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
EMA (exponential moving average) training of SDXL model
Recently I wanted to try out training and inference using the EMA variant of the SDXL model but was unable to find any info on it. Are the models not available or the models as seperate component the EMA variant? Also there aren't much info available on EMA training method of SDXL. Has anyone from the community tried working with the ema variant?
Recently I wanted to try out training and inference using the EMA variant of the SDXL model but was unable to find any info on it. Are the models not available or the models as seperate component the EMA variant? Also there aren't much info available on EMA training method of SDXL. Has anyone from the community tried working with the ema variant?
Have you find the correct way to handle it?