---
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
language:
- en
tags:
- flux
- diffusers
- lora
base_model: black-forest-labs/FLUX.1-schnell
pipeline_tag: text-to-image
instance_prompt: in a dark fantasy style, grainy
library_name: diffusers
inference:
  parameters:
    width: 1024
    height: 1024
widget:
- text: >-
    This image is a simplified, TSTVCTR vector-style portrait of a person with
    distinct cartoonish features. The man is wearing a gray hat and black-framed
    glasses. He has a thick, neatly trimmed beard and mustache. A playful touch
    is added by a small blue flower with a pink center placed behind his right
    ear. His expression is neutral, with a hint of warmth in his eyes and a
    faint smile. The background is a solid pale yellow, providing a calm,
    minimalistic backdrop that contrasts with the bold, dark colors of his beard
    and glasses. He is dressed in a simple green shirt, which matches the clean,
    modern, and flat art style of the image.  The overall feel of the
    illustration is lighthearted and modern, with geometric lines and a focus on
    smooth, flat shapes. The flower adds a fun and quirky element to the
    otherwise calm and straightforward portrayal.
  output:
    url: images/example_wyd3vx781.png


---

# Tosti vector
Model trained with [AI Toolkit by Ostris](https://github.com/ostris/ai-toolkit) under the [Glif Loradex program](https://huggingface.co/glif-loradex-trainer) by [Glif](https://glif.app) user `tostiok`.


## Trigger words
You should use `in a dark fantasy style, grainy` to trigger the image generation.
<Gallery />


## 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.float16).to('cuda')
pipeline.load_lora_weights('lichorosario/flux-samhtr-remastered', weight_name='lora.safetensors')
image = pipeline('your prompt').images[0]
```



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)