Cool model! Integration into Diffusers?
patrickvonplaten opened this issue · comments
Hey @dome272,
Congrats on releasing this model! Are you interested in adding it to diffusers: https://github.com/huggingface/diffusers by any chance? Would love to help :-)
We would love to. Can you ask Thom or Ahsen to get us into contact on slack?
Here's our hugging face org:
https://huggingface.co/wand-ai
(still need to upload the model)
Way faster but isn't trained on big dataset.
Add to Diffusers, will try with big dataset
What exactly do you mean by not trained on big dataset? LAION-5B aesthetic isn't exactly small, is it? :-)
We trained for two weeks on 64 A100s. But feel invited to train longer on more GPU resources.
Looking forward to seeing this in action!
So in case you have not noticed: Paella is available on huggingface, meanwhile, just follow this link.
So in case you have not noticed: Paella is available on huggingface, meanwhile, just follow this link.
Can you please provide its inpainting version too?