1. Abstract Qwen-Image-Layered is an open-source image "layering" model from the Qwen team: it takes a normal RGB image and outputs multiple RGBA laye...
1. Abstract VTP (Visual Tokenizer Pre-training) is an open-source visual tokenizer pre-training framework developed by the MiniMax (Hailuo) team, whic...
- Abstract PE-AV (Perception Encoder Audiovisual) is Meta's open-source audio-visual joint encoder family, which adds native audio capabilities on the...
1. Abstract HY World 1.5 (WorldPlay) is an open-source real-time world model framework developed by Tencent's Hunyuan team, with a video diffusion mod...
1. Abstract MiMo-V2-Flash is an open-sourced hybrid expert (MoE) large language model from the Xiaomi MiMo team, with a total parameter of about 309B ...
1. Abstract LongCat-Video-Avatar is an audio-driven avatar (virtual human) video generation model based on the LongCat-Video architecture, which is su...