Instructions to use nitrosocke/redshift-diffusion with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use nitrosocke/redshift-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("nitrosocke/redshift-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
- Draw Things
- DiffusionBee
Applying redshift style to existing image
#20
by fastandthefinetuned - opened
Hi, big fan of this model!
Would love to be able to apply this style directly to an image.
When using img2img, it always seems to step far away from the original image before the redshift style is in place?
ONNX is mentioned in the docs, maybe it is possible to make something like this one, but with redshift style?