UnCLIP Text Interpolation Pipeline Demo
A demo of the community pipeline described at https://github.com/huggingface/diffusers/issues/1869. The pipeline encodes two given prompts to their text_embeddings and interpolates between the embeddings for n steps. The interpolated embeddings are passed to the model for decoding to images.
This would be too slow to run on a CPU so I'd like to apply for GPU grant for showcasing the capabilities of the community pipeline. :)
Hi @NagaSaiAbhinay , we have assigned a gpu to this space. Note that GPU Grants are provided temporarily and might be removed after some time if the usage is very low.
To learn more about GPUs in Spaces, please check out https://huggingface.co/docs/hub/spaces-gpus