Apply for community grant: Academic project (gpu)
Hello,
We would like to demo CustomDiffusion360, a method that allows you to control the camera viewpoint of the custom object in generated images by text-to-image diffusion models, such as Stable Diffusion. Given a 360-degree multiview dataset (~50 images), we fine-tune FeatureNeRF blocks in the intermediate feature space of the diffusion model to condition the generation on a target camera pose.
This is an academic project and the code is released here: https://github.com/customdiffusion360/custom-diffusion360
Thank you!
Hi @customdiffusion360 , 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
BTW, looks like the models are included in this Space repo, but would you create separate model repositories for them? It would make it easier for people to find your models.
You can download models easily using huggingface_hub library in your code. https://huggingface.co/docs/hub/en/models-adding-libraries#download-files-from-the-hub
Also, it's easy to upload and download models via CLI. https://huggingface.co/docs/huggingface_hub/main/en/guides/cli
Hello,
Thank you for the GPU assignment. We have done some testing, fixed deployment issues, and reduced memory usage, but we still run out of memory when loading Stable Diffusion XL.
Could we please get a A10G large assigned to this space?
We will look into creating separate model repositories in the future.