Instructions to use stabilityai/stable-diffusion-x4-upscaler with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use stabilityai/stable-diffusion-x4-upscaler 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-x4-upscaler", 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
Use Case - little bit better result
#29
by jureklookas - opened
Put your source files into canva instead of resize
Instead of working with asymmetrically resized files, you can create a canva, then adjust the longest side of the source file to the size of the canva and resize the source file while maintaining the proportions.
You can adjust the color of the canva to suit your needs.