Hi, this is a academic project for our recent paper https://arxiv.org/abs/2212.07352. It investigates how the prior of diffusion models works for image-to-image. This space provides a colorization demo and shows how the bi-noising prior makes the result difference.
Hi @MKFMIKU, 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