Spaces:
Running
on
Zero
Apply for community grant: Academic project (gpu)
We present PixelFlow, a family of image generation models that operate directly in the raw pixel space, in contrast to the predominant latent-space models. This approach simplifies the image generation process by eliminating the need for a pre-trained Variational Autoencoder (VAE) and enabling the whole model end-to-end trainable. Through efficient cascade flow modeling, PixelFlow achieves affordable computation cost in pixel space. It achieves an FID of 1.98 on 256x256 ImageNet class-conditional image generation benchmark. The qualitative text-to-image results demonstrate that PixelFlow excels in image quality, artistry, and semantic control. We hope this new paradigm will inspire and open up new opportunities for next-generation visual generation models.
Hi @ShoufaChen Looks like this Space is already running on ZeroGPU. As you are in the ZeroGPU explorers org, I believe you assigned it yourself and you don't need a grant.
Hi @hysts ,
Thanks for your help! It looks like I’ve run out of my quota — could you please help me with this?
Ah, sorry, but unfortunately, it's simply not possible to increase ZeroGPU quota. Even HF staff are affected by the same ZeroGPU quota limit. ZeroGPU quota is refreshed every day, though I'm not sure what time it happens.
Got it. Thank you @hysts .