* 4 new video models * Multiple image models, including SANA & Flux Control * New quantizers -> GGUF & TorchAO * New training scripts Enjoy this holiday-special Diffusers release ๐ค Notes: https://github.com/huggingface/diffusers/releases/tag/v0.32.0
In the past seven days, the Diffusers team has shipped:
1. Two new video models 2. One new image model 3. Two new quantization backends 4. Three new fine-tuning scripts 5. Multiple fixes and library QoL improvements
Coffee on me if someone can guess 1 - 4 correctly.
๐ We've just dropped a new release v0.27.0 of the ๐๐๐๐๐๐๐๐๐๐๐_๐๐๐ Python library!
This release includes: - ๐พ New torch model loading utilities in the serialization module โ providing a standardized way to save and load torch models with built-in support for sharding and safe serialization. - ๐ฆ Tooling for something exciting โ if you like single-file formats for models like GGUF, you'll love what we're cooking up ๐ More coming soon! - ๐ ๏ธ Loads of quality-of-life improvements and bug fixes!