fast-stable-diffusion + DreamBooth

SD.Next: All-in-one WebUI for AI generative image and video creation

SUPIR aims at developing Practical Algorithms for Photo-Realistic Image Restoration In the Wild. Our new online demo is also released at suppixel.ai.

OneDiff: An out-of-the-box acceleration library for diffusion models.

A collection of ComfyUI custom nodes.- Awesome smart way to work with nodes!

PALLAIDIUM — a generative AI movie studio, seamlessly integrated into the Blender Video Editor (VSE), enabling end-to-end production from script to screen and back.

HyperGen - Optimized inference and fine-tuning framework for diffusion (image & video) models. Up to 3x faster & 80% less VRAM.

✨ Hotshot-XL: State-of-the-art AI text-to-GIF model trained to work alongside Stable Diffusion XL

Custom nodes for SDXL and SD1.5 including Multi-ControlNet, LoRA, Aspect Ratio, Process Switches, and many more nodes.

ComfyUI docker images for use in GPU cloud and local environments. Includes AI-Dock base for authentication and improved user experience.

Custom nodes and workflows for SDXL in ComfyUI

Enhanced version of Fooocus for SDXL, more suitable for Chinese and Cloud

A microframework on top of PyTorch with first-class citizen APIs for foundation model adaptation

FastAPI powered API for Fooocus

⚡ Flash Diffusion ⚡: Accelerating Any Conditional Diffusion Model for Few Steps Image Generation (AAAI 2025 Oral)

ComfyUI as a serverless API on RunPod

A demo application using fal.realtime and the lightning fast SDXL API provided by fal

A Versatile and Robust SDXL-ControlNet Model for Adaptable Line Art Conditioning

♾️ Helix is a private GenAI stack for building AI agents with declarative pipelines, knowledge (RAG), API bindings, and first-class testing.

📚A curated list of Awesome Diffusion Inference Papers with Codes: Sampling, Cache, Quantization, Parallelism, etc.🎉