Stable Diffusion
This release adds a new interface for the :hugs: Diffusers library which enables to support the Stable Diffusion pipeline for inference. Thus, you can now generate images from text on Gaudi relying on the user-friendliness of :hugs: Diffusers.
- Add support for Stable Diffusion 131
Check out the [documentation](https://huggingface.co/docs/optimum/habana/usage_guides/stable_diffusion) and [this example](https://github.com/huggingface/optimum-habana/tree/main/examples/stable-diffusion) for more information.
Wav2Vec2
After text and image models, a third modality is now supported with the addition of Wav2Vec2.
- Add suport for Wav2Vec2 120
Check out the [audio classification](https://github.com/huggingface/optimum-habana/tree/main/examples/audio-classification) and [speech recognition](https://github.com/huggingface/optimum-habana/tree/main/examples/speech-recognition) examples to see how to use it.