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

Prompt

A cartoon style couple takes a selfie in front of an Egyptian pyramid, which is composed of a man and a woman, both wearing sunglasses. Men wear blue shirts, jeans, and white shoes, while women wear yellow hats, blue jackets, white tops, orange dresses, and pink sneakers. Sand and a group of tourists in the distance. Integrating reality and cartoon elements.,

Prompt

In a picturesque village, a narrow cobblestone street with rustic stone buildings, colorful blinds, and lush green spaces, a cartoon man drawn with simple lines and solid colors stands in the foreground, wearing a red shirt, beige work pants, and brown shoes, carrying a strap on his shoulder. The scene features warm and enticing colors, a pleasant fusion of nature and architecture, and the camera's perspective on the street clearly shows the charming and quaint environment., Integrating elements of reality and cartoon.

Prompt

A cartoon-style boy playing games in his living room, artistic style blends reality and illustration elements.

Prompt

A cartoon-style pianist is playing in the Golden Hall, and artistic style blends reality and illustration elements.

Prompt

A cartoon-style basketball player, dunking on the NBA court, artistic style blends reality and illustration elements.

Prompt

A cartoon-style male singer, Concert, artistic style blends reality and illustration elements.

Prompt

A cartoon-style Donald Duck, walking on the street, the art style combines reality and illustration elements.,

Prompt

A cartoon-style Morty, walking on the street, the art style combines reality and illustration elements.,

Prompt

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

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.