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
Remove text-to-image tag
#19
by patrickvonplaten - opened
WebUIs build on top of diffusers start to rely on the HF Hub client library to filter for models. This one should not be displayed when listing "text-to-image" models:
import huggingface_hub as hf
hf_api = hf.HfApi()
model_filter = hf.ModelFilter(
model_name="",
task='text-to-image',
tags='stable-diffusion',
library=['diffusers', 'stable-diffusion'],
)
res = hf_api.list_models(filter=model_filter, full=True, limit=200, sort="downloads", direction=-1)
patrickvonplaten changed pull request status to merged