Spaces:
Sleeping
Apply for community grant: Academic project
Hi there, we built a tool that creates a hard prompt that describes the user's images, or it can also shorten long prompts. The user can also feed the learned hard prompt to the Stable Diffusion model to generate new images with similar semantic meanings.
The method requires at least around 1000 optimization steps on the CLIP model, so it requires GPU support. Our lab is funding the compute for this right now, but cannot do so for longer periods of time, so it will be helpful if we can get some GPU grant.
Thanks!
Hi @ywen , 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