Instructions to use madebyollin/sdxl-vae-fp16-fix with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use madebyollin/sdxl-vae-fp16-fix with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("madebyollin/sdxl-vae-fp16-fix", 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
VAE - don't force the vae to be upcasted to FP32 automatically
#3
by patrickvonplaten - opened
No description provided.
This would enable this PR: https://github.com/huggingface/diffusers/pull/4083
Really amazing work! You're saving the community 3GB of GPU RAM ;-)
Thanks! This PR is currently putting Python dict syntax in a json file, but I'm happy to merge once that's fixed.
Ups that was embarrassing - corrected it!
madebyollin changed pull request status to merged