Instructions to use stabilityai/stable-diffusion-xl-base-0.9 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use stabilityai/stable-diffusion-xl-base-0.9 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-0.9", 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
- Draw Things
- DiffusionBee
Get an nan image after vae
#38
by Number18-tong - opened
I loaded the required pretrained models and initialized StableDiffusionXLPipeline with these models. Show as bellow picture.
And no matter what prompt I enter, the result is a black image, I found the image after vae is nan, if i change the vae pretrained model(eg. changed to sd1.5) , the result is correct but unclear. Someone knows how to solve this problem? Thanks very much!
I am using stabilityai/sdxl-vae and have no issues with that
same issue here
Seems that turning of amp and only using fp32 also works