Instructions to use Guizmus/BloodborneDiffusion with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use Guizmus/BloodborneDiffusion with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("Guizmus/BloodborneDiffusion", 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
Can't get it to work.
When I load it in SD Auto1111 it says ERROR and then "RuntimeError: Expected all tensors to be on the same device, but found at least two devices, cpu and cuda:0! (when checking argument for argument index in method wrapper__index_select)"
Hey !
Yep, I have had this error on another model too. I fixed it and can now repair my models, I'll do this one next, I had this bug on multiple ones. Sorry for that, I'll update this conv once it's online.
New CKPT uploaded, it should work now. The file structure was wrong because I was in pytorch 1.13. going back to 1.12 let me make a valid ckpt again. It worked with --disable-safe-unpickle, but that's not good to use
I changed the version to v1-1 to reflect this change
Thanks so much! Great work! :D
Thanks !