---
tags:
- text-to-image
- stable-diffusion
- lora
- diffusers
- image-generation
- flux
- safetensors
widget:
- text: >-
    convert this image into sketches
  output:
    url: images/example1.png
- text: >-
    convert this image into sketches
  output:
    url: images/example2.png
- text: convert this image into sketches
  output:
    url: images/example3.png
base_model: black-forest-labs/FLUX.1-Kontext-dev
instance_prompt: convert real photos into sketches, sketch
license: other
license_name: flux-1-dev-non-commercial-license
license_link: >-
  https://huggingface.co/black-forest-labs/FLUX.1-Kontext-dev/blob/main/LICENSE.md
---
# FLUX.1-Kontext-dev-LoRA-Sketch-Style

This is a sketch style LoRA trained on FLUX.1-Kontext-dev by [yao](https://www.liblib.art/userpage/8c2ce72c564613278d3ee381f1d6f201/publish).

## Showcases
<Gallery />


## Trigger words
You should use `convert real photos into sketches`, `sketch` to trigger the image generation.


## Inference

```python
import torch
from diffusers import FluxKontextPipeline
from diffusers.utils import load_image

pipe = FluxKontextPipeline.from_pretrained("black-forest-labs/FLUX.1-Kontext-dev", torch_dtype=torch.bfloat16)
pipe.load_lora_weights("Shakker-Labs/FLUX.1-Kontext-dev-LoRA-Sketch-Style", weight_name="FLUX-kontext-lora-sketch-style.safetensors")
pipe.fuse_lora(lora_scale=1.0)
pipe.to("cuda")

input_image = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/cat.png")
prompt = "convert this image into sketches"

image = pipe(
    image=input_image,
    prompt=prompt, 
    num_inference_steps=24, 
    guidance_scale=2.5,
).images[0]
image.save(f"example.png")
```

## Acknowledgements
This model is trained by our copyrighted users [yao](https://www.liblib.art/userpage/8c2ce72c564613278d3ee381f1d6f201/publish). We release this model under permissions. The model follows [flux-1-dev-non-commercial-license](https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md).