Omar Sanseviero

This is blocked by https://github.com/huggingface/transformers/issues/20830 and the lack of image feature extraction working in transformers cc @amyeroberts @LysandreJik

Hey all! Let me copy-paste the template for tracking new tasks Note that you're not expected to do all of the following steps. This helps track all the steps required...

I think it's different, as one task operates with video as inputs (so temporal information) while the other just operates with static input images.

cc @dylanebert let's launch this soon?

There are lots of cool models (Shap-E, Wonder3D, GaussianDreamer, SceneDreamer, SyncDreamer, Stable Dreamfusion), that we're in good shape to kick this off

For changes for the API, the place to be updated is https://github.com/huggingface/api-inference-community/tree/main/docker_images/diffusers

Just missing a widget here. cc @mishig25 for this we could reuse the widget of image generation but with no input? Example model https://huggingface.co/google/ddpm-cifar10-32

fyi @Vaibhavs10 @mishig25

We don't have live ASR Support for 3rd party models I think

cc @apolinario work needs to be done first in community inference API for the widget