mouse1998mouse's Stars
showlab/Show-o
Repository for Show-o, One Single Transformer to Unify Multimodal Understanding and Generation.
showlab/BoxDiff
[ICCV 2023] BoxDiff: Text-to-Image Synthesis with Training-Free Box-Constrained Diffusion
Repository for Show-o, One Single Transformer to Unify Multimodal Understanding and Generation.
[ICCV 2023] BoxDiff: Text-to-Image Synthesis with Training-Free Box-Constrained Diffusion