kunthawat/ALwrity
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

AI blog writer & blog metadata updates & improvements

Browse Source
This commit is contained in:
ajaysi
2025-05-01 10:38:01 +05:30
parent a6e3ac2f8b
commit a27522d32e
6 changed files with 586 additions and 63 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
lib/gpt_providers/text_to_image_generation/gen_gemini_images.py
View File

@@ -190,6 +190,14 @@ def generate_gemini_image(prompt, keywords=None, style=None, focus=None, enhance
"""
logger.info(f"Generating image with prompt: '{prompt[:100]}...'")
# Check if the GEMINI_API_KEY is available
api_key = os.getenv("GEMINI_API_KEY")
if not api_key:
error_msg = "GEMINI_API_KEY is missing. Please set it in your environment variables."
logger.error(error_msg)
st.error(f"🔑 {error_msg}")
return None
# Enhance the prompt if requested
if enhance_prompt and keywords:
prompt_generator = AIPromptGenerator()
@@ -209,7 +217,7 @@ def generate_gemini_image(prompt, keywords=None, style=None, focus=None, enhance
while retry_count <= max_retries:
try:
client = genai.Client(api_key=os.getenv("GEMINI_API_KEY"))
client = genai.Client(api_key=api_key)
contents = (prompt)
logger.info("Sending request to Gemini API")

74
lib/gpt_providers/text_to_image_generation/main_generate_image_from_prompt.py
View File

@@ -27,7 +27,7 @@ from .gen_stabl_diff_img import generate_stable_diffusion_image
from ..text_generation.main_text_generation import llm_text_gen
from .gen_gemini_images import generate_gemini_image
def generate_image(user_prompt):
def generate_image(user_prompt, title=None, description=None, tags=None, content=None):
"""
The generation API endpoint creates an image based on a text prompt.
@@ -49,7 +49,8 @@ def generate_image(user_prompt):
if user_prompt:
try:
img_prompt = generate_img_prompt(user_prompt)
# Use enhanced prompt generator with all available parameters
img_prompt = generate_enhanced_img_prompt(user_prompt, title, description, tags, content)
if 'Dalle3' in image_engine:
logger.info(f"Calling Dalle3 text-to-image with prompt: {img_prompt}")
image_stored_at = generate_dalle3_images(img_prompt)
@@ -85,3 +86,72 @@ def generate_img_prompt(user_prompt):
response = llm_text_gen(prompt)
return response
def generate_enhanced_img_prompt(user_prompt, title=None, description=None, tags=None, content=None):
"""
Given user prompt and additional context (title, description, tags, content),
this function generates an enhanced prompt for better image generation.
Args:
user_prompt (str): Base prompt from the user
title (str, optional): Blog title or content title
description (str, optional): Blog or content description/summary
tags (list, optional): List of tags related to the content
content (str, optional): Actual content or excerpt
Returns:
str: Enhanced prompt for image generation
"""
# Start with the base prompt
context_parts = [user_prompt]
# Add relevant context if available
if title:
context_parts.append(f"Title: {title}")
if description:
context_parts.append(f"Description: {description}")
if tags and len(tags) > 0:
tag_text = ", ".join(tags[:5]) # Limit to 5 tags to avoid too much noise
context_parts.append(f"Tags: {tag_text}")
# Create a combined context
combined_context = "\n".join(context_parts)
# Add some content excerpt if available (limited to avoid token limits)
content_excerpt = ""
if content:
# Just use the first few hundred characters as excerpt
content_excerpt = content[:300] + "..." if len(content) > 300 else content
# Create the prompt for LLM
prompt = f"""
As an expert prompt engineer for AI image generation models, create a detailed, creative prompt
for generating a high-quality, relevant image based on the following context:
{combined_context}
Additional content excerpt:
{content_excerpt}
Your task is to:
1. Analyze the context and content to understand the main theme and subject
2. Create a rich, detailed prompt for image generation (50-75 words)
3. Include specific visual details, art style, mood, lighting, composition
4. Make sure the prompt is highly relevant to the original context
5. Avoid prohibited content or anything that violates image generation guidelines
Reply with ONLY the final prompt. No explanations or other text.
"""
# Generate the enhanced prompt
try:
enhanced_prompt = llm_text_gen(prompt)
logger.info(f"Generated enhanced image prompt: {enhanced_prompt[:100]}...")
return enhanced_prompt
except Exception as e:
logger.error(f"Error generating enhanced prompt: {e}")
# Fall back to the simple prompt generation if enhanced fails
return generate_img_prompt(user_prompt)

13
lib/gpt_providers/text_to_image_generation/save_image.py
View File

@@ -12,8 +12,16 @@ def save_generated_image(img_generation_response):
logging.basicConfig(level=logging.INFO)
logger = logging.getLogger(__name__)
# Get image save directory with fallback to a local directory
image_save_dir = os.getenv('IMG_SAVE_DIR', 'generated_images')
# Create the directory if it doesn't exist
if not os.path.exists(image_save_dir):
logger.info(f"Creating image save directory: {image_save_dir}")
os.makedirs(image_save_dir, exist_ok=True)
generated_image_name = f"generated_image_{datetime.datetime.now():%Y-%m-%d-%H-%M-%S}.webp"
generated_image_filepath = os.path.join(os.getenv('IMG_SAVE_DIR'), generated_image_name)
generated_image_filepath = os.path.join(image_save_dir, generated_image_name)
try:
for i, image in enumerate(img_generation_response["artifacts"]):
@@ -22,6 +30,9 @@ def save_generated_image(img_generation_response):
except requests.exceptions.RequestException as e:
logger.error(f"Failed to get generated image content: {e}")
return None
except Exception as e:
logger.error(f"Error saving image: {e}")
return None
logger.info(f"Saved image at path: {generated_image_filepath}")