tencent/HunyuanVideo
Text-to-Video β’ Updated β’ 1.02k β’ β’ 2.14k
Flexible Photo Recrafting While Preserving Your Identity
MultiImages-to-3D Generation
Text-to-3D and Image-to-3D Generation
Extend images to desired dimensions using prompts
Generate virtual try-on images by masking and overlaying garments
Try on clothes virtually with images
OpenAI's Deep Research, but open
High-quality speech synthesis powered by Kokoro TTS
A unified multimodal understanding and generation model.
https://huggingface.co/papers/2501.03006