Visual AI video studio for MiniMax H3 + ComfyUI. Create text-to-video, image-to-video, reference video, video-to-video, storyboards, resumable generations, and long-form AI videos.
CLI-native local AI image and video generation for people, scripts, and agents — CUDA on Linux, Metal on macOS, plus desktop, web, iPhone, REST/SSE, and MCP.
Comfy Cloud product skills: slash commands for generating images, video, audio, and 3D with Comfy Cloud agents. Single source of truth for the installer and MCP server.
Local desktop app to build structured MiniMax H3 video prompts (T2VA/I2VA/FL2VA/L2VA/Ref2VA) using a local LLM via Ollama or LM Studio. Streams output, auto-describes reference images with vision models, 100% offline — no API keys, no cloud.