Instructions to use sd-dreambooth-library/disco-diffusion-style with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use sd-dreambooth-library/disco-diffusion-style with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("sd-dreambooth-library/disco-diffusion-style", 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
- Draw Things
- DiffusionBee
ckpt
Where's the checkpoint/model file for this one?
I was looking for the ckpt as well, could not find it ;-(
i'd also like a ckpt so i can run this locally
Until now there is no person telling us how to download de CKTP from this
I find out that it need to be converted from this source code.
cehck this out:
https://github.com/huggingface/diffusers/issues/672#issuecomment-1265619410
you mean the thing that never ended up working in the webUI? not a useful solution
I tried this ,but I can‘t run it on my web ui
https://www.youtube.com/watch?v=tgRiZzwSdXg this video covers converting this dreambooth to ckpt, and it worked (you will have to download this repo, download script, and copy one line)