Generative media: what’s taking off on GitHub
The fastest-growing repositories in “Generative media”: plain-language summaries, use cases and a check on star quality. Updated every 30 minutes.
-
8.0
paipiange/nvzhuang
A static catalog of 1407 AI-generated women's clothing images with bilingual search and optional virtual try-on via external image generation models.
-
7.0
anhao/ai-pose-gallery-zh
Chinese localization of an AI pose reference gallery: 1439 records and 2878 images with a ready-to-deploy dependency-free static site. Useful for artists and 3D modelers picking poses.
-
6.7
sleepy-zone/ai-ref-library-cn
A Chinese-language search interface for three sets of AI drawing reference materials (faces, poses, clothing) by author agi/gia, with translated tags, bilingual search and one-click prompt copying.
-
6.1
D3voz/openjutsu
A local web app for swapping characters and objects in videos: drop a video and a character photo, and the main person in the frame is replaced by your character while camera, cuts and soundtrack stay intact. Runs on…
-
5.7
Pika-Labs/Pika-H3-Flex
Pika H3 Flex model for local inference of video generation with synchronized stereo audio in six sampling steps, supporting text, endpoint frames and multimodal references.
-
5.5
OpenSenseNova/SenseNova-6.8-Code2Video
An open lightweight model that creates short videos by generating and rendering executable code, built on Qwen3.8-27B with 512K context. Aimed at researchers exploring programmatic video creation.
-
5.1
wquguru/shisei
A CC0 pose reference library of faceless mannequin line-art drawings: 280 poses across four series, each drawn from five camera angles, meant to be fed to AI image tools as pose references. Names and categories in…
-
5.1
speridlabs/idol-sdk
Idol is an inference SDK that turns a single image of an object into a 3D Gaussian splat, including unseen sides, running on consumer GPUs with 7.2 GB VRAM in under 2 seconds.
-
5.0
Ka1-S/LYNX-SHARE
Lightweight open-source DAW in C++20/JUCE that recreates the FL Studio workflow (Channel Rack, Piano Roll, Playlist, Mixer) and imports .flp projects. Runs on Windows, macOS and Linux with built-in plugins inspired by…
-
5.0
pyqdcyy123-byte/IP-Bot
An Electron/Vue desktop workspace that chains script rewriting, speech synthesis, digital-human video generation, subtitles, music and multi-platform publishing into one flow, with an Express/SQLite admin backend.
-
4.9
debpalash/VoiceStudio
A fully local, open-source ElevenLabs alternative for voice cloning, voice design, video dubbing, dictation, transcription and audiobook creation on your own hardware, with no account or API key. Supports 16 TTS and 11…
-
4.9
MUSE-AI-Lab/Concept-Brittleness
Research code for interpreting and fixing object-dependent concept brittleness in text-to-image diffusion models: a sparse autoencoder is trained per denoising step to locate missing concept dimensions and correct…
-
4.8
wzc520pyfm/gen-ai-pose-image
Web studio and DeepSeek Harness plugin that generates images of the whale-girl model Dafeiyu from pose sketches and costume sets, with pose and outfit swapping.
-
4.8
Vibha-Ramprakash/claude-video-effects
A set of 42 video effects for Claude Code: drop a talking-head clip into the chat and type /effects with an effect name — Claude renders the result with face tracking.
-
4.7
andyhuo520/vibe-knowledge
A Claude Code skill that turns a single knowledge point into a narrated explainer short video with cited sources, using 44 visual styles and frame-by-frame code rendering.
-
4.6
toyxyz/toyxyz_RGBMocap
Native Windows app for video motion capture: reconstructs 3D human animation with ExMR, FlowHMR and GVHMR models, corrects contacts and exports FBX/VMD.
-
4.4
heygen-com/hyperframes
Framework for turning HTML, CSS, media and seekable animations into deterministic MP4 videos. Runs locally via CLI or from AI coding agents through a set of skills.
-
4.3
actionow-ai/vvv
A set of editable Remotion video templates plus an Agent Skill for Claude Code, Codex and other agents: the agent picks a template, fills in photos and copy, renders and checks the video.
-
4.0
wangweihong/comfyui-pose-gallery
A ComfyUI custom node that adds a local Chinese pose gallery with 1,439 images and 288 poses (up to 5 views each), letting you pick a pose and feed it into depth-control or pose-editing workflows.
-
4.0
lemomo-ai/lemo-opuscar
A collection of 39 film styles, each with a reusable style prompt, a short film made entirely in code (Canvas/WebGL, TTS, ffmpeg), and DIRECTOR.md/TECHNIQUE.md guides for an AI agent director.
-
3.8
remotion-dev/remotion
A framework for making videos programmatically with React: React code is the source of truth, and rendering can run on your own infrastructure or in the cloud. Aimed at developers who need video automation and…
-
3.6
deepopen-com/deepopen-3d-webs
A 3D scene generation system that takes a single reference image and a prompt, builds the scene along a camera trajectory, and produces previews, color and depth animations, and Gaussian point clouds viewable in the…
-
3.6
0xS4N4TG/kinetograph
A programmatic video engine in TypeScript with a Rust GPU compositor: renders video from code, supporting Remotion API, CSS, SVG, Canvas 2D, WebGL, and Web Audio.
-
3.5
storytold/filmcraft
An open-source non-linear video editor in Rust that reimplements the Adobe Premiere Pro workflow: editing, color, effects and audio, native on macOS, Windows, Linux and in the browser via WebAssembly.
-
3.5
Comfy-Org/ComfyUI
ComfyUI is a diffusion-model engine for generating images, video, audio and 3D with a visual node-graph interface. It lets you build and reuse pipelines without code, run them locally or via API.
-
3.5
openfilm/openfilm
Open source AI video agent that turns a coding agent (Claude Code, Codex) into a video agent that assembles a film from HTML pages, plus a local Studio editor for edits.
-
3.5
ElectronGirl/ComfyUI-Anima-Ref-Adapter
A ComfyUI adapter for the Anima image model that transfers a character's identity and style from a single reference image while pose, background and composition follow the text prompt.
-
3.4
jub0t/Concat
Cross-platform Rust video editor — a free CapCut replacement with no watermarks, subscriptions or accounts, running entirely locally. Supports multi-track editing, auto-captions, TTS and templates.
-
3.3
Tencent-Hunyuan/Hy-Nomas
An interactive video world generation model that creates video segments from free-form text prompts or camera trajectories using autoregressive generation with a lifelong KV cache. Includes inference, LoRA fine-tuning,…
-
3.3
storytold/artcraft
ArtCraft is a desktop IDE for AI image and video creation: compose in 2D, stage scenes in 3D, and choose models for precise, repeatable results.
-
3.2
yihui-dev/awesome-opus5-5-videos
A collection of 282 viral videos made with Claude Opus 5.5, each with the creator's exact prompt. The prompts generate animations as code using HTML, Canvas, SVG, Three.js and GLSL.
-
3.1
storytold/effectcraft
An open-source motion graphics and compositing tool in pure Rust — a clean-room reimplementation of Adobe After Effects with compositions, layers, keyframes, 259 effects, 3D cameras and a render queue.
-
3.1
storytold/lightcraft
An open-source clean-room reimplementation of Adobe Lightroom in pure Rust: non-destructive raw development, color grading, masking, presets and a photo library. Runs natively on macOS, Windows and Linux, in the…
-
3.0
Moessif/code-video-showcase
An Agent Skill that produces 30-90s beat-synced showcase videos entirely from code: frames rendered with HTML/Canvas/SVG/Three.js, soundtrack synthesized with Python numpy/scipy, assembled by FFmpeg, without any…
-
3.0
MiniMax-AI/MiniMax-H3
MiniMax H3 is an omni-modal generative system that understands text, images, video and audio and generates video with native stereo audio up to 2K and 15 seconds. The repository bundles prompt-writing and…
-
3.0
wide-trace/open-higgsfield
Open-source self-hosted studio for image and video generation across 32 models (8 image, 24 video) in one interface with a single prompt bar, gallery and per-model settings.
-
2.9
basketikun/infinite-canvas
An open-source infinite canvas workbench for AI creation: image and video generation, reference-based editing, a chat assistant, prompt library and asset management in one interface. Works with any OpenAI-compatible…
-
2.9
NomaDamas/CozyClay
Open-source previs tool in the browser: block a scene in 3D, pose characters, author camera moves and cuts, then hand the shot to an AI video model. For people making AI video who want to lock staging, timing and…
-
2.8
img2threejs/img2threejs
A tool that turns a single reference image into a procedural Three.js 3D model as TypeScript code, with an animation-ready hierarchy and quality gates.
-
2.8
Kruk2/jasna
A tool that restores mosaic areas in videos and images: it detects mosaics and restores only those regions, leaving the rest of the picture untouched. Runs on GPU with a GUI app and a CLI.
-
2.8
upscayl/upscayl
Cross-platform open-source desktop app that enlarges and enhances low-resolution images using AI models (Real-ESRGAN, NCNN Vulkan).
-
2.7
dvbs2000/liuchunlin-shufa
Online Chinese calligraphy generator that imitates the Xiaokai style of the last imperial exam champion Liu Chunlin, laying out pasted poems into a formatted album page with seal and brocade trim.
-
2.7
OpenMOSS/MOSS-Image
MOSS-Image is a 5B-parameter DiT text-to-image base model with strong text rendering, JSON layout control, 4K-token prompts and LoRA fine-tuning support.
-
2.7
Vincentwei1021/mg-styles-15
A collection of 15 ten-second motion-design films, each in its own style, fully generated from code by Claude Opus 5.5 from a single prompt. The repository holds the films, prompts, and full source for animation,…
-
2.6
storytold/soundcraft
A clean-room reimplementation of Avid Pro Tools in pure Rust: a full digital audio workstation with multitrack editing, mixing, MIDI, plugins and automation, running on desktop and in the browser.
-
2.4
alchaincyf/huashu-art-motion
An agent skill for making animation with code: 35 art-style recipes (cave painting, Van Gogh, Bauhaus, 8-bit and more) with working Canvas scenes, plus 9 explainer-video grammars. It helps a coding agent turn a style…
-
2.4
shitagaki-lab/see-through
A research project that decomposes a single anime illustration into semantic layers (up to 23: hair, face, eyes, clothing, etc.) with inpainting of occluded regions and inferred drawing order, exporting the result as a…
-
2.4
patch-gg/crowdbricks
Batched NVIDIA MotionBricks: generates the motion of hundreds of characters in one model call via a TensorRT plan with a batch dimension and a light crowd runtime.
-
2.4
glanderness/BeefTV
A local-first desktop video workspace with AI agents: on a free canvas it links models, assets and generation tasks for text, images, video and audio into an editable workflow.
-
2.4
edenfunf/reelmimic
A local tool that analyzes a reference video and generates a new 2D animation in the same style using multiple AI agents (Claude Code or Codex).
-
2.3
academa-labs/manimgx
A 3D animation engine compatible with Manim CE's Python API, built on a Rust/wgpu GPU core for fast rendering of math and 3D videos, aimed at developers and AI agents.
-
2.3
mexicat/pdoom-video
A generative, code-rendered music video built with TypeScript and three.js, where every scene is synced to the song's lyrics and each frame is a deterministic function of track time. It includes a Python audio-analysis…
-
2.2
feitangyuan/onetake
A Claude Agent Skill for making product launch films and feature demos as one continuous take, where each beat grows out of the previous one and continuity is verified by an oracle.
-
2.2
Ebony-Vinyl/EAC-design-world
A local-first video production and design studio plugin for DeepSeek Harness, with multi-track editing, templates and design systems, native preview canvas and real file export. It is aimed at creators who want an AI…
-
2.2
0xShug0/audio.cpp
A native C++ inference engine for audio models built on ggml: TTS, speech recognition, VAD, voice cloning, music generation. Runs without Python on CPU, CUDA, ROCm, Vulkan and Metal.
-
2.2
OpenBMB/VoxCPM
VoxCPM2 is an open-source 2B-parameter tokenizer-free TTS system that synthesizes speech in 30 languages, designs voices from text descriptions, and clones voices from short reference clips with 48kHz output.
-
2.1
k2-fsa/OmniVoice
Massively multilingual zero-shot TTS model supporting 600+ languages with voice cloning and voice attribute control. Built on a diffusion language model-style architecture with fast inference.
-
2.1
appariciojunior/video-editor-skills
A set of Claude Code skills that turn it into a first-pass video editor in DaVinci Resolve Studio: rough cuts, vlog pacing, B-roll, music, captions, motion graphics and YouTube export.
-
2.1
alexturkey/voxcpm2-turkce-ses-tasarimi
A local Turkish text-to-speech tool: it designs voice variants from an English text description and reads Turkish text with them on a 4 GB GPU.
-
2.1
higgsfield-ai/skills
A set of Markdown skills for AI coding agents (Claude Code, Cursor, Codex) that use Higgsfield AI to generate images, video, audio, and 3D, and to build visual brand systems and ad creatives.
-
2.1
inclusionAI/Ming-3.0-tts
Open-source TTS model family with 0.5B dense and 7.9B-A1.3B MoE variants, supporting multilingual speech, voice cloning, voice design and natural-language control.
-
2.0
harry7557558/spirula-studio
A self-contained C++ binary for training 3D Gaussian Splatting models: turns photos and video into splats and textured meshes, running on NVIDIA, AMD, Intel and Apple GPUs via Vulkan or CUDA without Python or COLMAP.
-
2.0
Supra-3D/SUPRA-Tex
Generates textured 3D assets from a single image while preserving lettering, patterns and material boundaries, exporting a relightable GLB with PBR textures (base color, metallic, roughness).
-
1.9
opencv/opencv
OpenCV is an open source computer vision library written in C++ for image and video processing and machine learning tasks.
-
1.9
Emily2040/seedance-2.0
An agent skill for planning shot tables, binding references and continuing from an accepted clip; generation is handled by your video provider. For creators of short drama clips on Seedance 2.0.
-
1.9
JohnHeibel/PDoomVideo
Source code for a music video generated entirely by Claude Opus, with scenes, lyrics and transitions built in p5.js and rendered to MP4 via headless Chrome and ffmpeg.
-
1.9
yi1108/printfilm
Open-source AI studio for short videos and episodic comics: from theme and script through storyboard, image, video and voice generation to the final cut. Includes a user frontend, admin panel, billing and an open API.
-
1.9
Arekejoker/qwen21-nsfw-pose-skill
A set of recipes and scripts for local NSFW image generation and pose control with Qwen-Image 2.1 via ComfyUI, including an NSFW LoRA and a library of 136 3D poses.
-
1.6
852wa/JIZURA
A browser app that automatically assembles lyric videos (文字PV) from song lyrics using 707 built-in parts and 24 styles, exporting to MP4. An After Effects panel is also included.
-
1.5
TencentARC/Looking-Ahead
Code and weights for autoregressive video generation: the Future Chunk Prediction (FCP) method trains models to predict future video chunks, improving physical consistency. Includes training and inference for 1.3B and…
-
1.4
JayWebtech/autoshorts
A local-first Tauri desktop app that turns long videos and audio into 9:16 vertical short clips, ranking viral moments with LLMs. Supports Deepgram, DeepSeek, Claude, and an offline mode with Ollama and Whisper.
-
1.4
blendi-remade/prompt2rig
Turns a text prompt into a rigged 3D character animation: a video model generates the motion clip, then GVHMR and WiLoR recover body and finger motion on your GPU and retarget it live onto a Mixamo rig in the browser.
-
1.3
antirez/h3.c
Native MiniMax-H3 inference engine for Apple Silicon on Metal: generates video and audio from text prompts, supports first/last-frame conditioning and Ref2VA references.
-
1.2
wj-sidiss/otopilot
A local tool that turns a topic and title into a finished video: it writes the script, finds images, voices it, and assembles MP4 with subtitles and a cover. Runs on localhost via a Node.js panel.
-
1.2
soumatheusgomes/editonny
A local video editing skill for Codex and Claude Code that turns conversational prompts into cuts, captions, framing, audio cleanup, and 145 visual scenes. Aimed at creators who want agent-guided editing without…
-
1.2
Enderfga/SolarRenderer
A generative renderer that turns a structure video (grey box, semantic maps, skeletons, depth, mesh, sketches) into a finished clip in four steps on MiniMax-H3 with two LoRAs. The look is set by the first frame and a…
-
1.2
LiamGvchi/gc-minimal-zine-poster
A Codex skill that turns a theme, sentence, or photograph into a sparse zine-style paper-texture poster and a production-ready image prompt. It works as a set of rules and recipes inside Codex with no scripts or…
-
1.2
kanaworksai-hue/audio-studio-mcp
A local MCP server that gives Claude Code and other MCP clients background music and sound effect generation via Stable Audio 3, with no cloud and no API key. Runs on Apple Silicon (MLX) and NVIDIA GPUs (PyTorch).
-
1.2
Zeejay0/gathered-scenes-zine-skill
A set of Codex skills that turn ordinary photos into zine pages: either a collage preserving the real photo or a distillation of the scene into a standalone illustration.
-
1.2
black-forest-labs/flux-3-image-klein
Reference inference code for FLUX 3 Image Klein, a 5.6B open-weights image model supporting text-to-image, editing with up to 10 reference images, and layout control via bounding boxes. It requires the bundled prompt…
-
1.2
ZzzLc0405/photo-abstract-editorial
A Codex Skill and prompt set that turns a single photo into a vertical editorial piece: the original shot on top, an abstract memory panel below, and a poetic English title. It is not a filter or style transfer — the…
-
1.1
GabrieleLozupone/kokon
A local app for editing and generating images from text descriptions on your own GPU, with no Python or cloud. Powered by Qwen-Image 2.1, it includes an MCP server for AI agents.
-
1.1
petergyang/video-short
An AI-agent skill (Claude Code, ChatGPT, Gemini) that turns a raw recording into a polished video short with B-roll, motion graphics, captions and music, plus a review page for frame-level feedback.
-
1.1
rossark0/rossark-motion-skill
A Claude Code skill that turns SVG drawings into lifelike 60 fps animations for React Native and SwiftUI: faces, characters, scenes. Ships an engine, templates and animation rules so motion feels alive instead of a…
-
1.0
Leonxlnx/napali
A procedural drone flight over the Na Pali coast, generated entirely in WebGL2 shaders with no textures, models or external assets. A single self-contained index.html plus tools to render stills and video via headless…
-
1.0
abus-aikorea/voice-pro
Gradio web app for speech recognition, translation and dubbing: combines YouTube download, vocal separation (Demucs), Whisper, TTS (Edge-TTS, kokoro) and zero-shot voice cloning (F5-TTS, E2-TTS, CosyVoice).
-
0.9
derek-zhuolin/motion-skill
A Skill for Codex/Agent plus an editable Remotion project that turns a script or voice recording into motion-graphics video without appearing on camera. Supports script and voice modes, synced captions and 96 motion…
-
0.8
Chenkin-x/ComfyUI-Moss-Image-Edit
A custom ComfyUI node for editing images from a text instruction with one or more reference images using the MOSS Image Edit model.
-
0.8
kailashsr38/ascii-magic-art
A library of 634 animated ASCII art pieces for web pages, READMEs, wallpapers, and terminals. Allows browsing, embedding, and creating ASCII animations.
-
0.7
Mayzmei/anime-series-maker
An agent skill for Claude Code and Codex that turns two character sheets and one line of story into a finished anime episode: script, voiced clips, edit, cover and caption.
-
0.6
OpenImagingLab/FlashVSR_Plus
Official implementation of FlashVSR+, a one-step diffusion framework for video super-resolution that enables spatially untiled 4K inference on a single 24GB RTX 4090. It ships inference code, pretrained models, and the…
-
0.3
swax/dub-anything
A local tool that dubs films and shows into another language in each actor's own voice, keeping the original music and sound effects, with an AI agent directing the process.
-
0.2
Netflix/vmaf
VMAF is Netflix's Emmy-winning perceptual video quality assessment algorithm, shipped as a C library plus Python tooling. It scores how close an encoded video looks to its source and supports model training.
-
0.1
HeyChengC/wallstreet-explainer
A Claude Code skill that renders Wall-Street-style finance and tech explainer videos frame by frame in code: sourcing and cutting real footage, matting people, drawing numbers, voicing and mixing audio.
-
0.0
DenRakEiw/scumble
Free desktop image editor with AI inpainting: select an area, write a prompt, and get the result as its own colour-matched layer. Runs on your own ComfyUI, Comfy Cloud, or API keys (FLUX, GPT Image, Nano Banana,…
-
0.0
ashukae/ComfyUI-MangaScreen
A ComfyUI filter that turns illustrations into black-and-white manga pages: crisp lines, flat tones, real screentone and framed panels.
-
0.0
nmbrthirteen/podcli
Local AI podcast clipper: transcribes an episode, picks the moments, crops to the speaker, and burns in captions. Driven from the CLI, a web studio, or an MCP agent.
-
0.0
ConquerorPhase/TAL-U-NO-Synth-Full-2026
Install guide for TAL U NO Synth Full 2026 on Windows — a synthesizer and recording, editing, and mixing tools for desktop music production.