Open aolko opened 8 months ago
Hello, Thank you for your interest in Differential Diffusion. Which pipeline do you use? I've tested the implementation on 2080 and 3090 GPUs, and the inference penalty of the algorithm is about 0.25%. In the meantime, you might want to explore some of the available demos:
https://huggingface.co/spaces/exx8/differential-diffusion https://replicate.com/lucataco/differential-diffusion https://colab.research.google.com/github/exx8/differential-diffusion/blob/main/examples/SD2.ipynb
i'm using the pinokio implementation
i'm using the pinokio implementation
Hi, sorry for the delay. I am not the maintainer of pinokio, I will try to communicate this with the maintainer of pinokio.
Thanks for sharing
Optimize differential diffusion for most consumer GPUs My GPU: NVIDIA GeForce GTX 1060 6GB slow ass steps: 15/40 [14:33<24:19, 58.37s/it]