Instructions to use stabilityai/stable-diffusion-xl-refiner-1.0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use stabilityai/stable-diffusion-xl-refiner-1.0 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline from diffusers.utils import load_image # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("stabilityai/stable-diffusion-xl-refiner-1.0", dtype=torch.bfloat16, device_map="cuda") prompt = "Turn this cat into a dog" input_image = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/cat.png") image = pipe(image=input_image, prompt=prompt).images[0] - Notebooks
- Google Colab
- Kaggle
difference between 2 models?
#37
by deleted - opened
@JeriffCheng
sd_xl_refiner_1.0_0.9vae.safetensors is the normal refiner model with the 0.9 vae(slightly worse fine detail)
sd_xl_refiner_1.0.safetensors is the normal refiner model with the 1.0 vae(slightly better fine detail)
Its basically unnoticeable and doesn't matter which one you use but just use the sd_xl_refiner_1.0.safetensors
You should rather try to use this vae "madebyollin/sdxl-vae-fp16-fix" since it will save considerable vram/ram and is the same quality as the 1.0 vae.
