Instructions to use stabilityai/sdxl-vae with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use stabilityai/sdxl-vae 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/sdxl-vae", 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
Everything comes back nsfw
#7
by dkackman - opened
My default prompt is "spoons" and even that is coming back as nsfw (using SD 1.5). I don't want to turn of that filter but regardless that doesn't seem right.
You need to use the new model, not SD 1.5.
meaning the SDXL base model? or 2.1?
Are you able to use it with SD v1 without getting artifacts all over the image?
Sd 1.5 comes as a black image & flagged nsfw. 2.1, I suppose since it doesn’t have the detector(?) comes back black but not flagged.
Maybe your computer just needs to get laid.