# The Diffusion Index

> The living index of AI image & video generation tooling — diffusion frameworks,
> video models, ComfyUI nodes, training & editing — ranked daily by GitHub momentum.

Updated: 2026-08-24T09:54:58.808190+00:00
Tools indexed: 260

## Top generation tools by momentum

- [Comfy-Org/ComfyUI](https://github.com/Comfy-Org/ComfyUI) — momentum 86, ⭐129665 — ComfyUI & Nodes — The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.
- [unslothai/unsloth](https://github.com/unslothai/unsloth) — momentum 83, ⭐74571 — Diffusion Frameworks — Local UI to run and train LLMs and diffusion models, including Qwen3.8, Kimi K3, MiniMax-H3, Gemma 4
- [huggingface/diffusers](https://github.com/huggingface/diffusers) — momentum 80, ⭐34364 — Diffusion Frameworks — 🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch.
- [invoke-ai/InvokeAI](https://github.com/invoke-ai/InvokeAI) — momentum 79, ⭐27954 — WebUIs & Apps — Invoke is a leading creative engine for Stable Diffusion models, empowering professionals, artists, 
- [Anil-matcha/Open-Generative-AI](https://github.com/Anil-matcha/Open-Generative-AI) — momentum 79, ⭐26987 — Diffusion Frameworks — Unrestricted Open-source alternative to AI video platforms — Free AI image & video generation studio
- [HBAI-Ltd/Toonflow-app](https://github.com/HBAI-Ltd/Toonflow-app) — momentum 76, ⭐14439 — WebUIs & Apps — Toonflow 是开源一站式 AI 短剧创作工具，将小说、剧本快速转化为动画短剧。集成 AI 编剧、智能分镜、角色与视频生成，跨平台桌面端轻量部署，助力创作者低成本批量产出视觉内容。Toonflow
- [vercel/satori](https://github.com/vercel/satori) — momentum 75, ⭐13846 — Image Models — Enlightened library to convert HTML and CSS to SVG
- [waooAI/waoowaoo](https://github.com/waooAI/waoowaoo) — momentum 74, ⭐13790 — Video Generation — 首家工业级全流程 AI 影视生产平台。Industry-first professional AI Agent platform for controllable film & video produ
- [Acly/krita-ai-diffusion](https://github.com/Acly/krita-ai-diffusion) — momentum 74, ⭐10499 — Editing & Control — Streamlined interface for generating images with AI in Krita. Inpaint and outpaint with optional tex
- [MengTo/kage](https://github.com/MengTo/kage) — momentum 74, ⭐1347 — Image Models — An interactive five-chapter night walk through a Kyoto mountain temple, rendered live in Three.js.
- [NVlabs/Sana](https://github.com/NVlabs/Sana) — momentum 73, ⭐8809 — Video Generation — SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformer
- [LykosAI/StabilityMatrix](https://github.com/LykosAI/StabilityMatrix) — momentum 73, ⭐8668 — ComfyUI & Nodes — Multi-Platform Package Manager for Stable Diffusion
- [MochiDiffusion/MochiDiffusion](https://github.com/MochiDiffusion/MochiDiffusion) — momentum 73, ⭐7926 — Image Models — Run Stable Diffusion on Mac natively
- [vladmandic/sdnext](https://github.com/vladmandic/sdnext) — momentum 73, ⭐7316 — WebUIs & Apps — SD.Next: All-in-one WebUI for AI generative image and video creation, captioning and processing
- [civitai/civitai](https://github.com/civitai/civitai) — momentum 73, ⭐7232 — Training & Fine-tuning — A repository of models, textual inversions, and more
- [leejet/stable-diffusion.cpp](https://github.com/leejet/stable-diffusion.cpp) — momentum 72, ⭐6827 — Diffusion Frameworks — Diffusion model(SD,Flux,Wan,Qwen Image,Z-Image,...) inference in pure C/C++
- [vllm-project/vllm-omni](https://github.com/vllm-project/vllm-omni) — momentum 72, ⭐6288 — Video Generation — A framework for efficient model inference with omni-modality models
- [marceloprates/prettymaps](https://github.com/marceloprates/prettymaps) — momentum 71, ⭐13964 — Image Models — Draw pretty maps from OpenStreetMap data! Built with osmnx +matplotlib + shapely
- [Akegarasu/lora-scripts](https://github.com/Akegarasu/lora-scripts) — momentum 71, ⭐6110 — Training & Fine-tuning — SD-Trainer. LoRA & Dreambooth training scripts & GUI use kohya-ss's trainer, for diffusion model.
- [williamngan/pts](https://github.com/williamngan/pts) — momentum 71, ⭐5342 — Image Models — A library for visualization and creative-coding
- [wiltodelta/remove-ai-watermarks](https://github.com/wiltodelta/remove-ai-watermarks) — momentum 71, ⭐5181 — ComfyUI & Nodes — Remove visible and invisible AI watermarks and provenance metadata from images and video. Python lib
- [HKUDS/ViMax](https://github.com/HKUDS/ViMax) — momentum 70, ⭐12084 — Video Generation — "ViMax: Agentic Video Generation (Director, Screenwriter, Producer, and Video Generator All-in-One)"
- [Osmantic/ODS](https://github.com/Osmantic/ODS) — momentum 70, ⭐4660 — ComfyUI & Nodes — Turn your PC, Mac, or Linux box into an AI server.  LLM inference, chat UI, voice, agents, workflows
- [mcmonkeyprojects/SwarmUI](https://github.com/mcmonkeyprojects/SwarmUI) — momentum 70, ⭐4484 — ComfyUI & Nodes — SwarmUI (formerly StableSwarmUI), A Modular Stable Diffusion Web-User-Interface, with an emphasis on
- [dramaclaw/dramaclaw](https://github.com/dramaclaw/dramaclaw) — momentum 70, ⭐4157 — Video Generation — A general-purpose AIGC video engine: script to finished film in one pipeline — dramas, ads, product 
- [ArcReel/ArcReel](https://github.com/ArcReel/ArcReel) — momentum 70, ⭐4149 — Video Generation — AI Agent 驱动的开源可自部署视频工作台：将小说与剧本转为角色、场景、道具资产、分镜、视频和剪映草稿，支持跨镜头一致性、多供应商与费用追踪 | Self-hosted AI video work
- [hao-ai-lab/FastVideo](https://github.com/hao-ai-lab/FastVideo) — momentum 70, ⭐4041 — Diffusion Frameworks — A unified inference and post-training framework for accelerated video generation.
- [easydiffusion/easydiffusion](https://github.com/easydiffusion/easydiffusion) — momentum 69, ⭐10449 — WebUIs & Apps — An easy 1-click way to create beautiful artwork on your PC using AI, with no tech knowledge. Provide
- [transformerlab/transformerlab-app](https://github.com/transformerlab/transformerlab-app) — momentum 69, ⭐5179 — Training & Fine-tuning — The open source research environment for AI researchers to seamlessly train, evaluate, and scale mod
- [Lightricks/ComfyUI-LTXVideo](https://github.com/Lightricks/ComfyUI-LTXVideo) — momentum 69, ⭐4092 — ComfyUI & Nodes — LTX-Video Support for ComfyUI
- [Hunyuan-PromptEnhancer/PromptEnhancer](https://github.com/Hunyuan-PromptEnhancer/PromptEnhancer) — momentum 69, ⭐3754 — Editing & Control — [CVPR 2026] PromptEnhancer is a prompt-rewriting tool, refining prompts into clearer, structured ver
- [rgthree/rgthree-comfy](https://github.com/rgthree/rgthree-comfy) — momentum 69, ⭐3393 — ComfyUI & Nodes — Making ComfyUI more comfortable!
- [bghira/SimpleTuner](https://github.com/bghira/SimpleTuner) — momentum 68, ⭐2907 — Diffusion Frameworks — A general fine-tuning kit geared toward image/video/audio diffusion models.
- [ModelTC/LightX2V](https://github.com/ModelTC/LightX2V) — momentum 68, ⭐2714 — Diffusion Frameworks — Lightweight Image Video Action Generation Inference Framework
- [heshengtao/super-agent-party](https://github.com/heshengtao/super-agent-party) — momentum 68, ⭐2599 — ComfyUI & Nodes — ⭐ All-in-one AI companion! Super Agent Party = Self hosted neuro sama + openclaw! ⭐ 全能AI伴侣！超级智能体派对 =
- [darkzOGx/youtube-automation-agent](https://github.com/darkzOGx/youtube-automation-agent) — momentum 68, ⭐2554 — Video Generation — 🎬 Fully automated YouTube channel management with AI agents. Creates, optimizes & publishes videos 2
- [yuanzhongqiao/printfilm](https://github.com/yuanzhongqiao/printfilm) — momentum 67, ⭐3886 — Video Generation — 短剧平台 AI Short Film  Motion Comic Generation Platform Industrial AI Motion Comic & Video Workbench
- [MaximeVandegar/Papers-in-100-Lines-of-Code](https://github.com/MaximeVandegar/Papers-in-100-Lines-of-Code) — momentum 67, ⭐2863 — Image Models — Implementation of papers in 100 lines of code.
- [1038lab/ComfyUI-RMBG](https://github.com/1038lab/ComfyUI-RMBG) — momentum 67, ⭐2081 — ComfyUI & Nodes — A ComfyUI custom node designed for advanced image background removal and object, face, clothes, and 
- [PKU-YuanGroup/Helios](https://github.com/PKU-YuanGroup/Helios) — momentum 67, ⭐2072 — Video Generation — Helios: Real Real-Time Long Video Generation Model