- OpenMontage by calesthio, 81k stars. Agentic video production pipelines and tools for AI coding assistants
- unsloth by unslothai, 80k stars. Local UI for running and fine-tuning LLMs and diffusion models
- diffusers by huggingface, 35k stars. Library of diffusion models for generating images, video and audio
- Pixelle-Video by ATH-MaaS, 30k stars. Automated short video generator using LLM scripts, TTS and ComfyUI images
- InvokeAI by invoke-ai, 29k stars. Creative engine and UI for generating and editing images with Stable Diffusion
- awesome-gpt-image-2-API-Prompts by Evolink-AI, 17k stars. Collection of prompts and API examples for GPT-Image-2
- garden-skills by ConardLi, 15k stars. Collection of agent skills for web design, retrieval and image generation
- Sana by NVlabs, 9.8k stars. Efficient diffusion models and inference engines for image and video
- ip-as-logo-skill by s1dashu, 6.6k stars. Codex skill that generates rounded mascot logo designs from an IP concept
- clarity-upscaler by philz1337x, 5.2k stars. Open source AI image upscaler and enhancer that adds detail
- locally-uncensored by PurpleDoubleD, 4.3k stars. Desktop app for local chat, image and video generation, and a coding agent
- gpt_image_playground by CookSleep, 4.1k stars. Web app for generating and editing images with the OpenAI image API
- skills by scenario-labs, 3.8k stars. Agent skills for generating images, video, audio and 3D through an MCP server
- OGAM by off-grid-ai, 3.4k stars. Offline app for running GGUF models, vision, speech, and image generation locally
- ideogram4 by ideogram-oss, 2.9k stars. Open image generation model aimed at design-focused images
- lyra by nv-tlabs, 2.9k stars. Open generative model for building 3D worlds with diffusion and Gaussians
- Qwen-Image-2.1 by QwenLM, 2.2k stars. Open-source image generation model from Qwen
- Portable-Local-Studio by techjarves, 2.0k stars. Portable offline GUI for image generation, GGUF LLMs and speech tools
- nano-banana-pro-prompts-recommend-skill by YouMind-OpenLab, 1.9k stars. Skill that finds image prompts by use case from a set of over 10,000
- StableGen by sakalond, 1.7k stars. Blender add-on that textures 3D models using Stable Diffusion and ControlNet
- dsh-image-gen by shanliuling, 1.5k stars. Image generation and editing plugin for DeepSeek Harness with ComfyUI support
- Lance by bytedance, 1.4k stars. 3B-active unified model for image and video understanding, generation and editing
- airunner by Capsize-Games, 1.3k stars. Offline engine for image generation, voice chat and local LLM workflows
- AI-Visual-Prompt-Cookbook by VigoZhao, 846 stars. Collection of JSON style prompts for consistent AI image generation
- AlayaRenderer by AlayaLab, 653 stars. Diffusion-based neural renderer for game and virtual world scenes
- FluxRT by tensorforger, 478 stars. Real-time video stream editing pipeline using a FLUX diffusion model on consumer GPUs
- kokon by GabrieleLozupone, 411 stars. Describe a photo edit and run it on your own GPU, with an MCP server
- ComfyUI-outputlists-combiner by geroldmeisinger, 210 stars. ComfyUI nodes to batch prompts, images and lists from files in one run
- awesome-qwen-image by wildminder, 166 stars. Curated list of Qwen-Image checkpoints, quants, LoRAs and ComfyUI tools
- ZPix by SamuelTallet, 163 stars. Local image generator and editor that runs open image models on your machine
- diffusion-bench by End2End-Diffusion, 109 stars. Benchmark suite for evaluating diffusion transformer generative models
- LinCa by QHR69, 35 stars. Trainable caching method that speeds up diffusion model inference
- GADC by 2018cx, 11 stars. PyTorch code for dataset condensation to train diffusion models, ICML 2026
- Lens by microsoft, 2 stars. 3.8B-parameter text-to-image diffusion model that rivals FLUX and SD3
New repos every two days, stars refreshed daily. Visits are counted without cookies, and the numbers are public. How it works Data RSS Newsletter