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 Settings
- Draw Things
- DiffusionBee
How to load the vae bin file in automatic1111's web ui?
#9
by JamesMiller91 - opened
Usually other models I use come with a .vae file but in the vae folder here there's only a .bin file.
I tried renaming the ext. and loading it, but it failed. Any help is appreciated
use this script https://github.com/huggingface/diffusers/blob/main/scripts/convert_diffusers_to_original_stable_diffusion.py
to convert vae to A1111 checkpoint, also this script will need the folder path, where all the subfolders are of vae, text_encoder, unet etc.
Let's say you have a folder my_redshift-model/
Open terminal/command prompt, using cd command go to that script folder
then use this command
convert_diffusers_to_original_stable_diffusion.py --model_path <path-to-my_redshift-model/> --checkpoint_path <name_of_the_model>.ckpt
Replace text encapsulated with <...> with your own text, this should help
nitrosocke changed discussion status to closed