Lists (1)
Sort Name ascending (A-Z)
Stars
Music Systems for Stage, Interaction and Live Performance 可表演音乐 —— 面向舞台、实时交互与现场表演的音乐系统研究
mukseq / vork
Forked from voyager-so/vorkHeadless 3D and VFX engine for agents. Research preview.
Headless 3D and VFX engine for agents. Research preview.
Local-first, agent-native control plane for ComfyUI — MCP server + sidebar agent that generates images, video & audio, authors and runs workflows, and edits your live graph in natural language on A…
Open-source Higgsfield on ComfyUI: 120 image, video, VFX and audio apps, every model open weights; runs on Modal or your own GPU
Open-source Higgsfield rebuilt on ComfyUI (#OpenSourceHiggsfield): 146 tools + all 83 Higgsfield apps, Cinema Studio, Elements. Open weights + partner models. 130 with real renders. MIT.
ComfyUI Timeline Studio for MiniMax H3: multi-shot video, visual memory across scenes and angles, and local or cloud Story writing.
OpenRouter for agent tools. Join community here: https://discord.gg/6mQYYfFMAn
Imagination Studio by keys+Wasserman powered by TensorFold: an AI film studio for Mac and NVIDIA DGX Spark. Plan a film like a crew (Slate workflow by Sam Wasserman), render Qwen-Image-2.1 / FLUX3-…
Self-evolving Context Database for AI Agents. Unify Agent Memory, Knowledge RAG and Skills.
sergiuszm / ninfer-4090
Forked from Don-Chad/ninfer-3090Qwen3.8-27B on one RTX 4090: full native 262K context via E8 4-bit KV, up to 149 tok/s code decode with MTP3, sm_89-retuned attention prefill, vision, llama.cpp-compatible /metrics + /slots
Free local LoRA training studio: build character, style and concept datasets from one photo or a big image folder, caption them (JoyCaption, prose or booru tags), train LoRAs with ai-toolkit for Kr…
mukseq / MagoStudio
Forked from MagoStudio/MagoStudioMagoStudio application
Open-source local AI video analyzer powered by Ollama. Visual search, automatic highlights, scene/action/object detection, audio analysis, and subtitle generation. Free, offline alternative to Twel…
Your GeForce runs AI at half speed. This fixes it for 20/30/40 series cards. Up to 2× FP16 / BF16 / TF32 tensor throughput
GPU tensor unlock source for RTX 4090 and experimental RTX 4070 Ti SUPER; firmware generated locally
KESHIKI (景色) VFX Studio — a local VFX studio inside ComfyUI on open-weights models (LTX-2.5, FLUX.3 Klein)
An intuitive controlnet 3D node pass generator from Mixamo FBX Animation files
An intuitive prompt builder Node
Open-source 3D camera, character & motion previs studio replacing Higgsfield 3D-Jutsu for AI video.
AI agent to iteratively create visual content via comfyui workflows
AI VFX elements for your own footage in ComfyUI: LTX-2.5 generates fire, lightning, smoke or particles; Element Forge tracks, lights and layers them into the shot. Open weights, runs locally.
Timeline-based video editor for ComfyUI with scenes, project assets, gallery, images as keyframes, render staging, and takes for iterative long-form generation.
A local, open source character designer that runs on your own ComfyUI.
An app that streamlines the Comfy stack. Featuring reference-supported generation and more all in one compact UI.
A open source desktop app for building Movies with Minimax H3.
Open-weights kinetic-type motion graphics: a ComfyUI node pack + browser app (Gemma 4, LTX 2.5, ACE-Step, MOSS)