 1200x630 (1.91:1)
- **Use Case**: Standard Facebook feed posts
- **Best For**: General posts, announcements, engagement
- **Provider**: Ideogram V3 or Stability Core
#### Feed Post (Square)
- **Dimensions**: 1080x1080 (1:1)
- **Use Case**: Square Facebook posts
- **Best For**: Visual content, product showcases
- **Provider**: Ideogram V3
#### Story
- **Dimensions**: 1080x1920 (9:16)
- **Use Case**: Facebook Stories
- **Best For**: Vertical content, temporary posts
- **Provider**: Ideogram V3
- **Note**: Consider safe zones
#### Cover Photo
- **Dimensions**: 820x312 (16:9)
- **Use Case**: Facebook page cover photos
- **Best For**: Page branding, headers
- **Provider**: Stability Core
- **Note**: Wide format, consider text placement
### Twitter/X Templates
#### Post
- **Dimensions**: 1200x675 (16:9)
- **Use Case**: Standard Twitter/X posts
- **Best For**: News, updates, general content
- **Provider**: Ideogram V3 or Stability Core
#### Card
- **Dimensions**: 1200x600 (2:1)
- **Use Case**: Twitter card images
- **Best For**: Link previews, article shares
- **Provider**: Ideogram V3
#### Header
- **Dimensions**: 1500x500 (3:1)
- **Use Case**: Twitter/X profile headers
- **Best For**: Profile branding, headers
- **Provider**: Stability Core
- **Note**: Very wide format
### YouTube Templates
#### Thumbnail
- **Dimensions**: 1280x720 (16:9)
- **Use Case**: YouTube video thumbnails
- **Best For**: Video thumbnails, engaging visuals
- **Provider**: Ideogram V3
- **Note**: Thumbnails need to be eye-catching
#### Channel Art
- **Dimensions**: 2560x1440 (16:9)
- **Use Case**: YouTube channel banners
- **Best For**: Channel branding, headers
- **Provider**: Stability Core
- **Note**: High resolution for large displays
### Pinterest Templates
#### Pin
- **Dimensions**: 1000x1500 (2:3)
- **Use Case**: Standard Pinterest pins
- **Best For**: Visual discovery, product showcases, tutorials
- **Provider**: Ideogram V3
- **Note**: Vertical format works best
#### Story Pin
- **Dimensions**: 1080x1920 (9:16)
- **Use Case**: Pinterest Stories
- **Best For**: Vertical content, temporary posts
- **Provider**: Ideogram V3
### TikTok Templates
#### Video Cover
- **Dimensions**: 1080x1920 (9:16)
- **Use Case**: TikTok video thumbnails
- **Best For**: Video covers, engaging visuals
- **Provider**: Ideogram V3
- **Note**: Vertical format, eye-catching design
### Blog Templates
#### Header
- **Dimensions**: 1200x628 (1.91:1)
- **Use Case**: Blog post featured images
- **Best For**: Article headers, featured images
- **Provider**: Ideogram V3 or Stability Core
#### Header Wide
- **Dimensions**: 1920x1080 (16:9)
- **Use Case**: Wide blog headers
- **Best For**: Full-width headers, hero images
- **Provider**: Stability Core
### Email Templates
#### Banner
- **Dimensions**: 600x200 (3:1)
- **Use Case**: Email newsletter banners
- **Best For**: Email headers, promotional banners
- **Provider**: Stability Core
- **Note**: Consider email client compatibility
#### Product Image
- **Dimensions**: 600x600 (1:1)
- **Use Case**: Email product images
- **Best For**: Product showcases in emails
- **Provider**: Ideogram V3
### Website Templates
#### Hero Image
- **Dimensions**: 1920x1080 (16:9)
- **Use Case**: Website hero sections
- **Best For**: Landing pages, homepage headers
- **Provider**: Stability Core or Ideogram V3
#### Banner
- **Dimensions**: 1200x400 (3:1)
- **Use Case**: Website banners
- **Best For**: Section headers, promotional banners
- **Provider**: Stability Core
## Using Templates
### Template Selection
1. **Open Template Selector**: Click template button in Create Studio
2. **Filter by Platform**: Select platform to see relevant templates
3. **Search Templates**: Use search to find specific templates
4. **Select Template**: Click template to apply it
5. **Auto-Configuration**: Settings are automatically applied
### Template Benefits
**Time Saving**:
- No manual dimension calculations
- Instant optimal settings
- Quick platform setup
**Optimization**:
- Platform-specific dimensions
- Optimal aspect ratios
- Provider recommendations
**Consistency**:
- Standard sizes across content
- Brand consistency
- Professional appearance
## Template Best Practices
### For Social Media
1. **Use Platform Templates**: Always use templates for social media
2. **Match Content Type**: Choose template that matches your content
3. **Consider Format**: Square vs. portrait vs. landscape
4. **Test Display**: Verify on actual platform
### For Marketing
1. **Consistent Sizing**: Use same templates across campaigns
2. **Platform Optimization**: Optimize for each platform
3. **Brand Alignment**: Ensure templates match brand guidelines
4. **Quality Settings**: Use Premium for important campaigns
### For Content Libraries
1. **Template Variety**: Use different templates for diversity
2. **Platform Coverage**: Generate for all relevant platforms
3. **Reusability**: Create assets that work across platforms
4. **Organization**: Tag by template type in Asset Library
## Template Recommendations
### By Content Type
#### Product Photography
- **Instagram**: Feed Post (Square) or Feed Post (Portrait)
- **Facebook**: Feed Post or Feed Post (Square)
- **Pinterest**: Pin
- **E-commerce**: Blog Header or Website Hero
#### Social Media Posts
- **Instagram**: Feed Post (Square) or Story
- **LinkedIn**: Post
- **Facebook**: Feed Post
- **Twitter**: Post
#### Blog Content
- **Featured Image**: Blog Header
- **Social Sharing**: Instagram Feed Post (Square)
- **Article Cover**: LinkedIn Article
#### Brand Assets
- **Profile Headers**: Twitter Header, LinkedIn Company Cover
- **Cover Photos**: Facebook Cover, YouTube Channel Art
- **Banners**: Website Banner, Email Banner
## Custom Templates (Coming Soon)
Future feature for creating custom templates:
- Save your own template configurations
- Share templates with team
- Brand-specific templates
- Custom dimensions and settings
## Troubleshooting
### Template Issues
**Wrong Dimensions**:
- Verify template selection
- Check platform requirements
- Use correct template for platform
**Quality Issues**:
- Adjust quality level
- Try different provider
- Check template recommendations
**Format Mismatch**:
- Verify template matches use case
- Check aspect ratio requirements
- Consider alternative templates
## Next Steps
- See [Create Studio Guide](create-studio.md) for template usage
- Check [Workflow Guide](workflow-guide.md) for template workflows
- Review [Social Optimizer](social-optimizer.md) for platform optimization
---
*For technical details, see the [Implementation Overview](implementation-overview.md). For API usage, see the [API Reference](api-reference.md).*

388
docs-site/docs/features/image-studio/transform-studio.md Normal file
View File

@@ -0,0 +1,388 @@
# Transform Studio Guide (Planned)
Transform Studio will enable conversion of images into videos, creation of talking avatars, and generation of 3D models. This guide covers the planned features and capabilities.
## Status
**Current Status**: 🚧 Planned for future release
**Priority**: High - Major differentiator feature
**Estimated Release**: Coming soon
## Overview
Transform Studio extends Image Studio's capabilities beyond static images, enabling you to create dynamic video content and 3D models from your images. This module will provide unique capabilities not available in most image generation platforms.
### Key Planned Features
- **Image-to-Video**: Animate static images into dynamic videos
- **Make Avatar**: Create talking avatars from photos
- **Image-to-3D**: Generate 3D models from 2D images
- **Audio Integration**: Add voiceovers and sound effects
- **Social Optimization**: Optimize videos for social platforms
---
## Image-to-Video
### Overview
Convert static images into dynamic videos with motion, audio, and social media optimization.
### Planned Features
#### Resolution Options
- **480p**: Fast processing, smaller file size
- **720p**: Balanced quality and size
- **1080p**: High quality for professional use
#### Duration Control
- **Maximum Duration**: Up to 10 seconds
- **Duration Selection**: Choose exact duration
- **Cost**: Based on duration ($0.05-$0.15 per second)
#### Audio Support
- **Audio Upload**: Upload custom audio/voiceover
- **Text-to-Speech**: Generate voiceover from text
- **Synchronization**: Audio synchronized with video
- **Music Library**: Optional background music
#### Motion Control
- **Motion Levels**: Subtle, medium, or dynamic motion
- **Motion Direction**: Control movement direction
- **Focus Points**: Define areas of motion
- **Preview**: Preview motion before generation
#### Social Media Optimization
- **Platform Formats**: Optimize for Instagram, TikTok, YouTube, etc.
- **Aspect Ratios**: Automatic aspect ratio adjustment
- **File Size**: Optimized file sizes for platforms
- **Format Export**: MP4, MOV, or platform-specific formats
### Use Cases
#### Product Showcases
- Animate product images
- Add voiceover descriptions
- Create engaging product videos
- Social media marketing
#### Social Media Content
- Create video posts from images
- Add motion to static content
- Enhance engagement
- Multi-platform distribution
#### Email Marketing
- Animated email headers
- Product video embeds
- Engaging email content
- Higher click-through rates
#### Advertising
- Animated ad creatives
- Video ad variations
- A/B testing videos
- Campaign optimization
### Workflow (Planned)
1. **Upload Image**: Select source image
2. **Choose Settings**: Select resolution, duration, motion
3. **Add Audio** (optional): Upload or generate audio
4. **Preview**: Preview motion and settings
5. **Generate**: Create video
6. **Optimize**: Optimize for target platforms
7. **Export**: Download or share
### Pricing (Estimated)
- **480p**: $0.05 per second
- **720p**: $0.10 per second
- **1080p**: $0.15 per second
**Example Costs**:
- 5-second 720p video: $0.50
- 10-second 1080p video: $1.50
---
## Make Avatar
### Overview
Create talking avatars from single photos with audio-driven lip-sync and emotion control.
### Planned Features
#### Avatar Creation
- **Photo Input**: Single portrait photo
- **Audio Input**: Upload audio or use text-to-speech
- **Lip-Sync**: Automatic lip-sync with audio
- **Emotion Control**: Adjust avatar expressions
#### Duration Options
- **Maximum Duration**: Up to 2 minutes
- **Duration Selection**: Choose exact duration
- **Cost**: Based on duration ($0.15-$0.30 per 5 seconds)
#### Resolution Options
- **480p**: Standard quality
- **720p**: High quality
#### Emotion Control
- **Emotion Types**: Neutral, happy, professional, excited
- **Emotion Intensity**: Adjust emotion strength
- **Natural Expressions**: Realistic facial expressions
#### Audio Features
- **Audio Upload**: Upload custom audio
- **Text-to-Speech**: Generate speech from text
- **Multi-Language**: Support for multiple languages
- **Voice Cloning**: Custom voice options (future)
#### Character Consistency
- **Face Preservation**: Maintain character appearance
- **Style Consistency**: Consistent avatar style
- **Quality Control**: High-quality output
### Use Cases
#### Personal Branding
- Create personal video messages
- Professional introductions
- Brand ambassador content
- Social media presence
#### Explainer Videos
- Product explanations
- Tutorial content
- Educational videos
- How-to guides
#### Customer Service
- Automated responses
- FAQ videos
- Support content
- Onboarding videos
#### Email Campaigns
- Personalized video emails
- Product announcements
- Customer communications
- Marketing campaigns
### Workflow (Planned)
1. **Upload Photo**: Select portrait photo
2. **Add Audio**: Upload or generate audio
3. **Configure Settings**: Set duration, resolution, emotion
4. **Preview**: Preview avatar with audio
5. **Generate**: Create talking avatar
6. **Review**: Review and refine if needed
7. **Export**: Download or share
### Pricing (Estimated)
- **480p**: $0.15 per 5 seconds
- **720p**: $0.30 per 5 seconds
**Example Costs**:
- 30-second 480p avatar: $0.90
- 2-minute 720p avatar: $7.20
---
## Image-to-3D
### Overview
Generate 3D models from 2D images for use in AR, 3D printing, or web applications.
### Planned Features
#### 3D Generation
- **Input**: 2D image
- **Output**: 3D model (GLB, OBJ formats)
- **Quality Options**: Multiple quality levels
- **Texture Control**: Adjust texture resolution
#### Export Formats
- **GLB**: Web and AR applications
- **OBJ**: 3D printing and modeling
- **Texture Maps**: Separate texture files
- **Metadata**: Model information and settings
#### Quality Control
- **Mesh Optimization**: Optimize polygon count
- **Texture Resolution**: Control texture quality
- **Foreground Ratio**: Adjust foreground/background balance
- **Detail Preservation**: Maintain image details
#### Use Cases
- **AR Applications**: Augmented reality content
- **3D Printing**: Physical model creation
- **Web 3D**: Interactive 3D web content
- **Gaming**: Game asset creation
### Workflow (Planned)
1. **Upload Image**: Select source image
2. **Configure Settings**: Set quality and format
3. **Generate**: Create 3D model
4. **Preview**: Preview 3D model
5. **Export**: Download in desired format
---
## Integration with Other Modules
### Complete Workflow
Transform Studio will integrate seamlessly with other Image Studio modules:
1. **Create Studio**: Generate base images
2. **Edit Studio**: Refine images before transformation
3. **Transform Studio**: Convert to video/avatar/3D
4. **Social Optimizer**: Optimize videos for platforms
5. **Asset Library**: Organize all transformed content
### Use Case Examples
#### Social Media Video Campaign
1. Create images in Create Studio
2. Edit images in Edit Studio
3. Transform to videos in Transform Studio
4. Optimize for platforms in Social Optimizer
5. Organize in Asset Library
#### Product Marketing
1. Create product images
2. Transform to product showcase videos
3. Create talking avatar for product explanations
4. Optimize for e-commerce platforms
5. Track usage in Asset Library
---
## Technical Details (Planned)
### Providers
#### WaveSpeed WAN 2.5
- **Image-to-Video**: WaveSpeed WAN 2.5 API
- **Make Avatar**: WaveSpeed Hunyuan Avatar API
- **Integration**: RESTful API integration
- **Async Processing**: Background job processing
#### Stability AI
- **Image-to-3D**: Stability Fast 3D endpoints
- **3D Generation**: Advanced 3D model generation
- **Format Support**: Multiple export formats
### Backend Architecture (Planned)
- **TransformStudioService**: Main service for transformations
- **Video Processing**: Async video generation
- **Audio Processing**: Audio synchronization
- **3D Processing**: 3D model generation
- **Job Queue**: Background processing system
### Frontend Components (Planned)
- **TransformStudio.tsx**: Main interface
- **VideoPreview**: Video preview player
- **AvatarPreview**: Avatar preview with audio
- **3DViewer**: 3D model preview
- **AudioUploader**: Audio file upload
- **MotionControls**: Motion adjustment controls
---
## Cost Considerations (Estimated)
### Image-to-Video
- **Base Cost**: $0.05-$0.15 per second
- **Resolution Impact**: Higher resolution = higher cost
- **Duration Impact**: Longer videos = higher cost
- **Example**: 10-second 1080p video = $1.50
### Make Avatar
- **Base Cost**: $0.15-$0.30 per 5 seconds
- **Resolution Impact**: 720p costs more than 480p
- **Duration Impact**: Longer avatars = higher cost
- **Example**: 2-minute 720p avatar = $7.20
### Image-to-3D
- **Cost**: TBD (to be determined)
- **Quality Impact**: Higher quality = higher cost
- **Format Impact**: Different formats may have different costs
---
## Best Practices (Planned)
### For Image-to-Video
1. **Start with High-Quality Images**: Better source = better video
2. **Choose Appropriate Motion**: Match motion to content
3. **Optimize Duration**: Shorter videos are more cost-effective
4. **Test Resolutions**: Start with 720p for balance
5. **Add Audio Strategically**: Audio enhances engagement
### For Make Avatar
1. **Use Clear Portraits**: High-quality face photos work best
2. **Match Audio Length**: Ensure audio matches desired duration
3. **Control Emotions**: Match emotions to content purpose
4. **Test Different Settings**: Experiment with emotion levels
5. **Consider Use Case**: Professional vs. casual content
### For Image-to-3D
1. **Use Clear Images**: High contrast images work best
2. **Consider Use Case**: Match quality to application
3. **Optimize Mesh**: Balance quality and file size
4. **Test Formats**: Choose format based on use case
5. **Preview Before Export**: Verify model quality
---
## Roadmap
### Phase 1: Image-to-Video
- Basic image-to-video conversion
- Resolution options (480p, 720p, 1080p)
- Duration control (up to 10 seconds)
- Audio upload support
### Phase 2: Make Avatar
- Avatar creation from photos
- Audio-driven lip-sync
- Emotion control
- Multi-language support
### Phase 3: Image-to-3D
- 3D model generation
- Multiple export formats
- Quality controls
- Texture optimization
### Phase 4: Advanced Features
- Motion control refinement
- Advanced audio features
- Custom voice cloning
- Enhanced 3D options
---
## Getting Updates
Transform Studio is currently in planning. To stay updated:
- Check the [Modules Guide](modules.md) for status updates
- Review the [Implementation Overview](implementation-overview.md) for technical progress
- Monitor release notes for availability announcements
---
*Transform Studio features are planned for future release. For currently available features, see [Create Studio](create-studio.md), [Edit Studio](edit-studio.md), [Upscale Studio](upscale-studio.md), [Social Optimizer](social-optimizer.md), and [Asset Library](asset-library.md).*

284
docs-site/docs/features/image-studio/upscale-studio.md Normal file
View File

@@ -0,0 +1,284 @@
# Upscale Studio User Guide
Upscale Studio enhances image resolution using AI-powered upscaling. This guide covers all upscaling modes and how to achieve the best results.
## Overview
Upscale Studio uses Stability AI's advanced upscaling technology to increase image resolution while maintaining or enhancing quality. Whether you need quick 4x upscaling or professional 4K enhancement, Upscale Studio provides the right tools.
### Key Features
- **Fast 4x Upscaling**: Quick upscale in ~1 second
- **Conservative 4K**: Preserve original style and details
- **Creative 4K**: Enhance with artistic improvements
- **Quality Presets**: Web, print, and social media optimizations
- **Side-by-Side Comparison**: View original and upscaled versions
- **Prompt Support**: Guide upscaling with prompts (conservative/creative modes)
## Getting Started
### Accessing Upscale Studio
1. Navigate to **Image Studio** from the main dashboard
2. Click on **Upscale Studio** or go directly to `/image-upscale`
3. Upload your image to begin
### Basic Workflow
1. **Upload Image**: Select the image you want to upscale
2. **Choose Mode**: Select Fast, Conservative, or Creative
3. **Set Preset** (optional): Choose quality preset
4. **Add Prompt** (optional): Guide the upscaling process
5. **Upscale**: Click "Upscale Image" to process
6. **Compare**: View side-by-side comparison with zoom
7. **Download**: Save your upscaled image
## Upscaling Modes
### Fast (4x Upscale)
**Speed**: ~1 second
**Cost**: 2 credits
**Quality**: 4x resolution increase
**When to Use**:
- Quick previews
- Web display
- Social media content
- When speed is priority
**Characteristics**:
- Fastest processing
- Minimal changes to original
- Good for general use
- Cost-effective
**Best For**:
- Social media images
- Web graphics
- Quick iterations
- Low-resolution source images
### Conservative (4K Upscale)
**Speed**: 10-30 seconds
**Cost**: 6 credits
**Quality**: 4K resolution, preserves original style
**When to Use**:
- Professional printing
- High-quality display
- Preserving original style
- When accuracy is critical
**Characteristics**:
- Preserves original details
- Maintains style consistency
- High fidelity
- Professional quality
**Prompt Support**:
- Optional prompt to guide upscaling
- Example: "High fidelity upscale preserving original details"
- Helps maintain specific characteristics
**Best For**:
- Product photography
- Professional prints
- High-quality displays
- Archival purposes
### Creative (4K Upscale)
**Speed**: 10-30 seconds
**Cost**: 6 credits
**Quality**: 4K resolution with artistic enhancements
**When to Use**:
- Artistic enhancement
- Style improvement
- Creative projects
- When you want improvements
**Characteristics**:
- Enhances artistic details
- Improves style
- Adds refinements
- Creative interpretation
**Prompt Support**:
- Recommended prompt for best results
- Example: "Creative upscale with enhanced artistic details"
- Guides the enhancement process
**Best For**:
- Artistic images
- Creative projects
- Style enhancement
- Visual improvements
## Quality Presets
Quality presets help optimize upscaling for specific use cases:
### Web (2048px)
- **Target**: Web display
- **Use Case**: Website images, online galleries
- **Balance**: Quality and file size
### Print (3072px)
- **Target**: Professional printing
- **Use Case**: High-resolution prints, publications
- **Balance**: Maximum quality
### Social (1080px)
- **Target**: Social media platforms
- **Use Case**: Instagram, Facebook, LinkedIn posts
- **Balance**: Platform optimization
## Using Prompts
Prompts help guide the upscaling process in Conservative and Creative modes:
### Conservative Mode Prompts
**Purpose**: Preserve specific characteristics
**Examples**:
- "High fidelity upscale preserving original details"
- "Maintain original colors and style"
- "Preserve sharp edges and fine details"
- "Keep original lighting and contrast"
### Creative Mode Prompts
**Purpose**: Enhance and improve the image
**Examples**:
- "Creative upscale with enhanced artistic details"
- "Add more detail and depth"
- "Enhance colors and vibrancy"
- "Improve texture and sharpness"
### Prompt Tips
1. **Be Specific**: Describe what to preserve or enhance
2. **Match Mode**: Conservative = preserve, Creative = enhance
3. **Consider Style**: Reference the original style
4. **Test Iteratively**: Refine prompts based on results
## Comparison Viewer
The side-by-side comparison viewer helps you evaluate upscaling results:
### Features
- **Side-by-Side Display**: Original and upscaled images
- **Synchronized Zoom**: Zoom both images together
- **Zoom Controls**: Adjust zoom level (1x to 5x)
- **Metadata Display**: View resolution and file size
### Using the Viewer
1. **Compare**: View original and upscaled side-by-side
2. **Zoom In**: Use zoom controls to inspect details
3. **Check Quality**: Evaluate sharpness and detail preservation
4. **Download**: Save if satisfied, or try different settings
## Best Practices
### For Web Images
1. **Use Fast Mode**: Quick and cost-effective
2. **Web Preset**: Optimize for web display
3. **Check File Size**: Ensure reasonable file sizes
4. **Test Display**: Verify on target devices
### For Print Materials
1. **Use Conservative Mode**: Preserve original quality
2. **Print Preset**: Maximum resolution
3. **Add Prompt**: Guide detail preservation
4. **Check Resolution**: Verify meets print requirements
### For Social Media
1. **Use Fast or Conservative**: Based on quality needs
2. **Social Preset**: Platform-optimized sizing
3. **Consider Speed**: Fast mode for quick posts
4. **Maintain Quality**: Ensure good visual quality
### For Product Photography
1. **Use Conservative Mode**: Preserve product details
2. **Add Prompt**: Emphasize detail preservation
3. **High Resolution**: Use print preset if needed
4. **Compare Carefully**: Verify product accuracy
### For Artistic Images
1. **Use Creative Mode**: Enhance artistic elements
2. **Add Prompt**: Guide artistic enhancement
3. **Experiment**: Try different prompts
4. **Compare Results**: Evaluate enhancements
## Troubleshooting
### Common Issues
**Low Quality Results**:
- Try Conservative mode instead of Fast
- Add a prompt to guide upscaling
- Check source image quality
- Use Print preset for maximum quality
**Artifacts or Distortions**:
- Use Conservative mode
- Add prompt to preserve details
- Check source image for issues
- Try different mode
**Slow Processing**:
- Fast mode is fastest (~1 second)
- Conservative/Creative take 10-30 seconds
- Large images take longer
- Check internet connection
**File Size Too Large**:
- Use Web preset for smaller files
- Consider Fast mode for web use
- Compress after upscaling if needed
### Getting Help
- Check mode-specific tips above
- Review the [Workflow Guide](workflow-guide.md) for common workflows
- See [Implementation Overview](implementation-overview.md) for technical details
## Cost Considerations
### Credit Costs
- **Fast Mode**: 2 credits
- **Conservative Mode**: 6 credits
- **Creative Mode**: 6 credits
### Cost Optimization
1. **Use Fast for Iterations**: Test with Fast mode first
2. **Choose Appropriate Mode**: Don't use Creative if Conservative is sufficient
3. **Batch Processing**: Upscale multiple images efficiently
4. **Check Before Upscaling**: Ensure source image is worth upscaling
## Next Steps
After upscaling images in Upscale Studio:
1. **Edit**: Use [Edit Studio](edit-studio.md) to refine upscaled images
2. **Optimize**: Use [Social Optimizer](social-optimizer.md) for platform-specific exports
3. **Organize**: Save to [Asset Library](asset-library.md) for easy access
4. **Create More**: Use [Create Studio](create-studio.md) to generate new images
---
*For technical details, see the [Implementation Overview](implementation-overview.md). For API usage, see the [API Reference](api-reference.md).*

370
docs-site/docs/features/image-studio/workflow-guide.md Normal file
View File

@@ -0,0 +1,370 @@
# Image Studio Workflow Guide
This guide covers end-to-end workflows for common Image Studio use cases. Learn how to combine multiple modules to achieve your content creation goals efficiently.
## Overview
Image Studio workflows combine multiple modules to create complete content pipelines. This guide shows you how to use Create, Edit, Upscale, Social Optimizer, and Asset Library together for maximum efficiency.
## Workflow Patterns
### Pattern 1: Create → Use
Simple generation workflow for quick content.
### Pattern 2: Create → Edit → Use
Generation with refinement for better results.
### Pattern 3: Create → Edit → Upscale → Use
Complete quality enhancement workflow.
### Pattern 4: Create → Edit → Optimize → Use
Social media ready workflow.
### Pattern 5: Create → Edit → Upscale → Optimize → Organize
Complete professional workflow.
## Common Workflows
### Workflow 1: Social Media Campaign
**Goal**: Create campaign visuals optimized for multiple platforms
**Steps**:
1. **Create Studio** - Generate Base Images
- Use platform templates (Instagram, Facebook, LinkedIn)
- Generate 3-5 variations for A/B testing
- Use Premium quality for best results
- Save to Asset Library
2. **Edit Studio** (Optional) - Refine Images
- Remove backgrounds if needed
- Adjust colors to match brand
- Fix any imperfections
- Save edited versions
3. **Social Optimizer** - Platform Optimization
- Upload final images
- Select all relevant platforms
- Choose appropriate formats
- Enable safe zones for text
- Batch export all formats
4. **Asset Library** - Organization
- Mark favorites
- Organize by campaign
- Download optimized versions
- Track usage
**Time**: 20-30 minutes for complete campaign
**Cost**: Varies by quality and variations
**Result**: Platform-optimized images ready for all social channels
---
### Workflow 2: Blog Post Featured Image
**Goal**: Create high-quality featured images for blog posts
**Steps**:
1. **Create Studio** - Generate Featured Image
- Use blog post template
- Write descriptive prompt
- Use Standard or Premium quality
- Generate 2-3 variations
2. **Edit Studio** (Optional) - Enhance Image
- Add text overlays if needed (via General Edit)
- Adjust colors for readability
- Remove unwanted elements
- Fix composition issues
3. **Upscale Studio** - Enhance Resolution
- Upload final image
- Use Conservative 4K mode
- Add prompt: "High fidelity upscale preserving original details"
- Upscale for high-quality display
4. **Social Optimizer** (Optional) - Social Sharing
- Optimize for social media sharing
- Create square version for Instagram
- Create landscape version for Twitter/LinkedIn
5. **Asset Library** - Track Usage
- Save to Asset Library
- Track downloads and shares
- Monitor performance
**Time**: 15-20 minutes per image
**Cost**: Moderate (Standard quality + upscale)
**Result**: High-quality featured image ready for blog and social sharing
---
### Workflow 3: Product Photography
**Goal**: Create professional product images with transparent backgrounds
**Steps**:
1. **Create Studio** - Generate Product Image
- Use product photography style
- Describe product in detail
- Use Premium quality
- Generate base product image
2. **Edit Studio** - Remove Background
- Upload product image
- Select "Remove Background" operation
- Get transparent PNG
- Save isolated product
3. **Edit Studio** (Optional) - Add Variations
- Use "Search & Recolor" for color variations
- Create multiple product colors
- Use "Replace Background" for different scenes
4. **Upscale Studio** (Optional) - Enhance Quality
- Upscale for high-resolution display
- Use Conservative mode to preserve details
- Ensure product details are sharp
5. **Social Optimizer** - E-commerce Optimization
- Optimize for product listings
- Create square versions for catalogs
- Optimize for social media product posts
6. **Asset Library** - Product Catalog
- Organize by product line
- Mark favorites
- Track which images perform best
**Time**: 20-30 minutes per product
**Cost**: Moderate to high (Premium quality + editing)
**Result**: Professional product images ready for e-commerce and marketing
---
### Workflow 4: Content Library Building
**Goal**: Build a library of reusable content assets
**Steps**:
1. **Create Studio** - Batch Generation
- Generate multiple variations (5-10 per prompt)
- Use different styles and templates
- Mix Draft and Standard quality
- Create diverse content library
2. **Asset Library** - Initial Organization
- Review all generated images
- Mark favorites
- Delete low-quality results
- Organize by category
3. **Edit Studio** - Refine Favorites
- Edit best images
- Remove backgrounds
- Adjust colors
- Create variations
4. **Upscale Studio** - Enhance Quality
- Upscale favorite images
- Use Conservative mode
- Prepare for various use cases
5. **Social Optimizer** - Create Formats
- Optimize for different platforms
- Create multiple format versions
- Batch export for efficiency
6. **Asset Library** - Final Organization
- Organize by use case
- Tag and categorize
- Track usage
- Build reusable library
**Time**: 1-2 hours for initial library
**Cost**: Varies by volume
**Result**: Comprehensive content library ready for various campaigns
---
### Workflow 5: Quick Social Post
**Goal**: Fast content creation for immediate posting
**Steps**:
1. **Create Studio** - Quick Generation
- Use Draft quality for speed
- Select appropriate template
- Generate 1-2 variations
- Quick preview
2. **Social Optimizer** - Immediate Optimization
- Upload generated image
- Select target platform
- Use Smart Crop
- Download optimized version
3. **Post** - Use immediately
**Time**: 2-5 minutes
**Cost**: Low (Draft quality)
**Result**: Quick social media content ready to post
---
### Workflow 6: Brand Asset Creation
**Goal**: Create consistent brand visuals
**Steps**:
1. **Create Studio** - Generate Base Assets
- Use consistent style prompts
- Match brand colors
- Use Premium quality
- Generate multiple variations
2. **Edit Studio** - Brand Consistency
- Adjust colors to brand palette
- Use "Search & Recolor" for consistency
- Remove elements that don't match brand
- Create brand-aligned variations
3. **Upscale Studio** - Professional Quality
- Upscale for various uses
- Use Conservative mode
- Maintain brand style
4. **Social Optimizer** - Multi-Platform
- Optimize for all brand channels
- Maintain brand consistency
- Create format variations
5. **Asset Library** - Brand Organization
- Organize by brand guidelines
- Mark official brand assets
- Track brand asset usage
**Time**: 30-45 minutes per asset set
**Cost**: Moderate to high (Premium quality)
**Result**: Consistent brand assets across all platforms
---
## Workflow Best Practices
### Planning Your Workflow
1. **Define Goal**: Know what you're creating
2. **Choose Quality**: Match quality to use case
3. **Plan Steps**: Decide which modules you need
4. **Estimate Cost**: Check costs before starting
5. **Batch Operations**: Group similar tasks
### Efficiency Tips
1. **Start with Draft**: Test concepts with Draft quality
2. **Batch Generate**: Create multiple variations at once
3. **Use Templates**: Save time with platform templates
4. **Organize Early**: Use Asset Library from the start
5. **Reuse Assets**: Build library for future use
### Cost Optimization
1. **Draft First**: Test with low-cost Draft quality
2. **Batch Operations**: Process multiple items together
3. **Choose Wisely**: Use appropriate quality levels
4. **Reuse Results**: Don't regenerate similar content
5. **Track Usage**: Monitor costs in Asset Library
### Quality Management
1. **Start High**: Use Premium for important content
2. **Edit Strategically**: Only edit when necessary
3. **Upscale Selectively**: Upscale only best images
4. **Compare Results**: Use comparison tools
5. **Iterate Efficiently**: Refine based on results
## Workflow Templates
### Template: Weekly Social Content
**Frequency**: Weekly
**Time**: 1-2 hours
**Output**: 10-15 optimized images
1. **Monday**: Create 5-7 base images (Draft quality)
2. **Tuesday**: Edit and refine favorites
3. **Wednesday**: Upscale best images
4. **Thursday**: Optimize for all platforms
5. **Friday**: Organize in Asset Library, schedule posts
### Template: Campaign Launch
**Timeline**: 1 week
**Time**: 4-6 hours
**Output**: Complete campaign asset set
1. **Day 1-2**: Generate campaign visuals (Premium quality)
2. **Day 3**: Edit and refine all images
3. **Day 4**: Upscale key visuals
4. **Day 5**: Optimize for all platforms
5. **Day 6-7**: Final review and organization
### Template: Content Library
**Timeline**: Ongoing
**Time**: 2-3 hours/week
**Output**: Growing content library
1. **Weekly**: Generate 20-30 new images
2. **Review**: Mark favorites, delete rejects
3. **Enhance**: Edit and upscale favorites
4. **Organize**: Categorize in Asset Library
5. **Use**: Pull from library for campaigns
## Troubleshooting Workflows
### Common Issues
**Workflow Takes Too Long**:
- Use Draft quality for iterations
- Batch operations when possible
- Skip unnecessary steps
- Use templates to save time
**Results Don't Match Expectations**:
- Refine prompts in Create Studio
- Use Edit Studio for adjustments
- Try different providers
- Iterate based on results
**Costs Too High**:
- Use Draft quality for testing
- Reduce number of variations
- Skip upscaling when not needed
- Reuse existing assets
**Quality Issues**:
- Use Premium quality for important content
- Upscale with Conservative mode
- Edit strategically
- Compare results before finalizing
## Next Steps
- Explore individual module guides for detailed instructions
- Check the [Providers Guide](providers.md) for provider selection
- Review the [Cost Guide](cost-guide.md) for cost optimization
- See [Templates Guide](templates.md) for template usage
---
*For module-specific guides, see [Create Studio](create-studio.md), [Edit Studio](edit-studio.md), [Upscale Studio](upscale-studio.md), [Social Optimizer](social-optimizer.md), and [Asset Library](asset-library.md).*