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
"pooled_prompt_embeds" vs "prompt_embeds"
#71
by jloganolson - opened
What are 'pooled_prompt_embeds' in the xl pipeline and how are they different than 'prompt_embeds'?
Did you get sdxl to generate images when manually passed prompt_embeds?
When I pass the CLIP embeddings to the pipeline I get an error that seams to be caused by the Unet:RuntimeError: mat1 and mat2 shapes cannot be multiplied (2x2304 and 2816x1280)