FLUX.1-Kontext-dev-LoRA-Flat-Cartoon-Style

This is a flat cartoon style LoRA trained on FLUX.1-Kontext-dev by Mango.

Showcases

Prompt

Convert to a flat cartoon style while keeping the subject unchanged

Prompt

Convert to a flat cartoon style while keeping the subject unchanged

Prompt

Convert to a flat cartoon style while keeping the subject unchanged

Trigger words

You should use Convert to a flat cartoon style while keeping the subject unchanged 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-Flat-Cartoon-Style", weight_name="FLUX-kontext-lora-flat-cartoon-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 to a flat cartoon style while keeping the subject unchanged"

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