stable-diffusion-webui — A comprehensive web interface for Stable Diffusion implemented using the Gradio library, providing a wide array of tools for AI image generation and manipulation.

A comprehensive web interface for Stable Diffusion implemented using the Gradio library, providing a wide array of tools for AI image generation and manipulation.

About this project

Stable Diffusion web UI is a feature-rich browser-based interface for Stable Diffusion. It supports core functionalities such as text-to-image (txt2img) and image-to-image (img2img), alongside advanced tools including inpainting, outpainting, and color sketching. Key capabilities include: - Image Enhancement: Integration of various upscalers (RealESRGAN, ESRGAN, SwinIR, LDSR) and face restoration tools (GFPGAN, CodeFormer). - Prompt Control: Support for attention weighting, negative prompts, prompt editing mid-generation, and Composable Diffusion for multiple simultaneous prompts. - Model Management: Ability to merge checkpoints, load safetensors, and utilize Hypernetworks, LoRAs, and Textual Inversion embeddings. - Technical Features: X/Y/Z plotting for parameter testing, batch processing, and support for low-VRAM hardware (down to 2GB-4GB). - Integration: Support for Stable Diffusion 2.0, Alt-Diffusion, and Segmind Stable Diffusion, with an available API for external integration. The software is compatible with NVIDIA, AMD, Intel, and Apple Silicon hardware.