FLUX.1-Kontext-dev-LoRA-Sketch-Style

This is a sketch style LoRA trained on FLUX.1-Kontext-dev by yao.

Showcases

Prompt

convert this image into sketches

Prompt

convert this image into sketches

Prompt

convert this image into sketches

Trigger words

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

Inference

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. We release this model under permissions. The model follows flux-1-dev-non-commercial-license.