Stars
Character turnaround and location reference sheets from a MiniMax-H3 camera move, with vision-model frame selection.
Refine and improve the quality of small faces in MiniMax H3 video. Per-frame face tracking, crop, refine with H3, stitch back.
A model hybridization loader to combine different layers/blocks of the fl2va and ref2va models
Clip chaining for MiniMax H3 in ComfyUI - motion and audio genuinely continue across joins
A machine learning-based video super resolution and frame interpolation framework. Est. Hack the Valley II, 2018.
Clip chaining for MiniMax H3 in ComfyUI - motion and audio genuinely continue across joins
Lightweight FirstBlockCache acceleration node for native ComfyUI MiniMax H3
A skill that turn any brand into a scrollable 3D world landing page
Build voice agents with open-source models
Rebuild the object in a reference image as a code-only, procedural, quality-gated, animation-ready Three.js model. Token-efficient image-to-3D.
Toonflow 是开源一站式 AI 短剧创作工具，将小说、剧本快速转化为动画短剧。集成 AI 编剧、智能分镜、角色与视频生成，跨平台桌面端轻量部署，助力创作者低成本批量产出视觉内容。Toonflow is an open-source AI tool that turns stories and scripts into animated short dramas. Features AI…
Penpot: The open-source design platform for Product teams that need scalable collaboration.
a machine learning image inpainting task that instinctively removes watermarks from image indistinguishable from the ground truth image
TurboDiffusion: 100–200× Acceleration for Video Diffusion Models
A lightweight, lightning-fast, in-process vector database
JavaScript in-page GUI agent. Control web interfaces with natural language.
把 Markdown 一键排成可直接粘进公众号编辑器的精致 HTML —— 6 套精选主题 + 主题生成器 + 双关卡校验。An AI-agent skill that turns Markdown into paste-ready WeChat article HTML.
Comprehensive production pipeline for quad-modal AI filmmaking with Seedance 2.0
The open-source AI voice studio. Clone, dictate, create.
Unlimited-length talking video generation that supports image-to-video and video-to-video generation
We write your reusable computer vision tools. 💜
A unified AI model hub for aggregation & distribution. It supports cross-converting various LLMs into OpenAI-compatible, Claude-compatible, or Gemini-compatible formats. A centralized gateway for p…
Autonomous game development for Godot, Bevy, and Babylon.js with Claude Code and Codex
World's first open-source, agentic video production system. 12 production pipelines, 100+ tools, 700+ agent skill and production-knowledge files. Turn your AI coding assistant into a full video pro…
Confucius4-TTS: a Multilingual and Cross-Lingual Zero-Shot TTS Engine
TripoSplat converts a single 2D image into high-quality and variable number of 3D Gaussians, developed by TripoAI.
Official Implementation of SCAIL-2: Unifying Controlled Character Animation with End-to-end In-Context Conditioning