sources
- MatAnyone (CVPR 2025) active
- PlayCanvas Engine active
- Robust Video Matting (RVM) active
- ostris/ai-toolkit active
- OpenTalker/SadTalker active
- OpenAI Whisper active
- MMPose RTMPose project (open-mmlab/mmpose) active
- FaceForensics++ active
- OmniSVG active
- Piper TTS (OHF-Voice piper1-gpl) active
- ViPE: Video Pose Engine active
- nunchaku-ai/nunchaku (SVDQuant inference engine) active
- CorridorKey (neural green screen keyer) active
- Netflix VMAF and libvmaf active
- Netflix Photon (IMF validator) active
- Nerogar/OneTrainer active
- Gaussian Splatting SLAM (MonoGS) active
- YuE / YuE2 active
- pytorch-fid (Frechet Inception Distance) active
- LichtFeld Studio active
- three.js active
- Motion Canvas active
- MLT Multimedia Framework active
- Croissant (ML dataset metadata format) active
- ml-explore/mlx-examples active
- VibeVoice (TTS code removed) active
- TRELLIS (Structured 3D Latents) active
- Manim Community Edition active
- MakeHuman active
- WhisperX active
- ltdrdata/ComfyUI-Impact-Pack active
- LayerDiffuse (transparent image layer diffusion) active
- DiffuEraser active
- kohya-ss/sd-scripts active
- kohya-ss/musubi-tuner active
- ComfyUI-segment-anything-2 (SAM 2 nodes) active
- Kdenlive active
- StarVector (image/text to SVG) active
- CLIPScore active
- invoke-ai/InvokeAI active
- Coqui TTS (idiap maintained fork, coqui-tts) active
- IDEA-Research/DWPose active
- 4D Gaussian Splatting for Real-Time Dynamic Scene Rendering active
- Image-Adaptive 3D LUT (PAMI) active
- huggingface/safetensors active
- huggingface/peft active
- MMAudio (video-to-audio synthesis, CVPR 2025) active
- Cutie: Putting the Object Back into Video Object Segmentation active
- libplacebo active
- GuyTevet/motion-diffusion-model (MDM) active