alfredplpl commited on
Commit
ed32bba
1 Parent(s): 4ff3d64

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -2
README.md CHANGED
@@ -12,13 +12,13 @@ license_link: https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICE
12
  1. Download [this model](modern_anime_full.safetensors) .
13
  2. Move the file to ComfyUI/models/unet.
14
  3. Lunch ComfyUI.
15
- 4. Load [the workflow](anime-full-workflow.json).
16
  5. Queue prompt. (trigger words: modern anime style,)
17
  6. Get the following image.
18
  ![example](example.jpg)
19
 
20
  # How to full finetuning
21
- I used sd3 branch on sd-scripts.
22
  I ran the following command:
23
  ```bash
24
  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
 
12
  1. Download [this model](modern_anime_full.safetensors) .
13
  2. Move the file to ComfyUI/models/unet.
14
  3. Lunch ComfyUI.
15
+ 4. Load [this workflow](anime-full-workflow.json).
16
  5. Queue prompt. (trigger words: modern anime style,)
17
  6. Get the following image.
18
  ![example](example.jpg)
19
 
20
  # How to full finetuning
21
+ I used [sd3 branch on sd-scripts](https://github.com/kohya-ss/sd-scripts/tree/sd3?tab=readme-ov-file#flux1-fine-tuning).
22
  I ran the following command:
23
  ```bash
24
  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