Gradio app for textual inversion

README.md

@@ -1,14 +1,49 @@
----
-title: SD Textual Inversion Embeds
-emoji: 😻
-colorFrom: yellow
-colorTo: pink
-sdk: gradio
-sdk_version: 5.20.0
-app_file: app.py
-pinned: false
-license: mit
-short_description: Compare 5 different Embeds Style
----
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+# Style-Guided Image Generation with Purple Enhancement
+
+This Space demonstrates the use of various textual inversion style embeddings with Stable Diffusion, combined with a custom purple color enhancement technique.
+
+## Features
+
+- **Multiple Style Options**: Choose from 5 different artistic styles:
+  - Glitch Core (`001glitch-core`)
+  - Roth Style (`2814-roth`)
+  - Night Style (`4tnght`)
+  - 80s Anime (`80s-anime-ai`)
+  - Anime AI Being (`80s-anime-ai-being`)
+
+- **Purple Guidance**: Optional color enhancement that adds purple tones to the generated images
+- **Customizable Parameters**:
+  - Adjustable seed for reproducibility
+  - Control over purple guidance strength
+  - Custom prompt input
+
+## How to Use
+
+1. Enter your prompt in the text box
+2. Select a style from the radio buttons
+3. (Optional) Adjust the seed number for different variations
+4. (Optional) Enable purple guidance and adjust its strength
+5. Click "Submit" to generate the image
+
+## Examples
+
+The app includes several example combinations that you can try:
+- Mountain landscape with glitch effect
+- Magical forest in 80s anime style
+- Cyberpunk city with night style
+
+## Technical Details
+
+This application uses:
+- Stable Diffusion v1.4 as the base model
+- Textual Inversion embeddings from the Hugging Face Hub
+- Custom purple color guidance implementation
+- Gradio for the user interface
+
+## Credits
+
+Style embeddings are from the [SD Concepts Library](https://huggingface.co/sd-concepts-library) on Hugging Face.
+
+## License
+
+This project is released under the MIT License. The used models and embeddings maintain their original licenses. 

app.py

@@ -0,0 +1,120 @@
+import gradio as gr
+import torch
+from diffusers import StableDiffusionPipeline
+from huggingface_hub import hf_hub_download
+import numpy as np
+from PIL import Image
+import os
+
+# Suppress symlink warnings
+os.environ['HF_HUB_DISABLE_SYMLINKS_WARNING'] = "1"
+
+# Define styles
+styles = {
+    "glitch": {
+        "concept_url": "sd-concepts-library/001glitch-core",
+        "seed": 42,
+        "token": "<glitch-core>"
+    },
+    "roth": {
+        "concept_url": "sd-concepts-library/2814-roth",
+        "seed": 123,
+        "token": "<2814-roth>"
+    },
+    "night": {
+        "concept_url": "sd-concepts-library/4tnght",
+        "seed": 456,
+        "token": "<4tnght>"
+    },
+    "anime80s": {
+        "concept_url": "sd-concepts-library/80s-anime-ai",
+        "seed": 789,
+        "token": "<80s-anime>"
+    },
+    "animeai": {
+        "concept_url": "sd-concepts-library/80s-anime-ai-being",
+        "seed": 1024,
+        "token": "<80s-anime-being>"
+    }
+}
+
+def load_pipeline():
+    """Load and prepare the pipeline with all style embeddings"""
+    pipe = StableDiffusionPipeline.from_pretrained(
+        "CompVis/stable-diffusion-v1-4",
+        torch_dtype=torch.float16
+    ).to("cuda")
+    
+    # Load all embeddings
+    for style_info in styles.values():
+        embedding_path = hf_hub_download(
+            repo_id=style_info["concept_url"],
+            filename="learned_embeds.bin",
+            repo_type="model"
+        )
+        pipe.load_textual_inversion(embedding_path)
+    
+    return pipe
+
+def apply_purple_guidance(image, strength=0.5):
+    """Apply purple guidance to an image"""
+    img_array = np.array(image).astype(float)
+    purple_mask = (img_array[:,:,0] > 100) & (img_array[:,:,2] > 100)
+    img_array[purple_mask] = img_array[purple_mask] * (1 - strength) + np.array([128, 0, 128]) * strength
+    return Image.fromarray(np.uint8(img_array.clip(0, 255)))
+
+def generate_image(prompt, style, seed, apply_guidance, guidance_strength=0.5):
+    """Generate an image with selected style and optional purple guidance"""
+    if style not in styles:
+        return None
+    
+    # Get style info
+    style_info = styles[style]
+    
+    # Prepare generator
+    generator = torch.Generator("cuda").manual_seed(int(seed))
+    
+    # Create styled prompt
+    styled_prompt = f"{prompt} {style_info['token']}"
+    
+    # Generate image
+    image = pipe(
+        styled_prompt,
+        generator=generator,
+        guidance_scale=7.5,
+        num_inference_steps=50
+    ).images[0]
+    
+    # Apply purple guidance if requested
+    if apply_guidance:
+        image = apply_purple_guidance(image, guidance_strength)
+    
+    return image
+
+# Initialize the pipeline globally
+print("Loading pipeline and embeddings...")
+pipe = load_pipeline()
+
+# Create the Gradio interface
+demo = gr.Interface(
+    fn=generate_image,
+    inputs=[
+        gr.Textbox(label="Prompt", value="A serene mountain landscape with a lake at sunset"),
+        gr.Radio(choices=list(styles.keys()), label="Style", value="glitch"),
+        gr.Number(label="Seed", value=42),
+        gr.Checkbox(label="Apply Purple Guidance", value=False),
+        gr.Slider(minimum=0.0, maximum=1.0, value=0.5, label="Purple Guidance Strength")
+    ],
+    outputs=gr.Image(label="Generated Image"),
+    title="Style-Guided Image Generation with Purple Enhancement",
+    description="""Generate images in different styles with optional purple color guidance.
+    Choose a style, enter a prompt, and optionally apply purple color enhancement.""",
+    examples=[
+        ["A serene mountain landscape with a lake at sunset", "glitch", 42, True, 0.5],
+        ["A magical forest at twilight", "anime80s", 789, True, 0.7],
+        ["A cyberpunk city at night", "night", 456, False, 0.5],
+    ]
+)
+
+if __name__ == "__main__":
+    demo.launch() 

requirements.txt

@@ -0,0 +1,7 @@
+torch
+diffusers
+transformers
+gradio
+numpy
+Pillow
+accelerate