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
Where to download sdxl-vae-fp16-fix
#32
by UlyssesHeart - opened
... since it doesn't seem downloadable here. Is sdxl.vae.safetensors essentially the same vae?
UlyssesHeart changed discussion title from Don't understand difference between sdxl.vae. and sdxl-vae-fp16-fix. to Where to download sdxl-vae-fp16-fix
All of the safetensors/bin files in this repo contain the fixed sdxl-vae-fp16-fix weights, just with different filenames and weight-storage formats to accomodate different apps.