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

youtube shorts video generator

Browse Source
This commit is contained in:
ajaysi
2025-05-16 21:53:56 +05:30
parent b2ce1ceb49
commit 4049d19787
8 changed files with 1152 additions and 80 deletions
Download Patch File Download Diff File Expand all files Collapse all files

42
lib/gpt_providers/text_to_image_generation/gen_gemini_images.py
View File

@@ -161,7 +161,7 @@ class AIPromptGenerator:
return ", ".join(prompt_parts)
def generate_gemini_image(prompt, keywords=None, style=None, focus=None, enhance_prompt=True, max_retries=3, initial_retry_delay=2):
def generate_gemini_image(prompt, keywords=None, style=None, focus=None, enhance_prompt=True, max_retries=3, initial_retry_delay=2, aspect_ratio="16:9"):
"""
Generate images using Gemini
Depending on the prompt and context, Gemini will generate content in different modes (text to image, text to image and text, etc.).
@@ -184,6 +184,7 @@ def generate_gemini_image(prompt, keywords=None, style=None, focus=None, enhance
enhance_prompt (bool, optional): Whether to enhance the prompt using AIPromptGenerator. Defaults to True.
max_retries (int, optional): Maximum number of retry attempts for handling 503 errors. Defaults to 3.
initial_retry_delay (int, optional): Initial delay in seconds before retrying. Defaults to 2.
aspect_ratio (str, optional): The aspect ratio for the generated image. Must be one of "16:9", "9:16", "4:3", "3:4", or "1:1". Defaults to "16:9".
Returns:
str: The path to the generated image.
@@ -212,6 +213,10 @@ def generate_gemini_image(prompt, keywords=None, style=None, focus=None, enhance
prompt = f"{prompt}\n\nEnhanced prompt: {enhanced_prompt}"
logger.info(f"Final prompt: '{prompt[:100]}...'")
# Add aspect ratio to the prompt
if aspect_ratio:
prompt += f"\n\nPlease generate the image with {aspect_ratio} aspect ratio."
retry_count = 0
retry_delay = initial_retry_delay
@@ -238,7 +243,40 @@ def generate_gemini_image(prompt, keywords=None, style=None, focus=None, enhance
elif part.inline_data is not None:
logger.info("Received image data from Gemini")
image = Image.open(BytesIO((part.inline_data.data)))
image.show()
# Resize image to match aspect ratio if needed
if aspect_ratio:
current_width, current_height = image.size
target_width = current_width
target_height = current_height
# Calculate target dimensions based on aspect ratio
if aspect_ratio == "16:9":
target_height = int(current_width * 9/16)
elif aspect_ratio == "9:16":
target_width = int(current_height * 9/16)
elif aspect_ratio == "4:3":
target_height = int(current_width * 3/4)
elif aspect_ratio == "3:4":
target_width = int(current_height * 3/4)
elif aspect_ratio == "1:1":
target_size = min(current_width, current_height)
target_width = target_size
target_height = target_size
logger.info(f"Resizing image from {current_width}x{current_height} to {target_width}x{target_height}")
# Create a new image with the target dimensions
resized_image = Image.new('RGB', (target_width, target_height), (255, 255, 255))
# Calculate position to paste the original image
paste_x = (target_width - current_width) // 2
paste_y = (target_height - current_height) // 2
# Paste the original image onto the new canvas
resized_image.paste(image, (paste_x, paste_y))
image = resized_image
if part.text is not None:
img_name = f'{part.text}-gemini-native-image.png'
else:

10
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, title=None, description=None, tags=None, content=None):
def generate_image(user_prompt, title=None, description=None, tags=None, content=None, aspect_ratio="16:9"):
"""
The generation API endpoint creates an image based on a text prompt.
@@ -42,6 +42,7 @@ def generate_image(user_prompt, title=None, description=None, tags=None, content
-->response_format (str): The format in which the generated images are returned.
Must be one of "url" or "b64_json". Defaults to "url".
--> user (str): A unique identifier representing your end-user, which will help OpenAI to monitor and detect abuse.
--> aspect_ratio (str): The aspect ratio for the generated image. Must be one of "16:9", "4:3", or "1:1". Defaults to "16:9".
"""
# FIXME: Need to remove default value to match sidebar input.
image_engine = 'Gemini-AI'
@@ -51,6 +52,11 @@ def generate_image(user_prompt, title=None, description=None, tags=None, content
try:
# Use enhanced prompt generator with all available parameters
img_prompt = generate_enhanced_img_prompt(user_prompt, title, description, tags, content)
# Add aspect ratio to the prompt
if aspect_ratio:
img_prompt += f"\n\nAspect ratio: {aspect_ratio}"
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)
@@ -59,7 +65,7 @@ def generate_image(user_prompt, title=None, description=None, tags=None, content
image_stored_at = generate_stable_diffusion_image(img_prompt)
elif 'Gemini-AI' in image_engine:
logger.info(f"Calling Gemini text-to-image with prompt: \n{img_prompt}")
image_stored_at = generate_gemini_image(img_prompt)
image_stored_at = generate_gemini_image(img_prompt, aspect_ratio=aspect_ratio)
return image_stored_at
except Exception as err:
logger.error(f"Failed to generate Image: {err}")