41 lines
1.3 KiB
Bash
41 lines
1.3 KiB
Bash
export MODEL_NAME="models/Diffusion_Transformer/LTX-2"
|
|
export DATASET_NAME="datasets/internal_datasets/"
|
|
export DATASET_META_NAME="datasets/internal_datasets/metadata_control.json"
|
|
# 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/ltx2/train_lora.py \
|
|
--pretrained_model_name_or_path=$MODEL_NAME \
|
|
--train_data_dir=$DATASET_NAME \
|
|
--train_data_meta=$DATASET_META_NAME \
|
|
--image_sample_size=640 \
|
|
--video_sample_size=640 \
|
|
--token_sample_size=640 \
|
|
--video_sample_stride=1 \
|
|
--video_sample_n_frames=81 \
|
|
--train_batch_size=1 \
|
|
--video_repeat=1 \
|
|
--gradient_accumulation_steps=1 \
|
|
--dataloader_num_workers=8 \
|
|
--num_train_epochs=100 \
|
|
--checkpointing_steps=50 \
|
|
--learning_rate=1e-04 \
|
|
--seed=42 \
|
|
--output_dir="output_dir_ltx2_lora" \
|
|
--gradient_checkpointing \
|
|
--mixed_precision="bf16" \
|
|
--adam_weight_decay=3e-2 \
|
|
--adam_epsilon=1e-10 \
|
|
--vae_mini_batch=1 \
|
|
--max_grad_norm=0.05 \
|
|
--random_hw_adapt \
|
|
--training_with_video_token_length \
|
|
--enable_bucket \
|
|
--uniform_sampling \
|
|
--rank=64 \
|
|
--network_alpha=32 \
|
|
--target_name="to_q,to_k,to_v,ff.0,ff.2,audio_ff.0,audio_ff.2" \
|
|
--use_peft_lora \
|
|
--low_vram |