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.
-
7.3
multimodal-art-projection/YuE
YuE2 is a music generation model: from lyrics and a style prompt it builds an editable melody-and-chord plan, then renders a full song with vocals and accompaniment. It supports zero-shot covers and agentic composition…
-
5.9
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…
-
5.9
eternityspring/reelbench-skills
A set of Claude Code and Codex skills for video work: video-shots breaks a finished clip into a shot-by-shot analysis table (duration, shot size, camera moves), video-sync renders video with a side panel of shot info…
-
4.6
Colafornia/short-video-generator-AI
Open-source tool that turns long YouTube videos into vertical short clips: it detects highlights and adds subtitles, translation and voiceover. A free alternative to paid SaaS like OpusClip for content creators.
-
4.5
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.
-
4.5
govin-ai/dunhuang-aura-skill
An AI Skill for generating and editing commercial visuals in the Dunhuang mineral aesthetic, usable in Codex, Claude Code and other SKILL.md-compatible agent environments.
-
4.4
calesthio/OpenMontage
Open-source agentic video production system: an AI coding assistant researches, scripts, generates assets, edits and renders a finished video from a plain-language prompt. 12 pipelines, 100+ tools and 700+ agent skill…
-
4.4
Vincentwei1021/anything2explainer
A Claude Code / Codex skill that turns a topic or document into a black-canvas explainer video with TTS voiceover, subtitles and a chapter progress bar. Every frame is drawn in code with Remotion (React + TypeScript),…
-
3.9
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.
-
3.8
jeremyipark/vision-demos
A collection of Python computer vision demos: comparing dancers' sync, counting chin-ups, and analyzing running from video using the vitpose-plus-large model.
-
2.9
EverettFish/holo-card-studio
A Codex Skill that turns a text description or reference image into an editable Blender 3D card and an interactive Three.js page with parallax and holographic shimmer.
-
2.9
freestylefly/awesome-gpt-image-2
A prompt and template library for GPT-Image 2/2.5 image generation: 500+ reverse-engineered cases, 20+ industrial templates and an agent Skill, structured as Prompt-as-Code.
-
2.8
yang0/handraw-style
A library of 261 numbered hand-drawn art styles with bilingual prompts: pick a number and a theme to get ready Chinese and English prompts for image generation. Keeps a consistent visual style without needing to…
-
2.4
masihsultani/whiteboard-animator
A Python CLI that turns a finished whiteboard-style image into a hand-drawn reveal video: text is written word by word, outlines traced, fills painted with brush strokes. Runs on CPU with no GPU or API keys.
-
2.4
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.
-
2.3
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…
-
2.3
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.
-
2.3
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.
-
2.2
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…
-
2.0
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.
-
1.9
s1dashu/ip-as-logo-skill
An Agent Skill in the open Agent Skills format for generating extremely simple, rounded IP mascot logos with a dominant lower-corner composition and a solid named background. Works with any compatible AI agent that has…
-
1.8
helloianneo/ian-xiaohei-illustrations
A Codex Skill that turns key arguments, processes and metaphors from Chinese articles into 16:9 hand-drawn white-background illustrations featuring the "Xiaohei" character with short red/orange/blue annotations.
-
1.8
dsp56300/gearmulator
Low-level emulator of ICs (DSP56300 etc.) that runs original firmware of classic VA synths and effects from the late 90s/2000s as audio plugins in VST3, AU, CLAP, LV2 and FST formats.
-
1.7
ooolabdev/ooosplat
A local desktop app that turns videos or image sequences into 3D Gaussian Splats in one click, handling frame preparation, COLMAP camera reconstruction and Brush training automatically.
-
1.7
facok/comfyui-SelfLift
A ComfyUI extension for progressive-resolution sampling: early denoising steps run at low resolution, then the result is lifted to full resolution. Implements the paper's SelfLift-zero for rectified-flow image models…
-
1.5
HRuiCcc/RuiC-card-skill
A Codex Skill that turns a single prompt or reference image into a 3D holographic trading card: four layered images, a parallax Blender scene, and a single-file Three.js web viewer.
-
1.5
peggykangkang02/xialingguo-ip
A cover-design Skill and template system for generating article covers (21:9 and other ratios) with a real-person IP character, nine visual styles, and automatic layout based on title and visual focus.
-
1.5
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…
-
1.5
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.
-
1.4
opentoonz/opentoonz
OpenToonz is an open-source 2D animation creation software based on the Toonz Studio Ghibli Version. It is aimed at animators and studios for frame-by-frame and vector animation.
-
1.4
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.
-
1.3
diffusionstudio/lottie
A framework for generating production-ready Lottie animations with coding agents (Claude Code, Codex) via the text-to-lottie skill. The agent creates scenes in a project and a built-in player previews them live.
-
1.3
circle-group/hktex
HKTex is an intrinsic texture representation for triangular meshes that avoids UV atlases: appearance is defined by anisotropic heat kernels directly on the surface. It fits textures from an existing textured mesh or…
-
1.2
yanliudesign/mono-color-skill
An AI-agent skill that generates editorial images in one- or two-ink print style: posters, zines, packaging, portraits. It preserves a visual system rather than copying a reference.
-
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…
-
0.7
GangTailorUpgrade/undress-service
Self-hosted AI wardrobe service: uploads clothing photos, auto-tags items via CLIP, and generates outfits with Stable Diffusion/FLUX. Aimed at users who want private wardrobe management and AI styling recommendations.
-
0.5
cclank/lanshu-create-ai-presenter-video
Codex Skill for producing AI presenter videos: from a topic or script and an authorized person image it assembles voiceover, character generation, lip sync, subtitles and editing with QA.
-
0.4
LerSent001/holo-card
A Codex skill and local API that turn supplied artwork into an interactive holographic card with foreground parallax, a moving background, and adjustable contour glow.