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
New demo of SDXL. Fast and free!
#108
by deleted - opened
Try it! New one of the fastest demos of Stable Diffusion XL-1.0!
Space can:
- Generate images quickly
- Image resolution 1024x1024
- Generation takes place on the free Freya Inference API technology, so you can duplicate space and use it privately, no GPU needed!
Try it and if you like it, like the space: https://huggingface.co/spaces/openskyml/super-fast-sdxl-stable-diffusion-xl
in white minimal space divinely realistic close-up, photorealism, 3d render of real empty nautilus shell in vibrant colors on a white background., beautiful, dry, elegant, saturated, bright contrast, depth of field, neon tones, 100 mm shot, f/2.0, natural lighting, realistic, impressive, 8k, uhd in guokka color
This comment has been hidden