OmniFusion Translate
Multimodal speech & image-grounded translation, 25 languages
None defined yet.
Multimodal speech & image-grounded translation, 25 languages
Zero-shot voice-cloning TTS at 48 kHz from dots.tts
Turn a course brief into slides or an interactive widget
Egocentric video + instruction to robot trajectory
Generate and outpaint seamless 360ยฐ panoramas with Krea 2
Same prompt, many seeds - diversity LoRA for Krea 2 Turbo
Verbatim & intended ASR with word timestamps
Recurrent feed-forward 3D Gaussian Splatting
Thai document/handwriting OCR with OpenThai 2.0 27B VLM
Hebrew text to IPA phonemes for TTS
4-step MiniMax-H3 with sparse attention โ video + audio
Convert table images to LaTeX code with CSPO
Voice cloning, voice design, speech editing and ASR
Long-term planar tracking with SAM 2 homographies
Surgical spatio-temporal grounding with RefineRank
Browser-GUI screenshot to structured observation text
Detect PII in Korean text with a 34M param model
Anime image generation & editing via distillation
GUI grounding โ locate UI elements from screenshots
torch.export + AOTInductor compiler for Zing-0.5
Predict robot action chunks with GigaBrain-0.7 3.5B
4-step text-to-video+audio with MiniMax-H3 FlashGen LoRA
Edit human-object interactions in images with OneHOI.
Generate extensible underwater 3D scenes with flow matching