image-generation

AUTOMATIC1111/stable-diffusion-webui

Stable Diffusion web UI

OpenMontageInc/OpenMontage

Turn Claude, Copilot or Cursor into a video production studio — OpenMontage adds 12 production pipelines, 100+ tools and 700+ agent skill files that teach coding assistants like Claude, Copilot or Cursor to plan, generate and edit video end-to-end. It even lets you paste a video you like as a starting reference, aimed at developers who want agentic video workflows without proprietary tools.

unslothai/unsloth

Unsloth ships a desktop app to run and fine-tune LLMs locally — Unsloth now offers a native desktop app for Windows, macOS and Linux that lets users run and train LLMs and diffusion models locally, supporting GGUF, MLX, Qwen3.8, DeepSeek-V4, MiniMax-H3, Gemma 4 and FLUX. It targets self-hosted, privacy-conscious users who want fine-tuning and inference without cloud dependency.

mudler/LocalAI

A self-hosted AI engine that swaps backends like plugins — LocalAI wraps llama.cpp, vLLM, whisper.cpp, stable-diffusion and MLX each in its own image instead of bundling everything, keeping the core small. It runs LLMs, vision, voice, image and video models via an OpenAI-compatible API on CPU or GPU, with agents, rerank and distributed/libp2p setups for self-hosting without a GPU requirement.

khoj-ai/khoj

Your AI second brain. Self-hostable. Get answers from the web or your docs. Build custom agents, schedule automations, do deep research. Turn any online or local LLM into your personal, autonomous AI (gpt, claude, gemini, llama, qwen, mistral). Get started - free.

huggingface/diffusers

🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch.

invoke-ai/InvokeAI

A polished local web UI for Stable Diffusion workflows — Invoke packages Stable Diffusion image generation into a React-based web UI with a free, commercially-friendly license, aimed at both professionals and hobbyists. It supports txt2img, img2img, inpainting, outpainting, and runs locally on Windows, macOS, or Linux, with a dedicated launcher for installation.

krillinai/OpenCreator

Rebranded KrillinAI becomes a Codex-powered creator workspace — OpenCreator, formerly KrillinAI, wraps Codex CLI with a local Runtime and visual workspace so creators can download, translate, dub, and edit video, images, and voice through reusable Agent Skills. It targets YouTuber, TikTok, and Instagram creators who want local, agent-driven production without rebuilding an agent loop themselves.

leejet/stable-diffusion.cpp

A ggml-based C/C++ engine keeps pace with the latest image and video diffusion models — Built on ggml like llama.cpp, this pure C/C++ inference engine now adds day-0/day-1 support for newly released models such as FLUX.3 Klein, Qwen-Image-2.1, MOSS-Image, LTX-2.5 and Z-Image, plus a new embedded web UI. Useful for developers wanting fast, dependency-light diffusion inference without Python frameworks.

PurpleDoubleD/locally-uncensored

A single desktop app for local chat, image, video, and coding AI — Locally Uncensored bundles chat, image/video generation and a coding agent into one free desktop app for Windows and Linux. It runs fully locally with no Docker, terminal or cloud, aiming at users who want private, uncensored AI without juggling separate tools or config files.

scenario-labs/skills

Agent skills that turn Scenario MCP into a game-asset production pipeline — These skills teach Claude Code, Cursor, Codex, Copilot and 70+ other agents to generate images, video, audio and 3D via the Scenario MCP server. They pick the right model, estimate cost before spending, keep characters/brands consistent, and include expert workflows for Blender, Maya, ZBrush, Unreal and Unity.

kane50613/takumi

One layout engine for JSX, HTML, and CSS. Render images, SVG, PDFs, or a paint tree. No headless browser.

OpenMOSS/MOSS-Image

A 5B DiT Foundation Model Built for Precise Text Rendering — MOSS-Image is a 5B-parameter base DiT model from OpenMOSS offering Base and SFT checkpoints, ComfyUI integration, and an API platform. It targets high-quality text rendering and layout generation in generated images, with support for efficient fine-tuning, making it useful for developers building controllable text-to-image applications.

techjarves/Portable-Local-Studio

A zero-setup, offline desktop studio bundling four AI model types — Portable AI Studio packages Stable Diffusion, GGUF LLM chat, Whisper speech-to-text, and Kokoro text-to-speech into one offline, zero-configuration app for Windows, Linux, and macOS. It uses GPU/NPU acceleration and skips cloud logins, tracking, or subscriptions, aimed at users wanting a self-contained local AI toolkit.

stockedge/manga-generator

Turn a Novel Into a Finished Manga PDF With Codex Driving the Pipeline — This tool guides Codex through scripting, storyboarding, image generation, lettering, review, and PDF export from a plain-text novel. Text and speech bubbles are placed separately from artwork, making dialogue easy to revise later. It targets non-engineers, with Codex handling setup and command execution end to end.