You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Lumina-Image 2.0 is the latest model in the Lumina family and will be released very soon (https://huggingface.co/Alpha-VLLM/Lumina-Image-2.0). It is a 2-B parameter Diffusion Transformer that significantly improves instruction-following and generates higher-quality, more diverse images. Our paper will be released soon, and we have finished the diffuser pipeline for Lumina-Image 2.0.
Open source status
The model implementation is available.
The model weights are available (Only relevant if addition is not a scheduler).
@zhuole1025 This looks great! As you mention that the diffusers adaptation is complete, I wonder if you, or someone from your team, would like to open a PR adding support for it. We can then iterate together on finishing docs/tests and other things required for integration
Activity
a-r-r-o-w commentedon Jan 24, 2025
@zhuole1025 This looks great! As you mention that the diffusers adaptation is complete, I wonder if you, or someone from your team, would like to open a PR adding support for it. We can then iterate together on finishing docs/tests and other things required for integration
nitinmukesh commentedon Jan 29, 2025
@zhuole1025
Please if possible add bf16 variants in the repo.
a-r-r-o-w commentedon Feb 16, 2025
Support added in #10642. Thanks for the PR @zhuole1025!