---
tags:
- text-to-image
- flux
- lora
- diffusers
- template:sd-lora
- ai-toolkit
widget:
- text: A person in a bustling cafe, greyscale drawing
  output:
    url: samples/1740420377791__000000800_0.jpg
- text: a train station, a train entering the station, greyscale drawing
  output:
    url: samples/1740420407012__000000800_1.jpg
- text: aerial view of Paris, greyscale drawing
  output:
    url: samples/1740420436065__000000800_2.jpg
- text: a crocodile in the fountain, greyscale drawing
  output:
    url: images/example_b05hrcgw5.png
- text: a small airport, greyscale drawing
  output:
    url: images/example_ie0g9ftvs.png
- text: happy people playing petanque in front of the church, greyscale drawing
  output:
    url: images/example_jpeyydra2.png
- text: >-
    aerial view of a cowboy death duel on main street, western, greyscale
    drawing
  output:
    url: images/example_ol1f5bbio.png
- text: picnic at the lake, greyscale drawing
  output:
    url: images/example_dty4dnqxo.png
base_model: black-forest-labs/FLUX.1-dev
instance_prompt: greyscale drawing
license: other
license_name: flux-1-dev-non-commercial-license
license_link: https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md

---

# greyscale-tiny-town 
Model trained with [AI Toolkit by Ostris](https://github.com/ostris/ai-toolkit)
<Gallery />

## Trigger words

You should use `greyscale drawing` to trigger the image generation.

## Download model and use it with ComfyUI, AUTOMATIC1111, SD.Next, Invoke AI, etc.

Weights for this model are available in Safetensors format.

[Download](/fffiloni/greyscale-tiny-town/tree/main) them in the Files & versions tab.

## Use it with the [🧨 diffusers library](https://github.com/huggingface/diffusers)

```py
from diffusers import AutoPipelineForText2Image
import torch

pipeline = AutoPipelineForText2Image.from_pretrained('black-forest-labs/FLUX.1-dev', torch_dtype=torch.bfloat16).to('cuda')
pipeline.load_lora_weights('fffiloni/greyscale-tiny-town', weight_name='greyscale-tiny-town.safetensors')
image = pipeline('A person in a bustling cafe, greyscale drawing').images[0]
image.save("my_image.png")
```

For more details, including weighting, merging and fusing LoRAs, check the [documentation on loading LoRAs in diffusers](https://huggingface.co/docs/diffusers/main/en/using-diffusers/loading_adapters)