Hi there! I was invited by Hugging Face ML Engineer Ahsen Khaliq to create a demo for my project Mixture of Diffusers (https://github.com/albarji/mixture-of-diffusers, https://arxiv.org/abs/2302.02412).
This library allows combining several diffusion processes in the same canvas, thus creating a large image where the user can specify different prompts at each region of the image. In the demo I developed the user can configure three diffusion regions to create a panoramic image.
While the demo is functional, running it on CPU is unfeasible due to long running times. Therefore, I am requesting this grant to allow other Hugging Face users to try this out.
Hi @albarji, 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
Thanks a lot!