Open-source tools for Images & design

Image creation, visual design, UI, graphics and 3D tools.

Compare the supported inputs, editable outputs and hardware requirements. Check the licence for any model weights or assets used alongside the code.

61 projects

academiasd_loralab-trainerstudio academiasd · MIT
A one-install, one-launcher Flask app that lets you train your own LoRA AI image/video models on a budget consumer GPU, across nearly every major open image/video model.
agency-agents msitarzewski · MIT
Gives you a cast of specialized AI agent personas, each with its own personality and process, that install straight into Claude Code, Cursor, Codex, or Gemini.
agent-vision-toolkit anionex · MIT
Gives text-only AI coding agents the ability to understand images by handling image Q&A, screenshot OCR, and UI recognition outside the model itself.
ai-iso-skill mrbongoc · MIT
A Claude Code skill that draws interactive isometric diagrams as a single self-contained HTML file, just by describing what you want shown.
ai-system-design amitshekhariitbhu · Apache-2.0
A free, complete guide that teaches how to design real AI systems, step by step, from LLM inference and RAG to AI agents, guardrails, and cost optimization.
anymove patch-gg · Apache-2.0
Turns a single AI-generated video of any creature into a rigged 3D motion-capture animation, exported as a GLB, no mocap suit or manual keyframing needed.
artcraft storytold · Apache-2.0
ArtCraft is a free desktop app that turns AI image and video generation into a crafting tool: build scenes in 3D, pose characters, and generate with 60+ models…
astryx meta · MIT
Astryx is Meta's own open-sourced design system (150+ components, built on React 19 and StyleX) made so AI coding agents and human developers can both build with it the…
awesome-gpt-image-2 freestylefly · MIT
A large, curated library of reverse-engineered prompts and reusable templates for GPT-Image2, aimed at getting consistent, production-quality results from AI image…
awesome-opus5-5-videos yihui-dev · MIT
A curated collection of 513 prompts behind viral videos people made by asking Claude Opus 5.5 to write the animation as code, each linking to the creator's original post.
awwwards-mcp insane0777 · MIT
A free, open-source MCP server that lets your AI coding agent search real award-winning websites, pull their color palette and design DNA, and even record how a site…
blender-skills el4cteo · MIT
Gives AI coding assistants like Claude Code and Codex step-by-step skills to run professional 3D workflows in Blender: modeling, texturing, rigging, animation and export.
boardui boardui · MIT
BoardUI is a free, open-source kit of ready-made building blocks (chat windows, agent panels, dashboards) for anyone building an AI-powered app.
carrel fengzhenfei · MIT
Carrel is a self-hosted knowledge base for AI agents: it automatically parses, indexes and builds knowledge graphs from your documents (PDFs, Word, slides, code,…
codex-bridge sateezg · MIT
Lets Claude Code generate images and hand off heavy tasks to GPT-5, billed to your existing ChatGPT plan instead of a new API key.
comfyui comfy-org · GPL-3.0
ComfyUI is a free, node-based visual interface for running diffusion models like Stable Diffusion locally, so you can build AI image and video generation workflows by…
comfyui-h3-facerefine carasibana · MIT
A ComfyUI add-on that automatically detects, crops, and re-renders small faces in MiniMax H3-generated video so they come out sharp instead of blurry.
dioramas blendi-remade · MIT
An open-source framework that turns a text prompt into a 3D hero object (via AI image + image-to-3D generation) and drops it into a cinematic, interactive landing page,…
editor pascalorg · MIT
An open-source, local-first 3D building editor (React Three Fiber + WebGPU) that AI agents can connect to via MCP to place furniture, adjust floor plans, and check…
fable51-worlds philolabs · MIT
AI agent swarms build walk-through 3D models of real neighbourhoods that run in your browser as plain Three.js apps.
garden-skills conardli · MIT
A ready-made library of skills that plug into AI coding agents to do things like generate images, build web pages, and turn sources into polished articles.
gimp-openfill beckettharriman · GPL-3.0
A free GIMP 3 plugin that brings Photoshop-style Generative Fill, object removal, and Generative Expand to your own machine using local Stable Diffusion/FLUX models.
gitaviswa himanshumohanty-git24 · MIT
GitaVisva turns the Bhagavad Gita into an explorable 3D knowledge graph with 20 classical commentaries, and lets you ask it questions in plain English that it answers…
heiss-ui tristmeister · MIT
A free local app that sits on top of ComfyUI so you can type a prompt and watch an AI image or video render, without ever touching the node graph underneath.
imagegen-mac ph1lb4 · MIT
A native Mac app that runs an image-generation AI model fully on your own device, so you can create and edit images offline with no subscription, no API key, and…
ip-as-logo-skill s1dashu · MIT
ip-as-logo-skill is an installable AI agent skill (Codex, Doubao, and compatible agents) that guides image generation to produce simple, cute, commercially usable…
iris-3b speridlabs · Apache-2.0
A 3-billion-parameter diffusion model that paints images pixel by pixel instead of compressing through a VAE first, and the same base model also sharpens blurry photos…
iris-3b-metal tky-27 · Apache-2.0
A native macOS app and local engine that runs the Iris-3B pixel-space text-to-image model directly on Apple Silicon GPUs, so you can generate, restore and upscale…
khan-explainer haiderfarooq3 · MIT
A free, local Claude Code skill that generates Khan-Academy-style explainer videos: a pen draws on a whiteboard while an AI voice narrates, no cloud API keys needed.
kilnframe erhanmeydan · Apache-2.0
A free Premiere Pro/DaVinci Resolve plugin that listens to what you say and generates matching animated inserts and music, rendered locally.
kokon gabrielelozupone · AGPL-3.0
A free app for Windows and Mac that lets you edit a photo just by describing the change you want, running fully offline on your own GPU with no cloud upload.
longcat-video meituan-longcat · MIT
LongCat-Video is a 13.6B-parameter AI model that generates minutes-long, high-quality videos from text or images without quality degradation.
manga-generator stockedge · MIT
Hands a novel or short story to an AI coding agent and gets back a finished manga: script, AI-generated artwork, lettering and a PDF, with a real published example on…
markitdown microsoft · MIT
Converts PDFs, Word, PowerPoint, Excel, images and audio into clean Markdown so the text is ready to feed into an LLM.
mediagen cripacx · MIT
mediagen is an installable skill that gives AI coding agents like Claude Code one CLI/MCP server for image and video generation across three providers, with built-in EU…
mesh-avatar-studio shinshin86 · MIT
Give it one character illustration and a coding agent builds an animated talking avatar you can fine-tune in a local editor.
mono-color-skill yanliudesign · MIT
Open-source agent skill that turns a theme, sentence, object, or photo into an original one-ink editorial print style image, rebuilding a visual system around the…
moss-image openmoss · Apache-2.0
An open-source text-to-image AI model from the OpenMOSS research group that can place text and visual elements exactly where you want and render that text clearly and…
ods osmantic · Apache-2.0
Installs and connects everything needed to run AI locally so you get a private AI server without assembling the pieces by hand.
officely tahirpathan-ailab · Apache-2.0
A 3D virtual office where four AI agents collaborate on real tasks like email, file management, and GitHub, delegated by a reception-manager agent.
OG Converter dr-at0mic · GPL-3.0-or-later
Office workers can turn Word, Excel and PowerPoint files into PDFs, merge or split PDFs, and password-protect documents without uploading them to a website. Students…
oil-ui oil-oil · MIT
A free Claude Code / Codex skill that makes AI explore several genuinely different UI design directions, lines them up side by side for you to pick, then refines the…
openfill beckettharriman · Apache-2.0
A free, local generative-fill plugin for GIMP 3 and PhotoCraft that lets you remove objects, fill selections from a text prompt, and expand canvases, all running on…
openmontage calesthio · AGPL-3.0
Turns your AI coding assistant into a full video production studio: describe what you want and it researches, scripts, generates assets, edits, and renders a finished…
orbis-pictus 0toshigami · MIT
Orbis Pictus is an open-source homage to flipbook.page: an infinite browsing experience made entirely of AI-generated images, where clicking anything on the page makes…
qwen-image-2.1-studio janishar · MIT
A free local studio that lets you generate and edit images from text prompts on your own Mac using the Qwen-Image-2.1 model, with a prompt enhancer and a browser UI, no…
README Templates dr-at0mic · GPL-3.0-or-later
README Templates is a desktop app for Windows and Linux, which you can also run yourself as a web app. It helps you design a GitHub profile README and publish it. You…
sand3d sandflow-ai · Apache-2.0
A Python library that lets an AI model describe a 3D object as a short program instead of needing CAD or 3D-modeling skills, with a live docs site and a Hugging Face…
scene-card-studio swping999 · Apache-2.0
Turns a folder of personal photos into a structured, editable visual narrative using AI direction.
scroll-craft nateherkai · MIT
A Claude Code skill that builds premium scroll-driven websites and grades its own output against a real design standard, using a headless browser to catch dead scroll…
scroll-studio okohedeki · AGPL-3.0
Scroll Studio turns a single YAML file into a scrolling, AI-generated website: locally generated video, hand-drawn artwork, live 3D zooms, data stories, and map…
seam jdnichollsc · MIT
Give it a start and end photo and it generates the AI video transition between them (smoke, water bend, whip pan) on your own GPU, no cloud render needed.
skills scenario-labs · MIT
A skill pack that lets any AI agent generate ready-to-use images, video, audio and 3D assets while keeping characters and brand style consistent, and even drive…
solid-glass deeplethe · MIT
A free, documented design system for building polished AI chat and agent UIs, with an official site and 13-item component registry.
sparky anisayari · MIT
A free, open-source private AI assistant for Windows that runs entirely offline: chat like ChatGPT, see images, generate pictures and videos with sound, search your own…
stable-diffusion.cpp leejet · MIT
Lets you run popular image and video generation models like Stable Diffusion, Flux, and Qwen Image without Python or a GPU-heavy setup.
syncso syncso-inc · MIT
SyncSo is an MCP server that feeds AI agents live, real-time data about what is actually happening in a city right now (events, classes, shows, bookings), instead of…
taste-skill leonxlnx · MIT
An open-source Agent Skill that gives AI coding agents real art direction, actual reference photographs, and a way to check its own output in a browser, so the pages it…
trompe patch-gg · Apache-2.0
Turns a plain gray 3D game level into a fully textured one using AI image models, baking real shadows into the texture instead of faking them.
unsloth unslothai · Apache-2.0
A free local app for running and training your own AI language and image models on your own machine.
whatsmyagentdoing charonyuu · MIT
Type /myoffice and see every Claude Code/Codex agent on your machine rendered as a character in a 3D office, working at a desk or wandering when idle.