alfredplpl/flux.1-dev-modern-anime-full

Modern Anime for FLUX.1 dev

FLUX.1 dev Modern Anime is an anime model by full finetuning. We can load this model by ComfyUI.

Usage

• ComfyUI (Recommended)

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

• ComfyUI (GGUF)

1. Download this 4bit model or this 8bit model.
2. Move the file to ComfyUI/models/unet.
3. Install ComfyUI Custom Node for GGUF.
4. Lunch ComfyUI.
5. Create workflow.
6. Queue prompt. (trigger words: modern anime style,)

How to full finetuning

I used sd3 branch on sd-scripts. I ran the following command:

accelerate launch --num_cpu_threads_per_process 1 flux_train.py --pretrained_model_name_or_path 'flux/flux1-dev.safetensors'  --clip_l 'flux/clip_l.safetensors'  --t5xxl 'flux/t5xxl_fp16.safetensors'  --ae '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 --learning_rate 5e-6 --optimizer_type adafactor --optimizer_args "relative_step=False" "scale_parameter=False" "warmup_init=False"  --cache_text_encoder_outputs --max_train_epochs 10 --save_every_n_epochs 5 --dataset_config modern_anme_full.toml --output_dir flux --output_name modern_anime_full --timestep_sampling sigmoid  --model_prediction_type raw --guidance_scale 1.0 --full_bf16 --max_bucket_reso 2048 --min_bucket_reso 512 --apply_t5_attn_mask --mixed_precision bf16 --cache_text_encoder_outputs_to_disk --cache_latents_to_disk --blockwise_fused_optimizer

[general]
enable_bucket = true

[[datasets]]
resolution = 1024
batch_size = 4

  [[datasets.subsets]]
  image_dir = 'modern_anime'
  metadata_file = 'modern_anime.json'