import torch
from diffusers import DiffusionPipeline
from diffusers.utils import load_image
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("runwayml/stable-diffusion-inpainting", dtype=torch.bfloat16, device_map="cuda")
pipe.load_lora_weights("ShreyashDhoot/v3")
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]ShreyashDhoot/v3
Last updated: 2026-05-06 04:41
Model Description
KTO fine-tuned Stable Diffusion inpainter with LoRA for safety alignment.
Base model: runwayml/stable-diffusion-inpainting
Checkpoints
checkpoint--1000checkpoint--1250checkpoint--1500checkpoint--1750checkpoint--2000checkpoint--2250checkpoint--250checkpoint--2500checkpoint--2750checkpoint--3000checkpoint--3250checkpoint--3500checkpoint--3750checkpoint--4000checkpoint--4250checkpoint--4500checkpoint--4750checkpoint--500checkpoint--5000checkpoint--5250checkpoint--5500checkpoint--750
Example Eval Outputs
Auto-generated by push_to_hf.py
- Downloads last month
- -
Model tree for ShreyashDhoot/v3
Base model
runwayml/stable-diffusion-inpainting