---
tags:
- text-to-image
- flux
- lora
- diffusers
language:
- en
pipeline_tag: text-to-image
thumbnail: "https://cdn-uploads.huggingface.co/production/uploads/633792e60578e2c92edffc1e/dNdc3ktAsZVsS6eVsqnJx.webp"
widget:
- text: a pink crystal gem suspended in space, frstingln illustration
  output:
    url: samples/example1.webp
- text: a man wearing a hunters cap frstingln illustration
  output:
    url: samples/example1.webp
- text: a beautiful castle frstingln illustration
  output:
    url: samples/example1.webp
- text: >-
    a small girl with a big grin, confident, on their toes, holding a sign that
    says "I LOVE PROMPTS!" frstingln illustration
  output:
    url: images/content - 2024-08-11T005917.270.jpeg
base_model: black-forest-labs/FLUX.1-dev
instance_prompt: in the style of TOK
license: other
license_name: flux-dev-license
license_link: https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md
---
# Create unique half illustrated, half photo images

<Gallery />

## Model description 

Flux Dev 1 training of my Half Illustration model

I trained this model on Replicate following Lucataco's toolkit here:
https://replicate.com/lucataco/ai-toolkit/readme

You can run this LoRA and try it yourself here (just update the LoRA):
https://replicate.com/lucataco/flux-dev-lora

Let me know your thoughts and have a wonderful day.

## Trigger words

You should use `in the style of TOK` to trigger the image generation. Works best to place the trigger words first. Describe illustrative elements in your scene like clothing or expressive elements.