Add Arcane Diffusion for Diffusers
Hey @nitrosocke ,
Amazing work on Arcane Stable Diffusion. I've been playing around with it a bit and it works just great! In this PR I propose to add weights for the diffusers library to potentially improve user experience and give the user more functionality (TPU / Flax support / Apple MPS support).
This PR both adds diffusers weights and adds a section to the README which looks as follows:
Diffusers
This model can be used just like any other Stable Diffusion model. For more information,
please have a look at the Stable Diffusion.
You can also export the model to ONNX, MPS and/or FLAX/JAX.
from diffusers import StableDiffusionPipeline
import torch
model_id = "nitrosocke/Arcane-Diffusion"
pipe = StableDiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.float16)
pipe = pipe.to("cuda")
prompt = "arcane style, a magical princess with golden hair"
image = pipe(prompt).images[0]
image.save("./magical_princess.png")
Thank you so much for your work! I merged the the request and that should make the space work as well.
The space works now, but it's extremely slow on CPU 😅
@nitrosocke btw, If you could add diffusers support to your other fine-tuned models, I'd add them all into one space to choose between.
Okay I'll look into that and update you when it's done.
I tried the space as well but it would have taken over an hour to generate. I hope there are some settings that could be optimized to make it faster.