Instructions to use stabilityai/stable-cascade with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use stabilityai/stable-cascade 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-cascade", 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
- Local Apps
- Draw Things
- DiffusionBee
Weights License?
#58
by JonMichaelGalindo - opened
What is the license for Stable Cascade's pre-trained weights? The training code is MIT license. When can we get a license for the pre-trained weights? The MIT license is the only license linked from this model card (by linking to the github repo), so the most reasonable interpretation is that the weights are also MIT licensed. I am fine with indemnifying Stability and the Würstchen team / accepting full legal responsibility for any kind of commercial deployment, but I would love some clarification.