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
Unet config only_cross_attention list looks weird
#17
by thnbp24 - opened
https://huggingface.co/stabilityai/stable-diffusion-x4-upscaler/blob/main/unet/config.json
In this file,
(1) DownBlock2D doesn't have any only_cross_attention argument but it's set to True (index 0). This has no impact either True or False. Just want to confirm.
(2) The down_block_types sequence is also reverse of that of V2 model. (link: https://huggingface.co/stabilityai/stable-diffusion-2/blob/main/unet/config.json)
Are both of these intended? Thanks.