# Generative media: what’s taking off on GitHub

Magnitude (0–10) measures how fast and how unusually interest in a repository is growing right now. It is not a quality score. Days are UTC. “So far today” is a fact; “expected by the end of the day” is a forecast.

Data as of 2026-10-30 17:16 UTC, updated every 30 minutes.

1. **paipiange/nvzhuang** — 8.0 · Early signal · Generative media · Go · +889 stars measured 2026-10-30, 00:16–17:01 UTC, ≈ 1,171 by evening
   A static catalog of 1407 AI-generated women's clothing images with bilingual search and optional virtual try-on via external image generation models.
   Full card: https://gitnova.dev/en/r/paipiange/nvzhuang.md
2. **anhao/ai-pose-gallery-zh** — 6.9 · Peaking · Generative media · HTML · +762 stars measured 2026-10-30, 00:15–17:00 UTC, ≈ 1,070 by evening
   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.
   Full card: https://gitnova.dev/en/r/anhao/ai-pose-gallery-zh.md
3. **sleepy-zone/ai-ref-library-cn** — 6.6 · Early signal · Generative media · JavaScript · +223 stars measured 2026-10-30, 03:05–17:01 UTC, ≈ 306 by evening
   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.
   Full card: https://gitnova.dev/en/r/sleepy-zone/ai-ref-library-cn.md
4. **D3voz/openjutsu** — 6.2 · Early signal · Generative media · TypeScript · +168 stars measured 2026-10-30, 00:16–17:01 UTC, ≈ 234 by evening
   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 your own GPU via…
   Full card: https://gitnova.dev/en/r/D3voz/openjutsu.md
5. **Pika-Labs/Pika-H3-Flex** — 5.8 · Early signal · Generative media · Python · +47 stars measured 2026-10-30, 09:22–17:01 UTC, ≈ 70 by evening
   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.
   Full card: https://gitnova.dev/en/r/Pika-Labs/Pika-H3-Flex.md
6. **OpenSenseNova/SenseNova-6.8-Code2Video** — 5.5 · Early signal · Generative media · Python · +86 stars measured 2026-10-30, 00:17–17:01 UTC, ≈ 118 by evening
   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.
   Full card: https://gitnova.dev/en/r/OpenSenseNova/SenseNova-6.8-Code2Video.md
7. **speridlabs/idol-sdk** — 5.2 · Early signal · Generative media · Python · +53 stars measured 2026-10-30, 13:01–17:01 UTC, ≈ 74 by evening
   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.
   Full card: https://gitnova.dev/en/r/speridlabs/idol-sdk.md
8. **wquguru/shisei** — 5.1 · Early signal · Generative media · Python · +26 stars measured 2026-10-30, 11:34–17:01 UTC, ≈ 41 by evening
   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 ja/zh/en/ko.
   Full card: https://gitnova.dev/en/r/wquguru/shisei.md
9. **debpalash/VoiceStudio** — 5.0 · Steady · Generative media · Python · +1,059 stars measured 2026-10-30, 00:16–17:01 UTC, ≈ 1,461 by evening
   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 ASR engines, a…
   Full card: https://gitnova.dev/en/r/debpalash/VoiceStudio.md
10. **Ka1-S/LYNX-SHARE** — 5.0 · Early signal · Generative media · C++ · +25 stars measured 2026-10-30, 00:17–17:01 UTC, ≈ 38 by evening
   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 common production…
   Full card: https://gitnova.dev/en/r/Ka1-S/LYNX-SHARE.md
11. **pyqdcyy123-byte/IP-Bot** — 5.0 · Early signal · Generative media · TypeScript · +37 stars measured 2026-10-30, 09:23–17:01 UTC, ≈ 58 by evening
   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.
   Full card: https://gitnova.dev/en/r/pyqdcyy123-byte/IP-Bot.md
12. **MUSE-AI-Lab/Concept-Brittleness** — 4.9 · Early signal · Generative media · Python · +72 stars measured 2026-10-30, 07:15–17:01 UTC, ≈ 104 by evening
   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 failures at inference…
   Full card: https://gitnova.dev/en/r/MUSE-AI-Lab/Concept-Brittleness.md
13. **wzc520pyfm/gen-ai-pose-image** — 4.9 · Early signal · Generative media · JavaScript · +47 stars measured 2026-10-30, 13:48–17:01 UTC, ≈ 64 by evening
   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.
   Full card: https://gitnova.dev/en/r/wzc520pyfm/gen-ai-pose-image.md
14. **Vibha-Ramprakash/claude-video-effects** — 4.8 · Early signal · Generative media · Python · +71 stars measured 2026-10-30, 00:16–17:01 UTC, ≈ 96 by evening
   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.
   Full card: https://gitnova.dev/en/r/Vibha-Ramprakash/claude-video-effects.md
15. **toyxyz/toyxyz_RGBMocap** — 4.6 · Early signal · Generative media · Python · +54 stars measured 2026-10-30, 00:16–17:01 UTC, ≈ 76 by evening
   Native Windows app for video motion capture: reconstructs 3D human animation with ExMR, FlowHMR and GVHMR models, corrects contacts and exports FBX/VMD.
   Full card: https://gitnova.dev/en/r/toyxyz/toyxyz_RGBMocap.md
16. **andyhuo520/vibe-knowledge** — 4.6 · Early signal · Generative media · JavaScript · +32 stars measured 2026-10-30, 00:16–17:01 UTC, ≈ 46 by evening
   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.
   Full card: https://gitnova.dev/en/r/andyhuo520/vibe-knowledge.md
17. **heygen-com/hyperframes** — 4.4 · Steady · Generative media · TypeScript · +445 stars measured 2026-10-30, 00:16–17:01 UTC, ≈ 624 by evening
   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.
   Full card: https://gitnova.dev/en/r/heygen-com/hyperframes.md
18. **actionow-ai/vvv** — 4.3 · Early signal · Generative media · Python · +56 stars measured 2026-10-30, 00:21–17:02 UTC, ≈ 74 by evening
   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.
   Full card: https://gitnova.dev/en/r/actionow-ai/vvv.md
19. **wangweihong/comfyui-pose-gallery** — 4.0 · Early signal · Generative media · HTML · +5 stars measured 2026-10-30, 14:36–17:02 UTC, ≈ 11 by evening
   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.
   Full card: https://gitnova.dev/en/r/wangweihong/comfyui-pose-gallery.md
20. **lemomo-ai/lemo-opuscar** — 3.9 · Steady · Generative media · JavaScript · +305 stars measured 2026-10-30, 00:17–17:02 UTC, ≈ 417 by evening
   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.
   Full card: https://gitnova.dev/en/r/lemomo-ai/lemo-opuscar.md
21. **remotion-dev/remotion** — 3.8 · Steady · Generative media · TypeScript · +200 stars measured 2026-10-30, 00:17–17:02 UTC, ≈ 277 by evening
   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 generation.
   Full card: https://gitnova.dev/en/r/remotion-dev/remotion.md
22. **deepopen-com/deepopen-3d-webs** — 3.6 · Early signal · Generative media · Python · +222 stars measured 2026-10-30, 00:18–17:03 UTC, ≈ 290 by evening · unusual star pattern (heuristic)
   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 browser. Runs in demo…
   Full card: https://gitnova.dev/en/r/deepopen-com/deepopen-3d-webs.md
23. **0xS4N4TG/kinetograph** — 3.5 · Early signal · Generative media · TypeScript · +17 stars measured 2026-10-30, 00:16–17:03 UTC, ≈ 24 by evening
   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.
   Full card: https://gitnova.dev/en/r/0xS4N4TG/kinetograph.md
24. **storytold/filmcraft** — 3.5 · Steady · Generative media · Rust · +72 stars measured 2026-10-30, 00:17–17:03 UTC, ≈ 102 by evening
   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.
   Full card: https://gitnova.dev/en/r/storytold/filmcraft.md
25. **Comfy-Org/ComfyUI** — 3.5 · Cooling · Generative media · Python · +170 stars measured 2026-10-30, 00:17–17:03 UTC, ≈ 235 by evening
   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.
   Full card: https://gitnova.dev/en/r/Comfy-Org/ComfyUI.md
26. **openfilm/openfilm** — 3.5 · Steady · Generative media · TypeScript · +142 stars measured 2026-10-30, 00:17–17:03 UTC, ≈ 199 by evening
   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.
   Full card: https://gitnova.dev/en/r/openfilm/openfilm.md
27. **ElectronGirl/ComfyUI-Anima-Ref-Adapter** — 3.4 · Early signal · Generative media · Python · +16 stars measured 2026-10-30, 00:16–17:03 UTC, ≈ 23 by evening
   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.
   Full card: https://gitnova.dev/en/r/ElectronGirl/ComfyUI-Anima-Ref-Adapter.md
28. **jub0t/Concat** — 3.4 · Steady · Generative media · Rust · +150 stars measured 2026-10-30, 00:17–17:03 UTC, ≈ 209 by evening
   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.
   Full card: https://gitnova.dev/en/r/jub0t/Concat.md
29. **Tencent-Hunyuan/Hy-Nomas** — 3.3 · Early signal · Generative media · Python · +25 stars measured 2026-10-30, 00:17–17:03 UTC, ≈ 34 by evening
   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, data annotation,…
   Full card: https://gitnova.dev/en/r/Tencent-Hunyuan/Hy-Nomas.md
30. **storytold/artcraft** — 3.3 · Cooling · Generative media · Rust · +117 stars measured 2026-10-30, 00:17–17:04 UTC, ≈ 168 by evening
   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.
   Full card: https://gitnova.dev/en/r/storytold/artcraft.md
31. **yihui-dev/awesome-opus5-5-videos** — 3.2 · Cooling · Generative media · +156 stars measured 2026-10-30, 00:17–17:04 UTC, ≈ 216 by evening
   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.
   Full card: https://gitnova.dev/en/r/yihui-dev/awesome-opus5-5-videos.md
32. **storytold/effectcraft** — 3.1 · Steady · Generative media · Rust · +33 stars measured 2026-10-30, 00:18–17:04 UTC, ≈ 47 by evening
   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.
   Full card: https://gitnova.dev/en/r/storytold/effectcraft.md
33. **storytold/lightcraft** — 3.1 · Cooling · Generative media · Rust · +37 stars measured 2026-10-30, 00:17–17:04 UTC, ≈ 53 by evening
   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 browser via WebAssembly,…
   Full card: https://gitnova.dev/en/r/storytold/lightcraft.md
34. **MiniMax-AI/MiniMax-H3** — 3.0 · Steady · Generative media · Python · +70 stars measured 2026-10-30, 00:18–17:04 UTC, ≈ 96 by evening
   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 style-specific video generation…
   Full card: https://gitnova.dev/en/r/MiniMax-AI/MiniMax-H3.md
35. **Moessif/code-video-showcase** — 3.0 · Early signal · Generative media · JavaScript · +19 stars measured 2026-10-30, 00:18–17:04 UTC, ≈ 27 by evening
   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 generative models.
   Full card: https://gitnova.dev/en/r/Moessif/code-video-showcase.md
36. **wide-trace/open-higgsfield** — 3.0 · Steady · Generative media · TypeScript · +42 stars measured 2026-10-30, 00:17–17:04 UTC, ≈ 59 by evening
   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.
   Full card: https://gitnova.dev/en/r/wide-trace/open-higgsfield.md
37. **NomaDamas/CozyClay** — 2.9 · Peaking · Generative media · JavaScript · +54 stars measured 2026-10-30, 00:19–17:05 UTC, ≈ 73 by evening
   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 camera cheaply first.
   Full card: https://gitnova.dev/en/r/NomaDamas/CozyClay.md
38. **basketikun/infinite-canvas** — 2.9 · Cooling · Generative media · TypeScript · +48 stars measured 2026-10-30, 00:18–17:05 UTC, ≈ 66 by evening
   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 API, with keys stored…
   Full card: https://gitnova.dev/en/r/basketikun/infinite-canvas.md
39. **img2threejs/img2threejs** — 2.8 · Steady · Generative media · Python · +61 stars measured 2026-10-30, 00:18–17:05 UTC, ≈ 85 by evening
   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.
   Full card: https://gitnova.dev/en/r/img2threejs/img2threejs.md
40. **Kruk2/jasna** — 2.8 · Steady · Generative media · Python · +55 stars measured 2026-10-30, 00:18–17:05 UTC, ≈ 78 by evening
   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.
   Full card: https://gitnova.dev/en/r/Kruk2/jasna.md
41. **upscayl/upscayl** — 2.8 · Steady · Generative media · TypeScript · +43 stars measured 2026-10-30, 00:18–17:05 UTC, ≈ 61 by evening
   Cross-platform open-source desktop app that enlarges and enhances low-resolution images using AI models (Real-ESRGAN, NCNN Vulkan).
   Full card: https://gitnova.dev/en/r/upscayl/upscayl.md
42. **dvbs2000/liuchunlin-shufa** — 2.7 · Early signal · Generative media · +27 stars measured 2026-10-30, 00:23–17:06 UTC, ≈ 37 by evening
   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.
   Full card: https://gitnova.dev/en/r/dvbs2000/liuchunlin-shufa.md
43. **Vincentwei1021/mg-styles-15** — 2.7 · Steady · Generative media · Python · +68 stars measured 2026-10-30, 00:18–17:05 UTC, ≈ 92 by evening
   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, audio, and rendering.
   Full card: https://gitnova.dev/en/r/Vincentwei1021/mg-styles-15.md
44. **OpenMOSS/MOSS-Image** — 2.7 · Steady · Generative media · Python · +68 stars measured 2026-10-30, 00:19–17:05 UTC, ≈ 93 by evening
   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.
   Full card: https://gitnova.dev/en/r/OpenMOSS/MOSS-Image.md
45. **storytold/soundcraft** — 2.6 · Cooling · Generative media · Rust · +25 stars measured 2026-10-30, 00:19–17:06 UTC, ≈ 34 by evening
   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.
   Full card: https://gitnova.dev/en/r/storytold/soundcraft.md
46. **alchaincyf/huashu-art-motion** — 2.4 · Steady · Generative media · JavaScript · +54 stars measured 2026-10-30, 00:18–17:15 UTC, ≈ 76 by evening
   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 into a moving scene…
   Full card: https://gitnova.dev/en/r/alchaincyf/huashu-art-motion.md
47. **shitagaki-lab/see-through** — 2.4 · Steady · Generative media · Python · +23 stars measured 2026-10-30, 00:18–17:06 UTC, ≈ 32 by evening
   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 PSD.
   Full card: https://gitnova.dev/en/r/shitagaki-lab/see-through.md
48. **glanderness/BeefTV** — 2.4 · Steady · Generative media · TypeScript · +28 stars measured 2026-10-30, 00:21–17:07 UTC, ≈ 38 by evening
   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.
   Full card: https://gitnova.dev/en/r/glanderness/BeefTV.md
49. **patch-gg/crowdbricks** — 2.4 · Cooling · Generative media · Python · +9 stars measured 2026-10-30, 00:17–17:07 UTC, ≈ 12 by evening
   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.
   Full card: https://gitnova.dev/en/r/patch-gg/crowdbricks.md
50. **academa-labs/manimgx** — 2.3 · Steady · Generative media · Python · +34 stars measured 2026-10-30, 00:19–17:07 UTC, ≈ 47 by evening
   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.
   Full card: https://gitnova.dev/en/r/academa-labs/manimgx.md
51. **edenfunf/reelmimic** — 2.3 · Steady · Generative media · JavaScript · +19 stars measured 2026-10-30, 00:21–17:07 UTC, ≈ 26 by evening
   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).
   Full card: https://gitnova.dev/en/r/edenfunf/reelmimic.md
52. **mexicat/pdoom-video** — 2.3 · Steady · Generative media · TypeScript · +30 stars measured 2026-10-30, 00:20–17:08 UTC, ≈ 41 by evening
   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 pipeline (Demucs,…
   Full card: https://gitnova.dev/en/r/mexicat/pdoom-video.md
53. **feitangyuan/onetake** — 2.2 · Steady · Generative media · Python · +43 stars measured 2026-10-30, 00:20–17:08 UTC, ≈ 58 by evening
   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.
   Full card: https://gitnova.dev/en/r/feitangyuan/onetake.md
54. **0xShug0/audio.cpp** — 2.2 · Steady · Generative media · C++ · +24 stars measured 2026-10-30, 00:20–17:08 UTC, ≈ 32 by evening
   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.
   Full card: https://gitnova.dev/en/r/0xShug0/audio.cpp.md
55. **Ebony-Vinyl/EAC-design-world** — 2.2 · Steady · Generative media · JavaScript · +19 stars measured 2026-10-30, 00:20–17:08 UTC, ≈ 26 by evening
   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 to help assemble…
   Full card: https://gitnova.dev/en/r/Ebony-Vinyl/EAC-design-world.md
56. **OpenBMB/VoxCPM** — 2.2 · Cooling · Generative media · Python · +31 stars measured 2026-10-30, 00:20–17:08 UTC, ≈ 43 by evening
   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.
   Full card: https://gitnova.dev/en/r/OpenBMB/VoxCPM.md
57. **alexturkey/voxcpm2-turkce-ses-tasarimi** — 2.2 · Steady · Generative media · Python · +23 stars measured 2026-10-30, 00:21–17:08 UTC, ≈ 30 by evening
   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.
   Full card: https://gitnova.dev/en/r/alexturkey/voxcpm2-turkce-ses-tasarimi.md
58. **appariciojunior/video-editor-skills** — 2.1 · Cooling · Generative media · +12 stars measured 2026-10-30, 00:18–17:08 UTC, ≈ 16 by evening
   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.
   Full card: https://gitnova.dev/en/r/appariciojunior/video-editor-skills.md
59. **k2-fsa/OmniVoice** — 2.1 · Cooling · Generative media · Python · +32 stars measured 2026-10-30, 00:20–17:08 UTC, ≈ 44 by evening
   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.
   Full card: https://gitnova.dev/en/r/k2-fsa/OmniVoice.md
60. **higgsfield-ai/skills** — 2.1 · Steady · Generative media · Python · +3 stars measured 2026-10-30, 00:18–17:08 UTC, ≈ 7 by evening
   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.
   Full card: https://gitnova.dev/en/r/higgsfield-ai/skills.md
61. **inclusionAI/Ming-3.0-tts** — 2.1 · Steady · Generative media · Python · +17 stars measured 2026-10-30, 00:19–17:15 UTC, ≈ 24 by evening
   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.
   Full card: https://gitnova.dev/en/r/inclusionAI/Ming-3.0-tts.md
62. **harry7557558/spirula-studio** — 2.0 · Steady · Generative media · C++ · +16 stars measured 2026-10-30, 00:20–17:09 UTC, ≈ 22 by evening
   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.
   Full card: https://gitnova.dev/en/r/harry7557558/spirula-studio.md
63. **Supra-3D/SUPRA-Tex** — 1.9 · Steady · Generative media · Python · +17 stars measured 2026-10-30, 00:20–17:09 UTC, ≈ 24 by evening
   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).
   Full card: https://gitnova.dev/en/r/Supra-3D/SUPRA-Tex.md
64. **opencv/opencv** — 1.9 · Steady · Generative media · C++ · +16 stars measured 2026-10-30, 00:21–17:09 UTC, ≈ 22 by evening
   OpenCV is an open source computer vision library written in C++ for image and video processing and machine learning tasks.
   Full card: https://gitnova.dev/en/r/opencv/opencv.md
65. **Emily2040/seedance-2.0** — 1.9 · Steady · Generative media · Python · +21 stars measured 2026-10-30, 00:23–17:09 UTC, ≈ 28 by evening
   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.
   Full card: https://gitnova.dev/en/r/Emily2040/seedance-2.0.md
66. **JohnHeibel/PDoomVideo** — 1.9 · Steady · Generative media · JavaScript · +23 stars measured 2026-10-30, 00:21–17:10 UTC, ≈ 32 by evening
   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.
   Full card: https://gitnova.dev/en/r/JohnHeibel/PDoomVideo.md
67. **yi1108/printfilm** — 1.8 · Cooling · Generative media · Python · +5 stars measured 2026-10-30, 00:18–17:10 UTC, ≈ 11 by evening
   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.
   Full card: https://gitnova.dev/en/r/yi1108/printfilm.md
68. **Arekejoker/qwen21-nsfw-pose-skill** — 1.8 · Cooling · Generative media · Python · +21 stars measured 2026-10-30, 00:21–17:10 UTC, ≈ 29 by evening
   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.
   Full card: https://gitnova.dev/en/r/Arekejoker/qwen21-nsfw-pose-skill.md
69. **852wa/JIZURA** — 1.6 · Steady · Generative media · HTML · +12 stars measured 2026-10-30, 00:23–17:11 UTC, ≈ 16 by evening
   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.
   Full card: https://gitnova.dev/en/r/852wa/JIZURA.md
70. **TencentARC/Looking-Ahead** — 1.5 · Steady · Generative media · Python · +8 stars measured 2026-10-30, 00:22–17:11 UTC, ≈ 11 by evening
   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 5B TI2V models.
   Full card: https://gitnova.dev/en/r/TencentARC/Looking-Ahead.md
71. **JayWebtech/autoshorts** — 1.5 · Steady · Generative media · Rust · +10 stars measured 2026-10-30, 00:20–17:11 UTC, ≈ 13 by evening
   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.
   Full card: https://gitnova.dev/en/r/JayWebtech/autoshorts.md
72. **blendi-remade/prompt2rig** — 1.4 · Cooling · Generative media · JavaScript · +8 stars measured 2026-10-30, 00:23–17:12 UTC, ≈ 11 by evening
   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.
   Full card: https://gitnova.dev/en/r/blendi-remade/prompt2rig.md
73. **soumatheusgomes/editonny** — 1.3 · Cooling · Generative media · Python · +12 stars measured 2026-10-30, 00:24–17:12 UTC, ≈ 16 by evening
   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 uploading footage.
   Full card: https://gitnova.dev/en/r/soumatheusgomes/editonny.md
74. **antirez/h3.c** — 1.2 · Steady · Generative media · C · +5 stars measured 2026-10-30, 00:24–17:12 UTC, ≈ 7 by evening
   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.
   Full card: https://gitnova.dev/en/r/antirez/h3.c.md
75. **wj-sidiss/otopilot** — 1.2 · Steady · Generative media · JavaScript · +7 stars measured 2026-10-30, 00:24–17:12 UTC, ≈ 9 by evening
   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.
   Full card: https://gitnova.dev/en/r/wj-sidiss/otopilot.md
76. **Enderfga/SolarRenderer** — 1.2 · Steady · Generative media · Python · +7 stars measured 2026-10-30, 00:24–17:13 UTC, ≈ 10 by evening
   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 prompt.
   Full card: https://gitnova.dev/en/r/Enderfga/SolarRenderer.md
77. **kanaworksai-hue/audio-studio-mcp** — 1.2 · Cooling · Generative media · Python · +5 stars measured 2026-10-30, 00:23–17:15 UTC, ≈ 7 by evening
   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).
   Full card: https://gitnova.dev/en/r/kanaworksai-hue/audio-studio-mcp.md
78. **GabrieleLozupone/kokon** — 1.2 · Steady · Generative media · Rust · +5 stars measured 2026-10-30, 00:24–17:13 UTC, ≈ 7 by evening
   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.
   Full card: https://gitnova.dev/en/r/GabrieleLozupone/kokon.md
79. **LiamGvchi/gc-minimal-zine-poster** — 1.2 · Steady · Generative media · +7 stars measured 2026-10-30, 00:24–17:12 UTC, ≈ 10 by evening
   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 external dependencies.
   Full card: https://gitnova.dev/en/r/LiamGvchi/gc-minimal-zine-poster.md
80. **Zeejay0/gathered-scenes-zine-skill** — 1.2 · Steady · Generative media · Python · +6 stars measured 2026-10-30, 00:23–17:15 UTC, ≈ 8 by evening
   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.
   Full card: https://gitnova.dev/en/r/Zeejay0/gathered-scenes-zine-skill.md
81. **black-forest-labs/flux-3-image-klein** — 1.2 · Steady · Generative media · Python · +5 stars measured 2026-10-30, 00:24–17:15 UTC, ≈ 7 by evening
   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 upsampler.
   Full card: https://gitnova.dev/en/r/black-forest-labs/flux-3-image-klein.md
82. **ZzzLc0405/photo-abstract-editorial** — 1.2 · Steady · Generative media · +7 stars measured 2026-10-30, 00:24–17:13 UTC, ≈ 10 by evening
   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 abstraction is…
   Full card: https://gitnova.dev/en/r/ZzzLc0405/photo-abstract-editorial.md
83. **petergyang/video-short** — 1.1 · Cooling · Generative media · Python · +3 stars measured 2026-10-30, 00:23–17:13 UTC, ≈ 4 by evening
   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.
   Full card: https://gitnova.dev/en/r/petergyang/video-short.md
84. **rossark0/rossark-motion-skill** — 1.1 · Cooling · Generative media · Swift · +6 stars measured 2026-10-30, 00:19–17:13 UTC, ≈ 8 by evening
   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 slideshow.
   Full card: https://gitnova.dev/en/r/rossark0/rossark-motion-skill.md
85. **Leonxlnx/napali** — 1.0 · Cooling · Generative media · HTML · +3 stars measured 2026-10-30, 00:24–17:13 UTC, ≈ 4 by evening
   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 Chrome.
   Full card: https://gitnova.dev/en/r/Leonxlnx/napali.md
86. **abus-aikorea/voice-pro** — 0.9 · Cooling · Generative media · Python · +2 stars measured 2026-10-30, 00:24–17:13 UTC, ≈ 3 by evening
   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).
   Full card: https://gitnova.dev/en/r/abus-aikorea/voice-pro.md
87. **derek-zhuolin/motion-skill** — 0.9 · Cooling · Generative media · TypeScript · +1 star measured 2026-10-30, 00:23–17:14 UTC, ≈ 2 by evening
   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 studies.
   Full card: https://gitnova.dev/en/r/derek-zhuolin/motion-skill.md
88. **Chenkin-x/ComfyUI-Moss-Image-Edit** — 0.8 · Steady · Generative media · Python · +3 stars measured 2026-10-30, 00:23–17:14 UTC, ≈ 4 by evening
   A custom ComfyUI node for editing images from a text instruction with one or more reference images using the MOSS Image Edit model.
   Full card: https://gitnova.dev/en/r/Chenkin-x/ComfyUI-Moss-Image-Edit.md
89. **kailashsr38/ascii-magic-art** — 0.7 · Cooling · Generative media · JavaScript · +4 stars measured 2026-10-30, 00:25–17:14 UTC, ≈ 5 by evening
   A library of 634 animated ASCII art pieces for web pages, READMEs, wallpapers, and terminals. Allows browsing, embedding, and creating ASCII animations.
   Full card: https://gitnova.dev/en/r/kailashsr38/ascii-magic-art.md
90. **Mayzmei/anime-series-maker** — 0.7 · Cooling · Generative media · Python · +0 stars measured 2026-10-30, 00:18–17:14 UTC, ≈ 0 by evening
   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.
   Full card: https://gitnova.dev/en/r/Mayzmei/anime-series-maker.md
91. **OpenImagingLab/FlashVSR_Plus** — 0.5 · Steady · Generative media · Python · +2 stars measured 2026-10-30, 00:24–17:14 UTC, ≈ 3 by evening
   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 training dataset.
   Full card: https://gitnova.dev/en/r/OpenImagingLab/FlashVSR_Plus.md
92. **swax/dub-anything** — 0.3 · Steady · Generative media · Python · +0 stars measured 2026-10-30, 00:25–17:15 UTC, ≈ 0 by evening
   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.
   Full card: https://gitnova.dev/en/r/swax/dub-anything.md
93. **Netflix/vmaf** — 0.2 · Steady · Generative media · C · +0 stars measured 2026-10-30, 00:25–17:15 UTC, ≈ 0 by evening
   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.
   Full card: https://gitnova.dev/en/r/Netflix/vmaf.md
94. **HeyChengC/wallstreet-explainer** — 0.1 · Cooling · Generative media · JavaScript · +0 stars measured 2026-10-30, 00:24–17:15 UTC, ≈ 0 by evening
   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.
   Full card: https://gitnova.dev/en/r/HeyChengC/wallstreet-explainer.md
95. **DenRakEiw/scumble** — 0.0 · Quiet · Generative media · JavaScript · Not enough measurements today
   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, Seedream and more), and…
   Full card: https://gitnova.dev/en/r/DenRakEiw/scumble.md
96. **ashukae/ComfyUI-MangaScreen** — 0.0 · Steady · Generative media · Python · Not enough measurements today
   A ComfyUI filter that turns illustrations into black-and-white manga pages: crisp lines, flat tones, real screentone and framed panels.
   Full card: https://gitnova.dev/en/r/ashukae/ComfyUI-MangaScreen.md
97. **nmbrthirteen/podcli** — 0.0 · Quiet · Generative media · Python · Not enough measurements today
   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.
   Full card: https://gitnova.dev/en/r/nmbrthirteen/podcli.md
98. **ConquerorPhase/TAL-U-NO-Synth-Full-2026** — 0.0 · Cooling · Generative media · Not enough measurements today
   Install guide for TAL U NO Synth Full 2026 on Windows — a synthesizer and recording, editing, and mixing tools for desktop music production.
   Full card: https://gitnova.dev/en/r/ConquerorPhase/TAL-U-NO-Synth-Full-2026.md

For agents: https://gitnova.dev/llms.txt · search: https://gitnova.dev/api/v1/search?q=… · MCP: https://gitnova.dev/mcp · any page as Markdown — append .md to its URL