FLUX.1-dev-LoRA-Vector-Journey

This is a LoRA (Vector Journey) trained on FLUX.1-dev for blended realistic illustration by Muertu, the front character is in illustration style, while the background is realistic.

Showcases

Trigger words

You should use artistic style blends reality and illustration elements. to trigger the image generation. The recommended scale is 0.8 to 1.0 in diffusers.

Inference

import torch
from diffusers import FluxPipeline

pipe = FluxPipeline.from_pretrained("black-forest-labs/FLUX.1-dev", torch_dtype=torch.bfloat16)
pipe.load_lora_weights("Shakker-Labs/FLUX.1-dev-LoRA-Vector-Journey", weight_name="FLUX-dev-lora-Vector-Journey.safetensors")
pipe.fuse_lora(lora_scale=1.0)
pipe.to("cuda")

prompt = "A cartoon-style Batman, walking on the street, the art style combines reality and illustration elements."

image = pipe(prompt, 
             num_inference_steps=24, 
             guidance_scale=3.5,
             width=768, height=1024,
            ).images[0]
image.save(f"example.png")

Online Inference

You can also download this model at Shakker AI, where we provide an online interface to generate images.

Acknowledgements

This model is trained by our copyrighted users Muertu. We release this model under permissions. The model follows flux-1-dev-non-commercial-license.