Training details. XLabs AI team is happy to publish fune-tuning Flux scripts, including:

• LoRA

• ControlNet

See their 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.

Thank https://civitai.com/user/dobrosketchkun and https://civitai.com/user/sadxzero for datasets for loras

furry_lora

python3 main.py

--prompt "Female furry Pixie with text 'hello world'"

--lora_repo_id XLabs-AI/flux-furry-lora --lora_name furry_lora.safetensors --device cuda --offload --use_lora

--model_type flux-dev-fp8 --width 1024 --height 1024

--timestep_to_start_cfg 1 --num_steps 25 --true_gs 3.5 --guidance 4

mjv6_lora

python3 main.py

--prompt "A handsome man in a suit, 25 years old, cool, futuristic"

--lora_repo_id XLabs-AI/flux-lora-collection --lora_name mjv6_lora.safetensors

--device cuda:4 --offload --use_lora --model_type flux-dev-fp8 --width 1024 --height 1024

anime_lora

python3 main.py

--prompt "A cute corgi lives in a house made out of sushi, anime"

--lora_repo_id XLabs-AI/flux-lora-collection --lora_name anime_lora.safetensors

--device cuda --offload --use_lora --model_type flux-dev-fp8 --width 1024 --height 1024

art_lora

python3 main.py

--prompt "white rabbit in blue dress and hat holding bow and arrow, art"

--lora_repo_id XLabs-AI/flux-lora-collection --lora_name art_lora.safetensors

--device cuda --offload --use_lora --model_type flux-dev-fp8 --width 1024 --height 1024

License

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