README.md

---
base_model: runwayml/stable-diffusion-inpainting
tags:
  - stable-diffusion
  - inpainting
  - lora
  - kto
  - diffusers
license: creativeml-openrail-m
library_name: diffusers
pipeline_tag: image-to-image
---

# ShreyashDhoot/v2

**Last updated:** 2026-04-28 06:34

## Model Description

KTO fine-tuned Stable Diffusion inpainter with LoRA for safety alignment.
Base model: [`runwayml/stable-diffusion-inpainting`](https://huggingface.co/runwayml/stable-diffusion-inpainting)

## Checkpoints

- `checkpoint--1000`
- `checkpoint--250`
- `checkpoint--500`
- `checkpoint--750`

## Example Eval Outputs

![eval_step1000_sample0.png](eval_outputs/eval_step1000_sample0.png)
![eval_step1000_sample1.png](eval_outputs/eval_step1000_sample1.png)
![eval_step1000_sample10.png](eval_outputs/eval_step1000_sample10.png)
![eval_step1000_sample11.png](eval_outputs/eval_step1000_sample11.png)
![eval_step1000_sample12.png](eval_outputs/eval_step1000_sample12.png)
![eval_step1000_sample13.png](eval_outputs/eval_step1000_sample13.png)
![eval_step1000_sample14.png](eval_outputs/eval_step1000_sample14.png)
![eval_step1000_sample15.png](eval_outputs/eval_step1000_sample15.png)

---
_Auto-generated by push_to_hf.py_