theluyuan/DiffSynth-Studio
1
0
Fork 0
mirror of https://github.com/modelscope/DiffSynth-Studio.git synced 2026-03-22 08:40:47 +00:00
Code Issues Packages Projects Releases Wiki Activity

Docs:Supplement NPU training script samples and documentation instruction

Browse Source
This commit is contained in:
feng0w0
2025-12-30 19:58:47 +08:00
parent 8f1d10fb43
commit 507e7e5d36
14 changed files with 322 additions and 9 deletions
Download Patch File Download Diff File Expand all files Collapse all files

17
examples/flux/model_training/special/npu_scripts/FLUX.1-Kontext-dev-NPU.sh Normal file
View File

@@ -0,0 +1,17 @@
export PYTORCH_NPU_ALLOC_CONF=expandable_segments:True
export CPU_AFFINITY_CONF=1
accelerate launch --config_file examples/flux/model_training/full/accelerate_config.yaml examples/flux/model_training/train.py \
--dataset_base_path data/example_image_dataset \
--dataset_metadata_path data/example_image_dataset/metadata_kontext.csv \
--data_file_keys "image,kontext_images" \
--max_pixels 1048576 \
--dataset_repeat 400 \
--model_id_with_origin_paths "black-forest-labs/FLUX.1-Kontext-dev:flux1-kontext-dev.safetensors,black-forest-labs/FLUX.1-dev:text_encoder/model.safetensors,black-forest-labs/FLUX.1-dev:text_encoder_2/*.safetensors,black-forest-labs/FLUX.1-dev:ae.safetensors" \
--learning_rate 1e-5 \
--num_epochs 1 \
--remove_prefix_in_ckpt "pipe.dit." \
--output_path "./models/train/FLUX.1-Kontext-dev_full" \
--trainable_models "dit" \
--extra_inputs "kontext_images" \
--use_gradient_checkpointing

15
examples/flux/model_training/special/npu_scripts/FLUX.1-dev-NPU.sh Normal file
View File

@@ -0,0 +1,15 @@
export PYTORCH_NPU_ALLOC_CONF=expandable_segments:True
export CPU_AFFINITY_CONF=1
accelerate launch --config_file examples/flux/model_training/full/accelerate_config.yaml examples/flux/model_training/train.py \
--dataset_base_path data/example_image_dataset \
--dataset_metadata_path data/example_image_dataset/metadata.csv \
--max_pixels 1048576 \
--dataset_repeat 400 \
--model_id_with_origin_paths "black-forest-labs/FLUX.1-dev:flux1-dev.safetensors,black-forest-labs/FLUX.1-dev:text_encoder/model.safetensors,black-forest-labs/FLUX.1-dev:text_encoder_2/*.safetensors,black-forest-labs/FLUX.1-dev:ae.safetensors" \
--learning_rate 1e-5 \
--num_epochs 1 \
--remove_prefix_in_ckpt "pipe.dit." \
--output_path "./models/train/FLUX.1-dev_full" \
--trainable_models "dit" \
--use_gradient_checkpointing

35
examples/flux2/model_training/special/npu_scripts/FLUX.2-dev-NPU.sh Normal file
View File

@@ -0,0 +1,35 @@
export PYTORCH_NPU_ALLOC_CONF=expandable_segments:True
export CPU_AFFINITY_CONF=1
accelerate launch examples/flux2/model_training/train.py \
--dataset_base_path data/example_image_dataset \
--dataset_metadata_path data/example_image_dataset/metadata.csv \
--max_pixels 1048576 \
--dataset_repeat 1 \
--model_id_with_origin_paths "black-forest-labs/FLUX.2-dev:text_encoder/*.safetensors,black-forest-labs/FLUX.2-dev:vae/diffusion_pytorch_model.safetensors" \
--learning_rate 1e-4 \
--num_epochs 5 \
--remove_prefix_in_ckpt "pipe.dit." \
--output_path "./models/train/FLUX.2-dev-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_qkv_mlp_proj,to_out.0,to_add_out,linear_in,linear_out,single_transformer_blocks.0.attn.to_out,single_transformer_blocks.1.attn.to_out,single_transformer_blocks.2.attn.to_out,single_transformer_blocks.3.attn.to_out,single_transformer_blocks.4.attn.to_out,single_transformer_blocks.5.attn.to_out,single_transformer_blocks.6.attn.to_out,single_transformer_blocks.7.attn.to_out,single_transformer_blocks.8.attn.to_out,single_transformer_blocks.9.attn.to_out,single_transformer_blocks.10.attn.to_out,single_transformer_blocks.11.attn.to_out,single_transformer_blocks.12.attn.to_out,single_transformer_blocks.13.attn.to_out,single_transformer_blocks.14.attn.to_out,single_transformer_blocks.15.attn.to_out,single_transformer_blocks.16.attn.to_out,single_transformer_blocks.17.attn.to_out,single_transformer_blocks.18.attn.to_out,single_transformer_blocks.19.attn.to_out,single_transformer_blocks.20.attn.to_out,single_transformer_blocks.21.attn.to_out,single_transformer_blocks.22.attn.to_out,single_transformer_blocks.23.attn.to_out,single_transformer_blocks.24.attn.to_out,single_transformer_blocks.25.attn.to_out,single_transformer_blocks.26.attn.to_out,single_transformer_blocks.27.attn.to_out,single_transformer_blocks.28.attn.to_out,single_transformer_blocks.29.attn.to_out,single_transformer_blocks.30.attn.to_out,single_transformer_blocks.31.attn.to_out,single_transformer_blocks.32.attn.to_out,single_transformer_blocks.33.attn.to_out,single_transformer_blocks.34.attn.to_out,single_transformer_blocks.35.attn.to_out,single_transformer_blocks.36.attn.to_out,single_transformer_blocks.37.attn.to_out,single_transformer_blocks.38.attn.to_out,single_transformer_blocks.39.attn.to_out,single_transformer_blocks.40.attn.to_out,single_transformer_blocks.41.attn.to_out,single_transformer_blocks.42.attn.to_out,single_transformer_blocks.43.attn.to_out,single_transformer_blocks.44.attn.to_out,single_transformer_blocks.45.attn.to_out,single_transformer_blocks.46.attn.to_out,single_transformer_blocks.47.attn.to_out" \
--lora_rank 32 \
--use_gradient_checkpointing \
--dataset_num_workers 8 \
--task "sft:data_process"
accelerate launch examples/flux2/model_training/train.py \
--dataset_base_path "./models/train/FLUX.2-dev-LoRA-splited-cache" \
--max_pixels 1048576 \
--dataset_repeat 50 \
--model_id_with_origin_paths "black-forest-labs/FLUX.2-dev:transformer/*.safetensors" \
--learning_rate 1e-4 \
--num_epochs 5 \
--remove_prefix_in_ckpt "pipe.dit." \
--output_path "./models/train/FLUX.2-dev-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_qkv_mlp_proj,to_out.0,to_add_out,linear_in,linear_out,single_transformer_blocks.0.attn.to_out,single_transformer_blocks.1.attn.to_out,single_transformer_blocks.2.attn.to_out,single_transformer_blocks.3.attn.to_out,single_transformer_blocks.4.attn.to_out,single_transformer_blocks.5.attn.to_out,single_transformer_blocks.6.attn.to_out,single_transformer_blocks.7.attn.to_out,single_transformer_blocks.8.attn.to_out,single_transformer_blocks.9.attn.to_out,single_transformer_blocks.10.attn.to_out,single_transformer_blocks.11.attn.to_out,single_transformer_blocks.12.attn.to_out,single_transformer_blocks.13.attn.to_out,single_transformer_blocks.14.attn.to_out,single_transformer_blocks.15.attn.to_out,single_transformer_blocks.16.attn.to_out,single_transformer_blocks.17.attn.to_out,single_transformer_blocks.18.attn.to_out,single_transformer_blocks.19.attn.to_out,single_transformer_blocks.20.attn.to_out,single_transformer_blocks.21.attn.to_out,single_transformer_blocks.22.attn.to_out,single_transformer_blocks.23.attn.to_out,single_transformer_blocks.24.attn.to_out,single_transformer_blocks.25.attn.to_out,single_transformer_blocks.26.attn.to_out,single_transformer_blocks.27.attn.to_out,single_transformer_blocks.28.attn.to_out,single_transformer_blocks.29.attn.to_out,single_transformer_blocks.30.attn.to_out,single_transformer_blocks.31.attn.to_out,single_transformer_blocks.32.attn.to_out,single_transformer_blocks.33.attn.to_out,single_transformer_blocks.34.attn.to_out,single_transformer_blocks.35.attn.to_out,single_transformer_blocks.36.attn.to_out,single_transformer_blocks.37.attn.to_out,single_transformer_blocks.38.attn.to_out,single_transformer_blocks.39.attn.to_out,single_transformer_blocks.40.attn.to_out,single_transformer_blocks.41.attn.to_out,single_transformer_blocks.42.attn.to_out,single_transformer_blocks.43.attn.to_out,single_transformer_blocks.44.attn.to_out,single_transformer_blocks.45.attn.to_out,single_transformer_blocks.46.attn.to_out,single_transformer_blocks.47.attn.to_out" \
--lora_rank 32 \
--use_gradient_checkpointing \
--dataset_num_workers 8 \
--task "sft:train"

38
examples/qwen_image/model_training/special/npu_scripts/Qwen-Image-Edit-2509-LoRA-NPU.sh Normal file
View File

@@ -0,0 +1,38 @@
# 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
accelerate launch examples/qwen_image/model_training/train.py \
--dataset_base_path data/example_image_dataset \
--dataset_metadata_path data/example_image_dataset/metadata.csv \
--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-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"

38
examples/qwen_image/model_training/special/npu_scripts/Qwen-Image-LoRA-NPU.sh Normal file
View File

@@ -0,0 +1,38 @@
# 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
accelerate launch examples/qwen_image/model_training/train.py \
--dataset_base_path data/example_image_dataset \
--dataset_metadata_path data/example_image_dataset/metadata.csv \
--max_pixels 1048576 \
--dataset_repeat 1 \
--model_id_with_origin_paths "Qwen/Qwen-Image:text_encoder/model*.safetensors,Qwen/Qwen-Image:vae/diffusion_pytorch_model.safetensors" \
--learning_rate 1e-4 \
--num_epochs 5 \
--remove_prefix_in_ckpt "pipe.dit." \
--output_path "./models/train/Qwen-Image-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-LoRA-splited-cache" \
--max_pixels 1048576 \
--dataset_repeat 50 \
--model_id_with_origin_paths "Qwen/Qwen-Image:transformer/diffusion_pytorch_model*.safetensors" \
--learning_rate 1e-4 \
--num_epochs 5 \
--remove_prefix_in_ckpt "pipe.dit." \
--output_path "./models/train/Qwen-Image-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"

16
examples/wanvideo/model_training/special/npu_scripts/Wan2.1-T2V-14B-NPU.sh Normal file
View File

@@ -0,0 +1,16 @@
export PYTORCH_NPU_ALLOC_CONF=expandable_segments:True
export CPU_AFFINITY_CONF=1
accelerate launch --config_file examples/wanvideo/model_training/full/accelerate_config_14B.yaml examples/wanvideo/model_training/train.py \
--dataset_base_path data/example_video_dataset \
--dataset_metadata_path data/example_video_dataset/metadata.csv \
--height 480 \
--width 832 \
--dataset_repeat 100 \
--model_id_with_origin_paths "Wan-AI/Wan2.1-T2V-14B:diffusion_pytorch_model*.safetensors,Wan-AI/Wan2.1-T2V-14B:models_t5_umt5-xxl-enc-bf16.pth,Wan-AI/Wan2.1-T2V-14B:Wan2.1_VAE.pth" \
--learning_rate 1e-5 \
--num_epochs 2 \
--remove_prefix_in_ckpt "pipe.dit." \
--output_path "./models/train/Wan2.1-T2V-14B_full" \
--trainable_models "dit" \
--initialize_model_on_cpu

38
examples/wanvideo/model_training/special/npu_scripts/Wan2.2-T2V-A14B-NPU.sh Normal file
View File

@@ -0,0 +1,38 @@
export PYTORCH_NPU_ALLOC_CONF=expandable_segments:True
export CPU_AFFINITY_CONF=1
accelerate launch --config_file examples/wanvideo/model_training/full/accelerate_config_14B.yaml examples/wanvideo/model_training/train.py \
--dataset_base_path data/example_video_dataset \
--dataset_metadata_path data/example_video_dataset/metadata.csv \
--height 480 \
--width 832 \
--num_frames 49 \
--dataset_repeat 100 \
--model_id_with_origin_paths "Wan-AI/Wan2.2-T2V-A14B:high_noise_model/diffusion_pytorch_model*.safetensors,Wan-AI/Wan2.2-T2V-A14B:models_t5_umt5-xxl-enc-bf16.pth,Wan-AI/Wan2.2-T2V-A14B:Wan2.1_VAE.pth" \
--learning_rate 1e-5 \
--num_epochs 2 \
--remove_prefix_in_ckpt "pipe.dit." \
--output_path "./models/train/Wan2.2-T2V-A14B_high_noise_full" \
--trainable_models "dit" \
--max_timestep_boundary 0.417 \
--min_timestep_boundary 0 \
--initialize_model_on_cpu
# boundary corresponds to timesteps [875, 1000]
accelerate launch --config_file examples/wanvideo/model_training/full/accelerate_config_14B.yaml examples/wanvideo/model_training/train.py \
--dataset_base_path data/example_video_dataset \
--dataset_metadata_path data/example_video_dataset/metadata.csv \
--height 480 \
--width 832 \
--num_frames 49 \
--dataset_repeat 100 \
--model_id_with_origin_paths "Wan-AI/Wan2.2-T2V-A14B:low_noise_model/diffusion_pytorch_model*.safetensors,Wan-AI/Wan2.2-T2V-A14B:models_t5_umt5-xxl-enc-bf16.pth,Wan-AI/Wan2.2-T2V-A14B:Wan2.1_VAE.pth" \
--learning_rate 1e-5 \
--num_epochs 2 \
--remove_prefix_in_ckpt "pipe.dit." \
--output_path "./models/train/Wan2.2-T2V-A14B_low_noise_full" \
--trainable_models "dit" \
--max_timestep_boundary 1 \
--min_timestep_boundary 0.417 \
--initialize_model_on_cpu
# boundary corresponds to timesteps [0, 875)

45
examples/wanvideo/model_training/special/npu_scripts/Wan2.2-VACE-Fun-A14B-NPU.sh Normal file
View File

@@ -0,0 +1,45 @@
export PYTORCH_NPU_ALLOC_CONF=expandable_segments:True
export CPU_AFFINITY_CONF=1
accelerate launch --config_file examples/wanvideo/model_training/full/accelerate_config_14B.yaml examples/wanvideo/model_training/train.py \
--dataset_base_path data/example_video_dataset \
--dataset_metadata_path data/example_video_dataset/metadata_vace.csv \
--data_file_keys "video,vace_video,vace_reference_image" \
--height 480 \
--width 832 \
--num_frames 17 \
--dataset_repeat 100 \
--model_id_with_origin_paths "PAI/Wan2.2-VACE-Fun-A14B:high_noise_model/diffusion_pytorch_model*.safetensors,PAI/Wan2.2-VACE-Fun-A14B:models_t5_umt5-xxl-enc-bf16.pth,PAI/Wan2.2-VACE-Fun-A14B:Wan2.1_VAE.pth" \
--learning_rate 1e-4 \
--num_epochs 2 \
--remove_prefix_in_ckpt "pipe.vace." \
--output_path "./models/train/Wan2.2-VACE-Fun-A14B_high_noise_full" \
--trainable_models "vace" \
--extra_inputs "vace_video,vace_reference_image" \
--use_gradient_checkpointing_offload \
--max_timestep_boundary 0.358 \
--min_timestep_boundary 0 \
--initialize_model_on_cpu
# boundary corresponds to timesteps [900, 1000]
accelerate launch --config_file examples/wanvideo/model_training/full/accelerate_config_14B.yaml examples/wanvideo/model_training/train.py \
--dataset_base_path data/example_video_dataset \
--dataset_metadata_path data/example_video_dataset/metadata_vace.csv \
--data_file_keys "video,vace_video,vace_reference_image" \
--height 480 \
--width 832 \
--num_frames 17 \
--dataset_repeat 100 \
--model_id_with_origin_paths "PAI/Wan2.2-VACE-Fun-A14B:low_noise_model/diffusion_pytorch_model*.safetensors,PAI/Wan2.2-VACE-Fun-A14B:models_t5_umt5-xxl-enc-bf16.pth,PAI/Wan2.2-VACE-Fun-A14B:Wan2.1_VAE.pth" \
--learning_rate 1e-4 \
--num_epochs 2 \
--remove_prefix_in_ckpt "pipe.vace." \
--output_path "./models/train/Wan2.2-VACE-Fun-A14B_low_noise_full" \
--trainable_models "vace" \
--extra_inputs "vace_video,vace_reference_image" \
--use_gradient_checkpointing_offload \
--max_timestep_boundary 1 \
--min_timestep_boundary 0.358 \
--initialize_model_on_cpu
# boundary corresponds to timesteps [0, 900]

17
examples/z_image/model_training/special/npu_scripts/Z-Image-Turbo-NPU.sh Normal file
View File

@@ -0,0 +1,17 @@
# This example is tested on 8*A100
export PYTORCH_NPU_ALLOC_CONF=expandable_segments:True
export CPU_AFFINITY_CONF=1
accelerate launch --config_file examples/z_image/model_training/full/accelerate_config.yaml examples/z_image/model_training/train.py \
--dataset_base_path data/example_image_dataset \
--dataset_metadata_path data/example_image_dataset/metadata.csv \
--max_pixels 1048576 \
--dataset_repeat 400 \
--model_id_with_origin_paths "Tongyi-MAI/Z-Image-Turbo:transformer/*.safetensors,Tongyi-MAI/Z-Image-Turbo:text_encoder/*.safetensors,Tongyi-MAI/Z-Image-Turbo:vae/diffusion_pytorch_model.safetensors" \
--learning_rate 1e-5 \
--num_epochs 2 \
--remove_prefix_in_ckpt "pipe.dit." \
--output_path "./models/train/Z-Image-Turbo_full" \
--trainable_models "dit" \
--use_gradient_checkpointing \
--dataset_num_workers 8