FLUX.1-dev-LoRA-add-details

This is a LoRA trained on FLUX.1-dev for enhancing realism and details, achieveing natural skin. Made by Dote.

Showcases

Trigger words

There is no essential trigger words. The recommended scale is 1.0. The scale be can be negative.

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.1-dev-LoRA-add-details.safetensors")
pipe.fuse_lora(lora_scale=1.0)
pipe.to("cuda")

prompt = "A beautiful woman, flim rendering"

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 Dote. We release this model under permissions.