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
How to make the internal activation smaller
#24
by xuruipeng8641 - opened
Hi, thanks a lot for your contribution for sdxl-fp16 !! I have pruned a sdxl decoder in fp32, I wish I can transfer it smoothly to fp16. Could you open-source your training code, because I do not quite know how and what the extent to scale down weights and biases. THANKS !!!