45 lines
1.5 KiB
Bash
45 lines
1.5 KiB
Bash
export MODEL_NAME="models/Diffusion_Transformer/Wan2.2-TI2V-5B"
|
|
export DATASET_NAME="datasets/X-Fun-Videos-Demo/"
|
|
export DATASET_META_NAME="datasets/X-Fun-Videos-Demo/metadata_add_width_height.json"
|
|
export TAE_PATH="models/Diffusion_Transformer/taew2_2.safetensors"
|
|
# NCCL_IB_DISABLE=1 and NCCL_P2P_DISABLE=1 are used in multi nodes without RDMA.
|
|
# export NCCL_IB_DISABLE=1
|
|
# export NCCL_P2P_DISABLE=1
|
|
NCCL_DEBUG=INFO
|
|
|
|
accelerate launch --mixed_precision="bf16" scripts/taehv/train_taehv.py \
|
|
--config_path="config/wan2.2/wan_civitai_5b.yaml" \
|
|
--pretrained_model_name_or_path="$MODEL_NAME" \
|
|
--tae_path="$TAE_PATH" \
|
|
--train_data_dir="$DATASET_NAME" \
|
|
--train_data_meta="$DATASET_META_NAME" \
|
|
--fix_sample_size 720 1280 \
|
|
--video_sample_strides 1 2 3 \
|
|
--video_sample_n_frames=25 \
|
|
--validation_n_frames=49 \
|
|
--train_batch_size=1 \
|
|
--gradient_accumulation_steps=1 \
|
|
--dataloader_num_workers=8 \
|
|
--max_train_steps=10000 \
|
|
--checkpointing_steps=1000 \
|
|
--validation_steps=1000 \
|
|
--validation_paths "asset/inpaint_video.mp4" \
|
|
--learning_rate=1e-04 \
|
|
--lr_scheduler="constant_with_warmup" \
|
|
--lr_warmup_steps=200 \
|
|
--latent_loss_weight=1.0 \
|
|
--use_ema \
|
|
--ema_decay=0.999 \
|
|
--seed=42 \
|
|
--output_dir="output_dir_taehv_w2.2" \
|
|
--mixed_precision="bf16" \
|
|
--adam_beta1=0.9 \
|
|
--adam_beta2=0.99 \
|
|
--adam_weight_decay=1e-2 \
|
|
--adam_epsilon=1e-08 \
|
|
--vae_mini_batch=1 \
|
|
--max_grad_norm=1.0 \
|
|
--enable_bucket \
|
|
--trainable_modules "." \
|
|
--resume_from_checkpoint=latest
|