Today I wanted to share an early preview of some work I’ve done to run Stable Diffusion in with Sentis:
com.doji.diffusers
com.doji.transformers
I ported the ClipTokenizer from huggingface/transformers and the PNDMScheduler and the denoising loop from huggingface/diffusers.
There is still lots to do, the quality is not really there yet. I think the most important thing would be to get Classifier-Free Guidance to work which I haven’t managed to do yet. I know other people have already shown their success with running diffusion models with Sentis on here, so maybe someone can give some advice or would like to contribute.
The GIF below is with the Stable Diffusion 1.5 model and 15 steps at 512x512.
1 post - 1 participant