flux-RealismLora / README.md
Distortion8's picture
Add generated example
28254d7 verified
|
raw
history blame
3.42 kB
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
widget:
  - text: >-
      visualise a photorealistic fictional crime scene image, front view, with
      view of legs in black opaque tights clearly visible, where a wide eyed
      beautiful, pretty, young 18 year old, brunette haired, petite, female
      student who was strangled with a brown leather belt around her neck, and
      lifeless, wearing black opaque pantyhose, who was brutally murdered, brown
      leather belt tied tightly only around her neck, belt not around her waist,
      an aghast facial expression of panic and fear, wearing a uniform navy blue
      suit jacket with college patch, a fitted pure white cotton school uniform
      shirt, very short blue tartan skirt, black opaque tights with knees spread
      apart, black patent loafers, blue tartan tie, disheveled appearance, hair
      tied in a high ponytail, she is lying back dead and lifeless, on the back
      seat in a luxury car, in an alleyway in London, with her head angled
      backwards, mouth is agape, prim looking, makeup with eyelash extensions,
      red lipstick, arms limp and lifeless out at her sides, legs parted, she is
      wearing small pearl earrings, lying back, wide lifeless eyes bulging
      looking up at the ceiling, it’s a sunny day, fictional,
    output:
      url: images/example_692psrbyo.png

Lora Photorealism for Flux

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

Example Picture 1

ComfyUI

See our github for comfy ui workflows. Example Picture 1

Training details

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

  • LoRA πŸ”₯
  • ControlNet πŸ”₯

See our github for train script and train configs.

Training Dataset

Dataset has the following format for the training process:

β”œβ”€β”€ images/
β”‚    β”œβ”€β”€ 1.png
β”‚    β”œβ”€β”€ 1.json
β”‚    β”œβ”€β”€ 2.png
β”‚    β”œβ”€β”€ 2.json
β”‚    β”œβ”€β”€ ...

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"

Example Picture 1

License

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