---
license: cc-by-4.0
pipeline_tag: text-to-image
tags:
- art
- ' stable-diffusion'
- dreambooth
library_name: diffusers
language:
- en
---
<h1>This is a diffusion model for generating SD 1.5 images, trained on 11 pictures of my friend Vanya using Dreambooth.</h1>
<h3><i>Fine-tuned for ~14k steps using NVIDIA TESLA V100. Good similarity has been achieved despite a small dataset of 11 512 by 512 images</i></h3>

Usage of the token below:

| Token                 | Description                          |
|-----------------------|--------------------------------------|
| 👤 `VanyaKeshev`      | Uses concept trained on Vanya        |

## Examples

<h1>Original face sample from dataset</h1>
<img src="https://huggingface.co/MarkK/VanyaKeshevSD1.5/resolve/main/%D0%92%D0%B0%D0%BD%D0%B8%20%D0%9A%D1%83%D1%88%D0%B5%D0%B2%D1%8B/photo_2023-03-13_19-06-02.jpg" width="300">

<h1>Result</h1>
<img src="https://huggingface.co/MarkK/VanyaKeshevSD1.5/resolve/main/%D0%92%D0%B0%D0%BD%D0%B8%20%D0%9A%D1%83%D1%88%D0%B5%D0%B2%D1%8B/00037-868393631.png" width="250">
<img src="https://huggingface.co/MarkK/VanyaKeshevSD1.5/resolve/main/%D0%92%D0%B0%D0%BD%D0%B8%20%D0%9A%D1%83%D1%88%D0%B5%D0%B2%D1%8B/00026-1460256817.png" width="250">