Instructions to use nitrosocke/redshift-diffusion-768 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use nitrosocke/redshift-diffusion-768 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("nitrosocke/redshift-diffusion-768", 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
Did you upload the .ckpt file?
#2
by GalaxyTimeMachine - opened
Is the format different for this model? I don't see and .ckpt files.
Neither do I, is it only available through Patreon?
The ckpt is not available yet because it's not working with automatic yet. We haven't found the cause and don't know which step in the pipeline is causing this. Right now if you load the ckpt file in automatic it behaves like stock SD 2.0 without the fine tuning. I hopefully have a working checkpoint as soon as possible.
@Zimmy @GalaxyTimeMachine
Weights are now available to download! Make sure to update automatic1111 to the latest version to use them!
Thank you!!!
GalaxyTimeMachine changed discussion status to closed