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.
We will discolse more details about how to prepare training dataset soon!
Showcases
Trigger words
You should use artistic style blends reality and illustration elements. to trigger the image generation. The recommended scale is 1.0 in diffusers, but for ComfyUI or WebUI, the scale may be different.
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-blended-realistic-illustration", weight_name="FLUX-dev-lora-blended_realistic_illustration.safetensors")
pipe.fuse_lora(lora_scale=1.0)
pipe.to("cuda")
prompt = "A peaceful outdoor scene,surrounded by lush green leaves and vibrant vegetation on the stone road. A cartoon style man sits on white clothes,gently caressing two animated cats,one orange and one white. Soft sunlight creates shadows,simple walls and pebble floors create a peaceful atmosphere,blending reality and animation elements,and natural and procedural characters. The artistic style blends elements of reality and illustration."
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 and the generated images are also non commercial.
Downloads last month
491
Model tree for youknownothing/FLUX.1-dev-LoRA-blended-realistic-illustration