Spaces:
Sleeping
Apply for community grant: Company project (gpu)
The demo provided in this Spaces (https://huggingface.co/spaces/imatag/stable-signature-bzh) shows how to produce watermarked AI-generated images with SDXL-turbo. By finetuning the VAE decoder with StableSignature adapted to IMATAG robust decoder, we present a way to implement this state-of-the-art technology in an easy way. We also provide a detector (https://huggingface.co/imatag/stable-signature-bzh-detector-resnet18) in addition to our API so that the whole watermarking solution is standalone.
Altough the watermarking comes at no additional computational cost as part of the generation process, and detection is lightweight, images still need to be generated with SDXL-turbo. We apply to this grant for a GPU so that the images generated quickly enough to keep the demo interactive.
Thanks,
Vivien - researcher at IMATAG.
Hi @imatag-vch , 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
Great! Thank you very much!