by XLabs-AI
Open source · 13k downloads · 1217 likes
Flux RealismLora is an AI model specialized in generating ultra-realistic photographic images from text prompts. It is a LoRA (Low-Rank Adaptation) trained on the FLUX.1-dev model, optimized to produce visual renders of near-professional photography quality. This model excels particularly in portraits, landscapes, and detailed scenes, delivering striking natural textures, lighting, and details. It is ideal for artists, designers, or content creators seeking realistic images without photography or retouching skills. Its strength lies in its ability to transform text descriptions into believable visuals while maintaining great flexibility in use.
This repository provides a checkpoint with trained LoRA photorealism for FLUX.1-dev model by Black Forest Labs

See our github for comfy ui workflows.

XLabs AI team is happy to publish fine-tuning Flux scripts, including:
See our github for train script and train configs.
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.
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"

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