diff --git a/examples/wanvideo/model_training/full/Wan2.1-VACE-1.3B-Preview.sh b/examples/wanvideo/model_training/full/Wan2.1-VACE-1.3B-Preview.sh
index b348874..19b6ecb 100644
--- a/examples/wanvideo/model_training/full/Wan2.1-VACE-1.3B-Preview.sh
+++ b/examples/wanvideo/model_training/full/Wan2.1-VACE-1.3B-Preview.sh
@@ -7,10 +7,11 @@ accelerate launch examples/wanvideo/model_training/train.py \
   --num_frames 49 \
   --dataset_repeat 100 \
   --model_id_with_origin_paths "iic/VACE-Wan2.1-1.3B-Preview:diffusion_pytorch_model*.safetensors,iic/VACE-Wan2.1-1.3B-Preview:models_t5_umt5-xxl-enc-bf16.pth,iic/VACE-Wan2.1-1.3B-Preview:Wan2.1_VAE.pth" \
-  --learning_rate 1e-4 \
+  --learning_rate 5e-5 \
   --num_epochs 2 \
   --remove_prefix_in_ckpt "pipe.vace." \
   --output_path "./models/train/Wan2.1-VACE-1.3B-Preview_full" \
   --trainable_models "vace" \
   --extra_inputs "vace_video,vace_reference_image" \
-  --use_gradient_checkpointing_offload
\ No newline at end of file
+  --use_gradient_checkpointing_offload
+# The learning rate is kept consistent with the settings in the original paper
\ No newline at end of file
diff --git a/examples/wanvideo/model_training/full/Wan2.1-VACE-1.3B.sh b/examples/wanvideo/model_training/full/Wan2.1-VACE-1.3B.sh
index 763252e..f9768c6 100644
--- a/examples/wanvideo/model_training/full/Wan2.1-VACE-1.3B.sh
+++ b/examples/wanvideo/model_training/full/Wan2.1-VACE-1.3B.sh
@@ -7,10 +7,11 @@ accelerate launch examples/wanvideo/model_training/train.py \
   --num_frames 49 \
   --dataset_repeat 100 \
   --model_id_with_origin_paths "Wan-AI/Wan2.1-VACE-1.3B:diffusion_pytorch_model*.safetensors,Wan-AI/Wan2.1-VACE-1.3B:models_t5_umt5-xxl-enc-bf16.pth,Wan-AI/Wan2.1-VACE-1.3B:Wan2.1_VAE.pth" \
-  --learning_rate 1e-4 \
+  --learning_rate 5e-5 \
   --num_epochs 2 \
   --remove_prefix_in_ckpt "pipe.vace." \
   --output_path "./models/train/Wan2.1-VACE-1.3B_full" \
   --trainable_models "vace" \
   --extra_inputs "vace_video,vace_reference_image" \
-  --use_gradient_checkpointing_offload
\ No newline at end of file
+  --use_gradient_checkpointing_offload
+# The learning rate is kept consistent with the settings in the original paper
\ No newline at end of file
diff --git a/examples/wanvideo/model_training/full/Wan2.1-VACE-14B.sh b/examples/wanvideo/model_training/full/Wan2.1-VACE-14B.sh
index c549263..401a647 100644
--- a/examples/wanvideo/model_training/full/Wan2.1-VACE-14B.sh
+++ b/examples/wanvideo/model_training/full/Wan2.1-VACE-14B.sh
@@ -7,10 +7,11 @@ accelerate launch --config_file examples/wanvideo/model_training/full/accelerate
   --num_frames 17 \
   --dataset_repeat 100 \
   --model_id_with_origin_paths "Wan-AI/Wan2.1-VACE-14B:diffusion_pytorch_model*.safetensors,Wan-AI/Wan2.1-VACE-14B:models_t5_umt5-xxl-enc-bf16.pth,Wan-AI/Wan2.1-VACE-14B:Wan2.1_VAE.pth" \
-  --learning_rate 1e-4 \
+  --learning_rate 5e-5 \
   --num_epochs 2 \
   --remove_prefix_in_ckpt "pipe.vace." \
   --output_path "./models/train/Wan2.1-VACE-14B_full" \
   --trainable_models "vace" \
   --extra_inputs "vace_video,vace_reference_image" \
-  --use_gradient_checkpointing_offload
\ No newline at end of file
+  --use_gradient_checkpointing_offload
+# The learning rate is kept consistent with the settings in the original paper
\ No newline at end of file
diff --git a/examples/wanvideo/model_training/full/Wan2.2-VACE-Fun-A14B.sh b/examples/wanvideo/model_training/full/Wan2.2-VACE-Fun-A14B.sh
index ecfef32..ba3e875 100644
--- a/examples/wanvideo/model_training/full/Wan2.2-VACE-Fun-A14B.sh
+++ b/examples/wanvideo/model_training/full/Wan2.2-VACE-Fun-A14B.sh
@@ -7,7 +7,7 @@ accelerate launch --config_file examples/wanvideo/model_training/full/accelerate
   --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 \
+  --learning_rate 5e-5 \
   --num_epochs 2 \
   --remove_prefix_in_ckpt "pipe.vace." \
   --output_path "./models/train/Wan2.2-VACE-Fun-A14B_high_noise_full" \
@@ -18,6 +18,7 @@ accelerate launch --config_file examples/wanvideo/model_training/full/accelerate
   --min_timestep_boundary 0 \
   --initialize_model_on_cpu
 # boundary corresponds to timesteps [900, 1000]
+# The learning rate is kept consistent with the settings in the original paper
 
 
 accelerate launch --config_file examples/wanvideo/model_training/full/accelerate_config_14B.yaml examples/wanvideo/model_training/train.py \
@@ -29,7 +30,7 @@ accelerate launch --config_file examples/wanvideo/model_training/full/accelerate
   --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 \
+  --learning_rate 5e-5 \
   --num_epochs 2 \
   --remove_prefix_in_ckpt "pipe.vace." \
   --output_path "./models/train/Wan2.2-VACE-Fun-A14B_low_noise_full" \
@@ -39,4 +40,5 @@ accelerate launch --config_file examples/wanvideo/model_training/full/accelerate
   --max_timestep_boundary 1 \
   --min_timestep_boundary 0.358 \
   --initialize_model_on_cpu
-# boundary corresponds to timesteps [0, 900]
\ No newline at end of file
+# boundary corresponds to timesteps [0, 900]
+# The learning rate is kept consistent with the settings in the original paper
\ No newline at end of file