---
tags:
- text-to-image
- flux
- lora
- diffusers
- template:sd-lora
- ai-toolkit
widget:
- text: >-
    a painting of a woman with red hair wearing a hat. Her eyes are closed and
    her lips are slightly parted, giving her a peaceful and serene look. The
    background is a soft, muted color, allowing the woman to stand out in the
    painting. in the style of TOK
  output:
    url: samples/1739547289701__000001000_0.jpg
- text: a woman with red hair wearing a blue hat. in the style of TOK
  output:
    url: samples/1739547318618__000001000_1.jpg
- text: >-
    a woman with a bow on her head. She has a gentle expression on her face and
    her eyes are looking off to the side. in the style of TOK
  output:
    url: samples/1739547347440__000001000_2.jpg
- text: a man with blue hair wearing a black hat. in the style of TOK
  output:
    url: images/example_sxso69ocl.png
- text: >-
    a painting of a man, man wearing a red cap. He as black hair and he is
    wearing a yellow coat. in the style of TOK
  output:
    url: images/example_a3qelny6z.png
- text: a man with blond short hair. looking at the camera. in the style of TOK
  output:
    url: images/example_wbm38ge8x.png
- text: Portrait of Godzilla. in the style of TOK
  output:
    url: images/example_tmxj0w0y0.png
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

---

# carbo-800
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/carbo-800/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/carbo-800', weight_name='carbo-800.safetensors')
image = pipeline('a painting of a woman with red hair wearing a hat. Her eyes are closed and her lips are slightly parted, giving her a peaceful and serene look. The background is a soft, muted color, allowing the woman to stand out in the painting. 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)