How to use svdiff-library/svdiff_chair_example with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("svdiff-library/svdiff_chair_example", dtype=torch.bfloat16, device_map="cuda") prompt = "photo of a pink chair with black legs" image = pipe(prompt).images[0]
These are SVDiff weights for runwayml/stable-diffusion-v1-5. The weights were trained on photo of a pink chair with black legs as Single Image Editing.
Base model
