Instructions to use stabilityai/stable-diffusion-xl-base-1.0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use stabilityai/stable-diffusion-xl-base-1.0 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("stabilityai/stable-diffusion-xl-base-1.0", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Inference
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
- DiffusionBee
Does the fp16 vae still have issues?
#176
by sourcestakc - opened
I am trying to fine-tune the model and have tried both fp16 and default fp32 variants of the vae but don't notice any difference yet. There exists a fp16 fix here - https://huggingface.co/madebyollin/sdxl-vae-fp16-fix but I was wondering if the fp16 version in this repo has already been fixed?
NVM it still seems to generate black images.
sourcestakc changed discussion status to closed