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
Getting white borders when using clip vision encode
#49
by tristan22mc - opened
I seem to be having issues when using clip vision encode as im trying to use multiple reference images to essentially act as an IPadapter for stable cascade. I've noticed that once I string together a few clip vision encodes I start to get a white border around the image and I'm not exactly sure how to get it to go away.
Im not even 100% sure that its the clip vision encode that is causing the white borders they seem to come and go at random sometimes.
