README.md

metadata

license: other
license_name: flux-1-dev-non-commercial-license
license_link: LICENSE.md
language:
  - en
tags:
  - art

Modern Anime LoRA Adapter for FLUX.1 dev

Usage

• ComfyUI

1. Download lora.safetensors.
2. Move the file to ComfyUI/models/loras.
3. Lunch ComfyUI.
4. Load the workflow.
5. Queue prompt. (trigger words: modern anime style,)
6. Get the following image.

How to make

I used sd-scripts. The parameters is as follows:

accelerate launch --num_cpu_threads_per_process 1 flux_train_network.py --pretrained_model_name_or_path '/mnt/NVM/flux/flux1-dev.safetensors'  --clip_l '/mnt/NVM/flux/clip_l.safetensors'  --t5xxl '/mnt/NVM/flux/t5xxl_fp16.safetensors'  --ae '/mnt/NVM/flux/ae.safetensors'  --cache_latents --save_model_as safetensors --sdpa --persistent_data_loader_workers --max_data_loader_n_workers 2 --seed 42 --gradient_checkpointing --save_precision bf16 --network_module networks.lora_flux --network_dim 16 --network_alpha 16 --optimizer_type adamw8bit --learning_rate 1e-3 --network_train_unet_only --cache_text_encoder_outputs --cache_text_encoder_outputs --max_train_epochs 3 --save_every_n_epochs 1 --dataset_config flux_lora.toml --output_dir /mnt/NVM/flux --output_name flux_lora --timestep_sampling sigmoid --model_prediction_type raw --discrete_flow_shift 3.0 --guidance_scale 1.0 --loss_type l2 --mixed_precision bf16 --full_bf16 --max_bucket_reso 2048 --min_bucket_reso 512 --apply_t5_attn_mask --lr_scheduler cosine --lr_warmup_steps 10