Apply for community grant: Academic project

by orpatashnik - opened

Demo for the paper "Localizing Object-level Shape Variations with Text-to-Image Diffusion Models". In this paper, we use Stable Diffusion to generate variations for a specific object in a given image.

Hi @orpatashnik , 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


To support the usage of real images in my demo, I need to perform inversion which requires ~24GB RAM. Is it possible to get the T4 medium?

Sign up or log in to comment