awesome-stable-diffusion

Automatic detection and detailing extension for WebUI.

Advanced ControlNet nodes with timestep scheduling and attention masks.

Native BrushNet and PowerPaint inpainting nodes for any checkpoint.

Auxiliary preprocessors for ControlNet hint images in ComfyUI.

ComfyUI nodes for Flux image editing via RF-Inversion and related methods.

Reference IP-Adapter nodes for image prompt conditioning in ComfyUI.

All-in-one training toolkit for FLUX/SDXL and other diffusion models.

Popular GUI wrapper around kohya training scripts.

Alternative network architectures for efficient fine-tuning.

Kohya training scripts specialized for video diffusion models.

Unified GUI and scripts for training diffusion models including FLUX and SDXL.

Core training scripts for DreamBooth and LoRA.

Opinionated, actively maintained fork of Stable Diffusion WebUI.

Most powerful modular diffusion GUI with a graph/nodes interface.

Utility and workflow enhancement nodes for ComfyUI.

Efficiency nodes that integrate common utilities for faster ComfyUI workflows.

Quality-of-life utility and model optimization nodes for ComfyUI.

Photoshop-style layer, mask and compositing nodes for ComfyUI.

Generate images inside Photoshop via A1111 backend.

Stable Diffusion integration for Blender.

Generate and inpaint with AI inside Krita.

Nodes for 3D mesh, 3DGS, and NeRF generation from images in ComfyUI.

Video frame interpolation nodes supporting RIFE, FILM, GMFSS and other VFI models.

Nodes for video loading, combining, batching, and frame utilities in ComfyUI.

Wrapper nodes for Wan video generation models in ComfyUI.

Video generation ecosystem built on diffusion models.

Create videos by morphing between text prompts in latent space.

GGUF quantization support for native ComfyUI models (FLUX/SD3).

ComfyUI nodes for 4-bit SVDQuant inference of FLUX and related models.

Native MLX port of FLUX and related models for Apple Silicon.

Native Stable Diffusion on Mac.

CLI-native local AI image/video/3D generation in Rust/Candle with CUDA/Metal and MCP.

Stable Diffusion and Flux inference in pure C/C++.

Detector, detailer, and upscaler nodes for image enhancement in ComfyUI.

Inpainting and object removal powered by modern AI models.

Practical AI image upscaler commonly used with Stable Diffusion.

Unified diffusion engine with VRAM management, training and inference for FLUX, Wan and SD models.

Official Hugging Face library for diffusion pipelines and training helpers.

Official inference code for FLUX.1 open-weight models.