Instructions to use hakurei/artstation-diffusion with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use hakurei/artstation-diffusion with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("hakurei/artstation-diffusion", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
- DiffusionBee
Is there a ckpt file?
For a colab runnig webui I can't find a file to download.
i think you can just rename it to diffusion_pytorch_model.ckpt
edit: doesn't work
It's probably this: https://gist.github.com/Christopher-Hayes/636ba25e0ae2e7020722d5386ac2571b
But it is not super welcoming for users to have to go through hoops to access the model. ¯_(ツ)_/¯
Also, I don't know how would I use it in Colab.
If I may ask you to do the same for wikiart diffusion. (https://huggingface.co/valhalla/sd-wikiart-v2)
isnt 1.4 just a 400 mb vae right now, due to it not being complete, IIRC this is more or less a beta, its useable just put it in models/vae and turn it on via the web ui in settings.
i could be wrong ive been playing with a ton of these latley trying to get my bleach and DBZ models working.. bleach V1 is up :D **save rukia ark
Just convert it using this: https://github.com/huggingface/diffusers/blob/main/scripts/convert_diffusers_to_original_stable_diffusion.py