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
- Draw Things
- DiffusionBee
Run SDXL on multiple GPUs
#195
by Scianso - opened
Hi everyone, i have a server with 2 tesla V100 gpus and I want to know if it's possible to run SDXL on both instead of one
Like @YaTharThShaRma999 said, set device map to balanced, but one important detail is it wont double the vram, it will have to load the model onto both.