README.md

---
tags:
- text-to-image
- lora
- diffusers
- template:sd-lora
- flux
- ' image-generation'
widget:
- text: >-
    (ruins, broken, summer, dappled sunlight:1.2), sun, tree, forest, scenery,
    rock, reflection, water, ancient, overgrown, mountains, sunset, clouds,
    mountainous horizon, fantasy, medieval, 1other, looking away, cloak, (pixel
    art, pixelated:1.2), (masterpiece, exceptional, best aesthetic, best
    quality, masterpiece, extremely detailed:1.2), in the style of umempart
  output:
    url: images/Flux_00189_.png
- text: >-
    (ruins, broken, snow, dappled sunlight:1.2), sun, tree, forest, scenery,
    rock, reflection, ancient, overgrown, mountains, sunset, clouds, mountainous
    horizon, fantasy, medieval, 1other, looking away, (pixel art,
    pixelated:1.2), (masterpiece, exceptional, best aesthetic, best quality,
    masterpiece, extremely detailed:1.2), in the style of umempart
  output:
    url: images/c363192f-5fa0-4539-8295-b8d9e3e96747.jpeg
- text: >-
    (blue theme, summer, dappled sunlight, 1other, looking away, cloak:1.2),
    sun, tree, forest, scenery, rock, reflection, water, lake, island, ancient,
    overgrown, mountains, sunset, clouds, mountainous horizon, fantasy,
    medieval, (pixel art, pixelated:1.2), (masterpiece, exceptional, best
    aesthetic, best quality, masterpiece, extremely detailed:1.2), in the style
    of umempart
  output:
    url: images/89af1674-e4df-489a-8a5f-07626fc10b1e.jpeg
base_model: black-forest-labs/FLUX.1-dev
instance_prompt: umempart
license: mit
datasets:
- UmeAiRT/Ume-Modern_Pixel_Art
---
# LoRA - Modern pixel art

<Gallery />

## Model description 

Here&#39;s a new LoRA in a much more modern style.

Based on games I&#39;ve personally really enjoyed from the modern 2d pixel art category.

This is the first time I&#39;ve worked with such a large dataset (100), so I&#39;m not sure my settings are optimal.

Don&#39;t hesitate to send me feedback or suggestions!

## Trigger words

You should use `umempart` to trigger the image generation.


## Download model

Weights for this model are available in Safetensors format.

[Download](/UmeAiRT/FLUX.1-dev-LoRA-Modern_Pixel_art/tree/main) them in the Files & versions tab.

## Training parameter

epochs : 20

steps : 2000

lora_rank : 32

optimizer : prodigy

resolution : 1024