Spaces:
Sleeping
Apply for community grant: Academic project
The aim of our project called GlyphControl is to generate legible and readable visual text on the images through generative diffusion models, which is hard for current mainstream methods. With the custom specification of rendered text, the users could control the location, and font size of generated visual text. With this space, we would like to demonstrate our progress to the public. The relevant report is available at https://arxiv.org/pdf/2305.18259.pdf.
However, when the whole system is operating on CPU devices, the inference process takes too much time (more than 3 mins to generate 3 images), which would affect the user experience. Thus, we would like to apply for a community GPU grant to make the inference latency much shorter and provide the trials on our system to everyone in the AIGC community.
Hi @yyk19 , 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
Thanks for your help! We will release the demo as soon as possible! Thanks again!