BooM-VVT
Mask-free video virtual try-on
None defined yet.
Mask-free video virtual try-on
Keygen & demoscene chiptune with YuE2-3B + LoRA
Autoregressive image-to-video with Future Chunk Prediction
Zero-shot curation decisions with UltraBERT-380M
Document OCR VLM - text, layout, tables and math from pages
Transcribe, translate and reason over spoken audio
Gujarati TTS with voice cloning, 109M-param Pocket TTS
Predict single-cell gene perturbation effects in context
Typed questions about a state, answered as distributions
Upscale video drafts to 2K with MiniMax-H3 + refiner LoRA
Probe dense spine-X-ray embeddings for vertebral landmarks
159-category aerial object detection with LEVIRDetNet
DEIMv2-S real-time COCO object detection (DINOv3)
Multilingual ASR, translation & audio Q&A (40 langs)
Regenerate low-res video drafts at 2K with MiniMax-H3
Anima Role Ref KV - reference-guided character illustration
One reference image + prompt β same character, new scene
Protein-ligand docking with Matcha flow matching
Feed-forward 3D reconstruction from images or video
Isolate the caller's voice from a call recording, streaming
Locate any region in an image from a text description
Browser-screenshot fixed-choice decisions from a 2B VLM
Browser-screenshot decision model (VL-D protocol)
NVIDIA unified model - text-to-image, edit, VQA