README.md

metadata

license: other
license_name: flux-1-dev-non-commercial-license
license_link: https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.
language:
  - en
pipeline_tag: text-to-image
tags:
  - lora
  - Stable Diffusion
  - image-generation
  - Flux
  - diffusers
base_model: black-forest-labs/FLUX.1-dev

This repository provides a checkpoint with trained LoRA photorealism for FLUX.1-dev model by Black Forest Labs

ComfyUI

See our github for comfy ui workflows.

Training details

XLabs AI team is happy to publish fine-tuning Flux scripts, including:

• LoRA 🔥
• ControlNet 🔥

See our github for train script and train configs.

Training Dataset

Dataset has the following format for the training process:

├── images/
│    ├── 1.png
│    ├── 1.json
│    ├── 2.png
│    ├── 2.json
│    ├── ...

A .json file contains "caption" field with a text prompt.

Inference

python3 demo_lora_inference.py \
    --checkpoint lora.safetensors \
    --prompt " handsome girl in a suit covered with bold tattoos and holding a pistol. Animatrix illustration style, fantasy style, natural photo cinematic"
# Cargar el LoRA con un peso ajustable
def load_lora_weights(pipe, lora_path, scale=0.75):
    lora_weights = torch.load(lora_path)
    # Aplicar el peso del LoRA (influencia)
    pipe.unet.load_attn_procs(lora_weights, scale=scale)

# Generar la imagen con LoRA ajustado
image = pipe(prompt, num_inference_steps=50).images[0]
image.show()

License

lora.safetensors falls under the FLUX.1 [dev] Non-Commercial License