README.md

---
tags:
- text-to-image
- flux
- lora
- diffusers
- template:sd-lora
- ai-toolkit
base_model: black-forest-labs/FLUX.1-dev
instance_prompt: in the style of TOK
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
widget:
- text: a coi fish. in the style of TOK
  output:
    url: images/example_3buowzz1z.png
- text: a panda on eucalyptus branch, sleeping. in the style of TOK
  output:
    url: images/example_7wb9y3owz.png
- text: a boy snowboarding. in the style of TOK
  output:
    url: images/example_0s2fzx9kd.png
- text: a man tennis player playing tennis on tennis court. in the style of TOK
  output:
    url: images/example_u2i3ke60c.png
- text: playing curling. in the style of TOK
  output:
    url: images/example_is3gxmf20.png
- text: a man playing billard. in the style of TOK
  output:
    url: images/example_9j8fzdhey.png
- text: a bartender shaking a cocktail. in the style of TOK
  output:
    url: images/example_s2xhwvsmw.png
- text: >-
    old fierce pirate holding a shovel digging to find a treasure. in the style
    of TOK
  output:
    url: images/example_afdbsemxc.png
- text: >-
    a picturesque village nestled amidst rolling hills and colorful meadows. We
    see quaint houses with smoke curling from chimneys and children playing in
    the streets.. in the style of TOK
  output:
    url: images/example_mu38m53gb.png
- text: a panda playing football. in the style of TOK
  output:
    url: images/example_om6c5d6bt.png
- text: an illustration of a chameleon on a old wall. in the style of TOK
  output:
    url: images/example_8dc7wfv48.png

---

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

## Trigger words

You should use `in the style of TOK` 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/sweet-brush/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/sweet-brush', weight_name='sweet-brush.safetensors')
image = pipeline('A person in a bustling cafe. in the style of TOK').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)