mirror of
https://github.com/modelscope/DiffSynth-Studio.git
synced 2026-03-24 18:28:10 +00:00
21 lines
1.0 KiB
Bash
21 lines
1.0 KiB
Bash
# This script was tested using zero3 and on 8*910B(NPU)
|
|
export PYTORCH_NPU_ALLOC_CONF=expandable_segments:True
|
|
export CPU_AFFINITY_CONF=1
|
|
|
|
accelerate launch --config_file examples/qwen_image/model_training/full/accelerate_config_zero3.yaml examples/qwen_image/model_training/train.py \
|
|
--dataset_base_path data/example_image_dataset \
|
|
--dataset_metadata_path data/example_image_dataset/metadata_qwen_imgae_edit_multi.json \
|
|
--data_file_keys "image,edit_image" \
|
|
--extra_inputs "edit_image" \
|
|
--max_pixels 1048576 \
|
|
--dataset_repeat 50 \
|
|
--model_id_with_origin_paths "Qwen/Qwen-Image-Edit-2509:transformer/diffusion_pytorch_model*.safetensors,Qwen/Qwen-Image:text_encoder/model*.safetensors,Qwen/Qwen-Image:vae/diffusion_pytorch_model.safetensors" \
|
|
--learning_rate 1e-5 \
|
|
--num_epochs 2 \
|
|
--remove_prefix_in_ckpt "pipe.dit." \
|
|
--output_path "./models/train/Qwen-Image-Edit-2509_full" \
|
|
--trainable_models "dit" \
|
|
--use_gradient_checkpointing \
|
|
--find_unused_parameters \
|
|
--initialize_model_on_cpu
|