We present Hunyuan-DiT, a text-to-image diffusion transformer with fine-grained understanding of both English and Chinese. To construct Hunyuan-DiT, we carefully designed the transformer structure, ...
Model for Sound demixing challenge 2023: Music Demixing Track - MDX'23. Model perform separation of music into 4 stems "bass", "drums", "vocals", "other". Model won ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results