---
language:
- en
thumbnail: "https://huggingface.co/wavymulder/lomo-diffusion/resolve/main/images/page1.jpg"
license: creativeml-openrail-m
tags:
- stable-diffusion
- stable-diffusion-diffusers
- text-to-image
- safetensors
- diffusers
inference: true
---



**Lomo Diffusion**
![Header](https://huggingface.co/wavymulder/lomo-diffusion/resolve/main/images/page1.jpg)
[*CKPT DOWNLOAD LINK*](https://huggingface.co/wavymulder/lomo-diffusion/resolve/main/lomo-1.0.ckpt) - - - [*SAFETENSORS DOWNLOAD LINK*](https://huggingface.co/wavymulder/lomo-diffusion/resolve/main/lomo-1.0.safetensors)

This is a dreambooth model trained on a diverse set of stylized photographs.

Use the activation token **lomo style** in your prompt (I recommend at the start)

This model is inspired by the Lomography movement, which embraces the imperfections and style of old LOMO cameras. The model excels at producing bright saturated colors as well as a variety of film artifacts that add to the illusion of a real photograph.
When using most models, I typically use **blur haze** in my negative prompt. I encourage you to experiment and see what works well for you.

Trained from 1.5 with VAE.

Please see [this document where I share the parameters (prompt, sampler, seed, etc.) used for all example images.](https://huggingface.co/wavymulder/lomo-diffusion/resolve/main/paramets_for_samples.txt)

You can [see here a non-cherrypicked batch of 49 images here.](https://i.imgur.com/cfIj3iq.jpg)

And you can [see here a direct comparison between Analog Style and Lomo Style.](https://i.imgur.com/ugdFzPI.jpg)


![Environments Example](https://huggingface.co/wavymulder/lomo-diffusion/resolve/main/images/page2.jpg)