working system

Project.md

@@ -9,6 +9,7 @@ A Python application that uses Hugging Face inference endpoints for text-to-imag
 - Gradio UI for interactive use
 - API endpoints for integration with other applications
 - Configurable models via text input
+- Default values for prompts, negative prompts, and models
 
 ## Project Structure
 
@@ -37,6 +38,15 @@ A Python application that uses Hugging Face inference endpoints for text-to-imag
 - `POST /text-to-image` - Generate an image from text
 - `POST /image-to-image` - Transform an image with optional prompt
 
+## Default Values
+
+The application includes defaults for:
+- Sample prompts for text-to-image and image-to-image
+- Negative prompts to exclude unwanted elements
+- Pre-filled model names for both text-to-image and image-to-image
+
+These defaults are applied to both the Gradio UI and API endpoints for consistency.
+
 ## Environment Variables
 
 - `HF_TOKEN` - Your Hugging Face API token

api.py

@@ -17,9 +17,9 @@ async def root():
 
 @app.post("/text-to-image")
 async def text_to_image(
-    prompt: str = Form(...),
-    model: str = Form(None),
-    negative_prompt: str = Form(None),
+    prompt: str = Form(config.DEFAULT_TEXT2IMG_PROMPT),
+    model: str = Form(config.DEFAULT_TEXT2IMG_MODEL),
+    negative_prompt: str = Form(config.DEFAULT_NEGATIVE_PROMPT),
     guidance_scale: float = Form(7.5),
     num_inference_steps: int = Form(50)
 ):
@@ -27,10 +27,14 @@ async def text_to_image(
     Generate an image from a text prompt
     """
     try:
-        # Use default model if not specified
-        if not model:
+        # Use default model if not specified or empty
+        if not model or model.strip() == '':
             model = config.DEFAULT_TEXT2IMG_MODEL
             
+        # Use default negative prompt if not specified or empty
+        if not negative_prompt or negative_prompt.strip() == '':
+            negative_prompt = config.DEFAULT_NEGATIVE_PROMPT
+            
         # Call the inference module
         image = inference.text_to_image(
             prompt=prompt,
@@ -52,9 +56,9 @@ async def text_to_image(
 @app.post("/image-to-image")
 async def image_to_image(
     image: UploadFile = File(...),
-    prompt: str = Form(None),
-    model: str = Form(None),
-    negative_prompt: str = Form(None),
+    prompt: str = Form(config.DEFAULT_IMG2IMG_PROMPT),
+    model: str = Form(config.DEFAULT_IMG2IMG_MODEL),
+    negative_prompt: str = Form(config.DEFAULT_NEGATIVE_PROMPT),
     guidance_scale: float = Form(7.5),
     num_inference_steps: int = Form(50)
 ):
@@ -66,10 +70,18 @@ async def image_to_image(
         contents = await image.read()
         input_image = Image.open(io.BytesIO(contents))
         
-        # Use default model if not specified
-        if not model:
+        # Use default model if not specified or empty
+        if not model or model.strip() == '':
             model = config.DEFAULT_IMG2IMG_MODEL
             
+        # Use default prompt if not specified or empty
+        if not prompt or prompt.strip() == '':
+            prompt = config.DEFAULT_IMG2IMG_PROMPT
+            
+        # Use default negative prompt if not specified or empty
+        if not negative_prompt or negative_prompt.strip() == '':
+            negative_prompt = config.DEFAULT_NEGATIVE_PROMPT
+            
         # Call the inference module
         result = inference.image_to_image(
             image=input_image,

api_example.py

@@ -13,22 +13,31 @@ HF_TOKEN = os.getenv("HF_TOKEN")
 # API base URL
 API_BASE = "http://localhost:8000"
 
-def text_to_image(prompt, model=None, negative_prompt=None):
+def text_to_image(prompt=None, model=None, negative_prompt=None, guidance_scale=None, num_inference_steps=None):
     """
     Generate image from text using the API
+    All parameters are optional and will use server defaults if not provided
     """
     url = f"{API_BASE}/text-to-image"
     
-    # Prepare form data
-    data = {
-        "prompt": prompt,
-    }
+    # Prepare form data - only add parameters that are provided 
+    # (otherwise use server defaults)
+    data = {}
+    
+    if prompt is not None:
+        data["prompt"] = prompt
     
-    if model:
+    if model is not None:
         data["model"] = model
     
-    if negative_prompt:
+    if negative_prompt is not None:
         data["negative_prompt"] = negative_prompt
+        
+    if guidance_scale is not None:
+        data["guidance_scale"] = guidance_scale
+        
+    if num_inference_steps is not None:
+        data["num_inference_steps"] = num_inference_steps
     
     # Make API request
     response = requests.post(url, data=data)
@@ -42,20 +51,33 @@ def text_to_image(prompt, model=None, negative_prompt=None):
         print(response.text)
         return None
 
-def image_to_image(image_path, prompt=None, model=None):
+def image_to_image(image_path, prompt=None, model=None, negative_prompt=None, 
+                  guidance_scale=None, num_inference_steps=None):
     """
     Transform image using the API
+    Only image_path is required, other parameters are optional and will use server defaults
     """
     url = f"{API_BASE}/image-to-image"
     
-    # Prepare form data and files
+    # Prepare form data - only add parameters that are provided
     data = {}
-    if prompt:
+    
+    if prompt is not None:
         data["prompt"] = prompt
     
-    if model:
+    if model is not None:
         data["model"] = model
+        
+    if negative_prompt is not None:
+        data["negative_prompt"] = negative_prompt
+        
+    if guidance_scale is not None:
+        data["guidance_scale"] = guidance_scale
+        
+    if num_inference_steps is not None:
+        data["num_inference_steps"] = num_inference_steps
     
+    # Prepare the image file
     files = {
         "image": open(image_path, "rb")
     }
@@ -75,14 +97,18 @@ def image_to_image(image_path, prompt=None, model=None):
 if __name__ == "__main__":
     # Example usage
     print("Text to Image example:")
-    image = text_to_image("A beautiful mountain landscape at sunset")
+    # Can call without arguments to use server defaults
+    image = text_to_image()
     if image:
         image.save("text2img_output.png")
         print("Image saved as text2img_output.png")
     
+    # Or with specific parameters
+    # image = text_to_image("A beautiful mountain landscape at sunset")
+    
     print("Image to Image example (requires an input image):")
     # Uncomment and modify path to run:
-    # result = image_to_image("input.png", "Turn this into a fantasy scene")
+    # result = image_to_image("input.png")  # Uses default prompt
     # if result:
     #     result.save("img2img_output.png")
     #     print("Image saved as img2img_output.png")

app.py

@@ -12,7 +12,8 @@ def text_to_image_fn(prompt, model, negative_prompt=None, guidance_scale=7.5, nu
     Handle text to image generation request
     """
     try:
-        if not model:
+        # Model validation - fallback to default if empty
+        if not model or model.strip() == '':
             model = config.DEFAULT_TEXT2IMG_MODEL
             
         # Call the inference module
@@ -40,12 +41,13 @@ def image_to_image_fn(image, prompt, model, negative_prompt=None, guidance_scale
     if image is None:
         return None, "No input image provided."
     
-    if not model:
+    # Model validation - fallback to default if empty
+    if not model or model.strip() == '':
         model = config.DEFAULT_IMG2IMG_MODEL
     
-    # Handle empty prompt
-    if prompt == "":
-        prompt = None
+    # Handle empty prompt - use default if completely empty
+    if prompt is None or prompt.strip() == "":
+        prompt = config.DEFAULT_IMG2IMG_PROMPT
     
     try:
         # Call the inference module with explicit parameters
@@ -77,9 +79,9 @@ with gr.Blocks(title="Diffusion Models") as app:
     with gr.Tab("Text to Image"):
         with gr.Row():
             with gr.Column():
-                txt2img_prompt = gr.Textbox(label="Prompt", placeholder="Enter your prompt here...")
-                txt2img_negative = gr.Textbox(label="Negative Prompt (Optional)", placeholder="What to exclude from the image")
-                txt2img_model = gr.Textbox(label="Model", placeholder=f"Enter model name (default: {config.DEFAULT_TEXT2IMG_MODEL})")
+                txt2img_prompt = gr.Textbox(label="Prompt", placeholder="Enter your prompt here...", value=config.DEFAULT_TEXT2IMG_PROMPT)
+                txt2img_negative = gr.Textbox(label="Negative Prompt (Optional)", placeholder="What to exclude from the image", value=config.DEFAULT_NEGATIVE_PROMPT)
+                txt2img_model = gr.Textbox(label="Model", placeholder=f"Enter model name", value=config.DEFAULT_TEXT2IMG_MODEL)
                 txt2img_guidance = gr.Slider(minimum=1.0, maximum=20.0, value=7.5, step=0.5, label="Guidance Scale")
                 txt2img_steps = gr.Slider(minimum=10, maximum=100, value=50, step=1, label="Inference Steps")
                 txt2img_button = gr.Button("Generate Image")
@@ -98,9 +100,9 @@ with gr.Blocks(title="Diffusion Models") as app:
         with gr.Row():
             with gr.Column():
                 img2img_input = gr.Image(type="pil", label="Input Image")
-                img2img_prompt = gr.Textbox(label="Prompt", placeholder="Enter your prompt here...")
-                img2img_negative = gr.Textbox(label="Negative Prompt (Optional)", placeholder="What to exclude from the image")
-                img2img_model = gr.Textbox(label="Model", placeholder=f"Enter model name (default: {config.DEFAULT_IMG2IMG_MODEL})")
+                img2img_prompt = gr.Textbox(label="Prompt", placeholder="Enter your prompt here...", value=config.DEFAULT_IMG2IMG_PROMPT)
+                img2img_negative = gr.Textbox(label="Negative Prompt (Optional)", placeholder="What to exclude from the image", value=config.DEFAULT_NEGATIVE_PROMPT)
+                img2img_model = gr.Textbox(label="Model", placeholder=f"Enter model name", value=config.DEFAULT_IMG2IMG_MODEL)
                 img2img_guidance = gr.Slider(minimum=1.0, maximum=20.0, value=7.5, step=0.5, label="Guidance Scale")
                 img2img_steps = gr.Slider(minimum=10, maximum=100, value=50, step=1, label="Inference Steps")
                 img2img_button = gr.Button("Transform Image")

config.py

@@ -8,10 +8,17 @@ load_dotenv()
 HF_TOKEN = os.getenv("HF_TOKEN", "")
 
 # Default model for text to image
-DEFAULT_TEXT2IMG_MODEL = "stabilityai/stable-diffusion-2-1"
+DEFAULT_TEXT2IMG_MODEL = "stabilityai/stable-diffusion-3-medium-diffusers"
 
 # Default model for image to image
-DEFAULT_IMG2IMG_MODEL = "lllyasviel/sd-controlnet-depth"
+DEFAULT_IMG2IMG_MODEL = "stabilityai/stable-diffusion-xl-refiner-1.0"
+
+# Default prompts - used as placeholders in UI and defaults in API
+DEFAULT_TEXT2IMG_PROMPT = "A beautiful landscape with mountains and a lake"
+DEFAULT_IMG2IMG_PROMPT = "Transform this image with fantasy elements"
+
+# Default negative prompts - used to improve image quality by avoiding common issues
+DEFAULT_NEGATIVE_PROMPT = "blurry, low quality, distorted, deformed, ugly, pixelated, noise, grain, text, watermark, poor composition, bad proportions, disfigured, mutation, mutated, extra limbs, extra fingers, fused fingers, malformed hands, poorly drawn face, bad anatomy, amateur drawing, low resolution, duplicate, cropped, out of frame, worst quality, jpeg artifacts, compression artifacts, glitch, overexposed, underexposed, low contrast, washed out colors, oversaturated, signature, username, artist name, logo, unnatural lighting, uneven lighting, harsh shadows, motion blur, out of focus, chromatic aberration, film grain, scratches, stains, dark spots, light leaks, fuzzy edges, jagged edges, broken lines, stretched image, elongated features, asymmetrical eyes, misaligned features, missing details, incomplete rendering"
 
 # API settings
 API_HOST = os.getenv("API_HOST", "0.0.0.0")