Spaces:
Running
on
Zero
Running
on
Zero
| #import spaces | |
| import gradio as gr | |
| from PIL import Image | |
| import torch | |
| import os | |
| import gc | |
| from pathlib import Path | |
| from model import ( | |
| process_images, | |
| DEVICE, | |
| DIMENSION, | |
| MODEL_ID | |
| ) | |
| import logging | |
| logging.disable(logging.WARNING) | |
| def create_interface(): | |
| with gr.Blocks() as demo: | |
| gr.Markdown(""" | |
| # Diffusion Style Transfer with Feature, Style, and Latent Loss | |
| This tool combines Stable Diffusion with VGG feature control and latent matching to create styled images. | |
| """) | |
| with gr.Row(): | |
| with gr.Column(scale=1): | |
| init_image = gr.Image( | |
| label="Initial Image", | |
| type="pil", | |
| height=384 | |
| ) | |
| style_image = gr.Image( | |
| label="Style Image", | |
| type="pil", | |
| height=384 | |
| ) | |
| with gr.Column(scale=1): | |
| prompt = gr.Textbox( | |
| label="Prompt", | |
| lines=2 | |
| ) | |
| negative_prompt = gr.Textbox( | |
| label="Negative Prompt", | |
| value="extra details, jpeg artifacts, chromatic aberration" | |
| ) | |
| with gr.Row(): | |
| inference_steps = gr.Slider( | |
| minimum=20, | |
| maximum=100, | |
| value=60, | |
| step=1, | |
| label="Inference Steps" | |
| ) | |
| strength = gr.Slider( | |
| minimum=0.0, | |
| maximum=1.0, | |
| value=0.2, | |
| step=0.05, | |
| label="Initial Image Strength" | |
| ) | |
| gr.Markdown("### Gram Matrix Based Style Guidance Scales") | |
| with gr.Row(): | |
| style_guidance_1 = gr.Slider(minimum=0.0, maximum=2.0, value=1., step=0.1, label="Texture Fundamentals") | |
| with gr.Row(): | |
| style_guidance_2 = gr.Slider(minimum=0.0, maximum=2.0, value=1., step=0.1, label="Pattern Assembly") | |
| with gr.Row(): | |
| style_guidance_3 = gr.Slider(minimum=0.0, maximum=2.0, value=1., step=0.1, label="Style Motifs") | |
| with gr.Row(): | |
| style_guidance_4 = gr.Slider(minimum=0.0, maximum=2.0, value=1., step=0.1, label="Compositional Grammar") | |
| with gr.Row(): | |
| style_guidance_5 = gr.Slider(minimum=0.0, maximum=2.0, value=1., step=0.1, label="Style Signature") | |
| gr.Markdown("### Feature/Perceptual Based Content Guidance Scales") | |
| with gr.Row(): | |
| content_guidance_1 = gr.Slider(minimum=0.0, maximum=20, value=1.0, step=0.5, label="Edge Detector") | |
| with gr.Row(): | |
| content_guidance_2 = gr.Slider(minimum=0.0, maximum=20, value=1.0, step=0.5, label="Shape Assembler") | |
| with gr.Row(): | |
| content_guidance_3 = gr.Slider(minimum=0.0, maximum=20, value=0.0, step=0.5, label="Part Recognizer") | |
| with gr.Row(): | |
| content_guidance_4 = gr.Slider(minimum=0.0, maximum=20, value=0.0, step=0.5, label="Object Former") | |
| with gr.Row(): | |
| content_guidance_5 = gr.Slider(minimum=0.0, maximum=20, value=0.0, step=0.5, label="Scene Integrator") | |
| gr.Markdown("### Latent Space Guidance") | |
| latent_guidance = gr.Slider( | |
| minimum=0, | |
| maximum=1000, | |
| value=24, | |
| step=1, | |
| label="Latent Space Closeness", | |
| info="Controls how closely the output matches the style image in latent space" | |
| ) | |
| run_button = gr.Button("Generate") | |
| with gr.Column(scale=1): | |
| output = gr.Image( | |
| label="Output", | |
| height=384 | |
| ) | |
| gr.Markdown(""" | |
| The process works in three main steps: | |
| 1. **Initial Image Processing** | |
| - Your input image is partially noised based on the 'Initial Image Strength' | |
| - Higher strength means more noise, allowing more creative freedom but less preservation of original content | |
| 2. **Diffusion Denoising** | |
| - The image is gradually denoised using Stable Diffusion | |
| - The process is guided by your prompt and negative prompt | |
| - Takes place over the specified number of inference steps | |
| 3. **Multi-Level Style and Content Control** | |
| - During denoising, three types of guidance shape the output: | |
| **Style Features** (VGG16 layers): | |
| * Texture Fundamentals: Basic textures and edges | |
| * Pattern Assembly: Repeated elements and patterns | |
| * Style Motifs: Distinctive style elements | |
| * Compositional Grammar: Arrangement of elements | |
| * Style Signature: Overall artistic style | |
| **Content Features** (VGG16 layers): | |
| * Edge Detector: Basic lines and boundaries | |
| * Shape Assembler: Simple geometric forms | |
| * Part Recognizer: Complex shapes and parts | |
| * Object Former: Complete object representations | |
| * Scene Integrator: Overall composition | |
| **Latent Space Matching**: | |
| * Controls how closely the output matches the style image in Stable Diffusion's latent space | |
| * Higher values enforce stronger similarity to the style image's overall structure | |
| * Lower values allow more freedom for the other guidance systems | |
| ### Tips for Best Results | |
| - Start with lower strength (0.2-0.4) to preserve more of your initial image | |
| - Use higher style guidance for stronger artistic effect | |
| - Focus content guidance on middle layers for best object preservation | |
| - Balance latent loss weight: | |
| * Higher (30-50) for closer style image matching | |
| * Lower (10-20) for more creative interpretations | |
| [Read more here in my blog post](http://christhomas.co.uk/blog/2025/02/17/how-to-guide-stable-diffusion-with-vgg-features-style-loss-and-latent-mae/) | |
| [Github repo](https://github.com/chris-thomas/steering-stable-diffusion) | |
| """) | |
| run_button.click( | |
| fn=process_images, | |
| inputs=[ | |
| init_image, | |
| style_image, | |
| prompt, | |
| negative_prompt, | |
| inference_steps, | |
| strength, | |
| style_guidance_1, | |
| style_guidance_2, | |
| style_guidance_3, | |
| style_guidance_4, | |
| style_guidance_5, | |
| content_guidance_1, | |
| content_guidance_2, | |
| content_guidance_3, | |
| content_guidance_4, | |
| content_guidance_5, | |
| latent_guidance | |
| ], | |
| outputs=output | |
| ) | |
| return demo | |
| if __name__ == "__main__": | |
| demo = create_interface() | |
| demo.launch() | |