Image, video and design
Make and edit images, video and 3D, swap faces, upscale, or design graphics and interfaces.
taste-skill leads with 88, ahead of diffusers (81) and MoneyPrinterTurbo (76).33 projects ranked by score. Updated from public GitHub data.
On this page: Image and design (20), Video and animation (15), 3D (2).
In Best of Vibe Coding
13 projects, ranked by score.
| Rank | Project | Score |
|---|---|---|
| 1 | taste-skillAgent skills that steer coding agents toward distinctive landing-page design | 88 out of 100 |
| 2 | diagram-designAgent skill that draws brand-styled diagrams as single HTML and SVG files | 75 out of 100 |
| 3 | video-shotcraftClaude Code and Codex skill that builds promo videos with Remotion | 75 out of 100 |
| #4 | drawio-skillAgent skill that generates and syncs editable draw.io diagrams from prompts and code | 75 out of 100 |
| #5 | huashu-designAgent skill that turns prompts into HTML prototypes, decks, animations and infographics | 74 out of 100 |
| #6 | img2threejsAgent skill that rebuilds an image's object as procedural Three.js code | 74 out of 100 |
| #7 | bragAgent skill that renders a launch video for your project | 66 out of 100 |
| #8 | hallmarkDesign skill that steers coding agents away from generic AI-looking UI | 59 out of 100 |
| #9 | fireworks-tech-graphAgent skill that generates validated SVG, PNG, GIF and HTML technical diagrams | 56 out of 100 |
| #10 | cursor-talk-to-figma-mcpMCP server that lets Cursor or Claude Code read and edit Figma files | 52 out of 100 |
| #11 | ip-as-logo-skillAgent Skill that generates simple, cute animal mascot images from a brief | 49 out of 100 |
| #12 | m3e-canvasBrowser canvas for sketching linked Material 3 screens and exporting an AI prompt | 46 out of 100 |
| #13 | lottieAgent skill that generates Lottie animations from text prompts | 40 out of 100 |
In Best of Open-Source AI
20 projects, ranked by score.
| Rank | Project | Score |
|---|---|---|
| 1 | diffusersPyTorch library of diffusion pipelines and schedulers for image generation | 81 out of 100 |
| 2 | MoneyPrinterTurboTurns a topic into a short video with script, footage, voiceover and subtitles | 76 out of 100 |
| 3 | ComfyUINode-graph engine for diffusion image, video, audio and 3D models | 75 out of 100 |
| #4 | deep-live-camReal-time webcam face swap from a single source image | 75 out of 100 |
| #5 | toonflow-appInfinite-canvas tool for AI short drama and comic video production | 66 out of 100 |
| #6 | InvokeAICanvas-first web UI for Stable Diffusion and Flux image generation | 65 out of 100 |
| #7 | openmontageAgent-driven video production pipelines run from your AI coding assistant | 64 out of 100 |
| #8 | open-generative-aiImage, video and lip-sync studio UI that calls MuAPI, with optional local engines | 62 out of 100 |
| #9 | faceswapPython tool that trains neural models to swap faces in images and video | 49 out of 100 |
| #10 | lingbot-mapFeed-forward streaming 3D reconstruction and camera pose model for video | 48 out of 100 |
| #11 | opencreatorCreator workspace for video translation, image and video generation, built on Codex CLI | 47 out of 100 |
| #12 | Pixelle-VideoTopic-to-short-video pipeline built on ComfyUI workflows and TTS | 46 out of 100 |
| #13 | voice-proGradio web app for transcribing, translating and dubbing video with voice cloning | 43 out of 100 |
| #14 | Kohya's GUIGradio GUI and CLI for Kohya diffusion training scripts | 42 out of 100 |
| #15 | vimaxAgent pipeline that turns ideas, scripts or novels into multi-shot videos | 39 out of 100 |
| #16 | hivisionidphotosOffline ID photo maker: portrait matting, background swap, sizing and print layouts | 37 out of 100 |
| #17 | FluxGymWeb UI for training FLUX LoRAs on 12 to 20 GB GPUs | 36 out of 100 |
| #18 | upscaylDesktop image upscaler using Real-ESRGAN models over Vulkan | 31 out of 100 |
| #19 | open-llm-vtuberVoice-chat AI companion with a Live2D avatar and desktop pet mode | 30 out of 100 |
| #20 | video2xVideo upscaler and frame interpolator using Real-ESRGAN, Real-CUGAN, RIFE and Anime4K | 18 out of 100 |
A project's field comes from its own description: what it is made for. All fields.