mirror of
https://github.com/modelscope/DiffSynth-Studio.git
synced 2026-03-25 18:58:11 +00:00
41 lines
2.0 KiB
Bash
41 lines
2.0 KiB
Bash
# Due to memory limitations, split training is required to train the model on NPU
|
|
export PYTORCH_NPU_ALLOC_CONF=expandable_segments:True
|
|
export CPU_AFFINITY_CONF=1
|
|
|
|
modelscope download --dataset DiffSynth-Studio/diffsynth_example_dataset --include "qwen_image/Qwen-Image-Edit-2509/*" --local_dir ./data/diffsynth_example_dataset
|
|
|
|
accelerate launch examples/qwen_image/model_training/train.py \
|
|
--dataset_base_path data/diffsynth_example_dataset/qwen_image/Qwen-Image-Edit-2509 \
|
|
--dataset_metadata_path data/diffsynth_example_dataset/qwen_image/Qwen-Image-Edit-2509/metadata.json \
|
|
--max_pixels 1048576 \
|
|
--dataset_repeat 1 \
|
|
--model_id_with_origin_paths "Qwen/Qwen-Image-Edit-2509:text_encoder/model*.safetensors,Qwen/Qwen-Image-Edit-2509:vae/diffusion_pytorch_model.safetensors" \
|
|
--learning_rate 1e-4 \
|
|
--num_epochs 5 \
|
|
--remove_prefix_in_ckpt "pipe.dit." \
|
|
--output_path "./models/train/Qwen-Image-Edit-2509-LoRA-splited-cache" \
|
|
--lora_base_model "dit" \
|
|
--lora_target_modules "to_q,to_k,to_v,add_q_proj,add_k_proj,add_v_proj,to_out.0,to_add_out,img_mlp.net.2,img_mod.1,txt_mlp.net.2,txt_mod.1" \
|
|
--lora_rank 32 \
|
|
--use_gradient_checkpointing \
|
|
--dataset_num_workers 8 \
|
|
--find_unused_parameters \
|
|
--task "sft:data_process"
|
|
|
|
accelerate launch examples/qwen_image/model_training/train.py \
|
|
--dataset_base_path "./models/train/Qwen-Image-Edit-2509-LoRA-splited-cache" \
|
|
--max_pixels 1048576 \
|
|
--dataset_repeat 50 \
|
|
--model_id_with_origin_paths "Qwen/Qwen-Image-Edit-2509:transformer/diffusion_pytorch_model*.safetensors" \
|
|
--learning_rate 1e-4 \
|
|
--num_epochs 5 \
|
|
--remove_prefix_in_ckpt "pipe.dit." \
|
|
--output_path "./models/train/Qwen-Image-Edit-2509-LoRA-splited" \
|
|
--lora_base_model "dit" \
|
|
--lora_target_modules "to_q,to_k,to_v,add_q_proj,add_k_proj,add_v_proj,to_out.0,to_add_out,img_mlp.net.2,img_mod.1,txt_mlp.net.2,txt_mod.1" \
|
|
--lora_rank 32 \
|
|
--use_gradient_checkpointing \
|
|
--dataset_num_workers 8 \
|
|
--find_unused_parameters \
|
|
--task "sft:train"
|