Type a name, or just describe what you need. Results blend keyword and meaning-based search. 7 matches, each with an EU availability status.
Model
Efficient high-resolution video matting model using sparse memory propagation, extending MatAnyone 2.
Research model for video relighting that jointly generates relit video and per-frame environment maps, no camera poses needed.
Video-diffusion LoRA that repairs artifacts in 3DGS, NeRF, mesh and point-cloud renders while keeping the camera path.
Model · Tencent
Tencent's Qwen3-VL-based model unifying detection, pointing, OCR, segmentation and alpha matting in one VLM.
Research framework for real-time, causal streaming video editing with diffusion, running at about 12.66 FPS.
Research method for multi-shot text-to-video with frame-accurate cuts, fades and camera moves, built on Wan2.1-T2V-14B.
App
Community ComfyUI workflow that generates video with MiniMax and upscales it using the LTX 2.5 spatial upscaler.
