theluyuan/DiffSynth-Studio
1
0
Fork 0
mirror of https://github.com/modelscope/DiffSynth-Studio.git synced 2026-03-18 22:08:13 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge pull request #1215 from lzws/main

Browse Source 
updata learning rate in wan-vace training scripts
This commit is contained in:
Zhongjie Duan
2026-01-19 17:48:42 +08:00
committed by GitHub
parent 37c2868b61 8ad2d9884b
commit 3dd82a738e
4 changed files with 14 additions and 9 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
examples/wanvideo/model_training/full/Wan2.1-VACE-1.3B-Preview.sh
View File

@@ -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
--use_gradient_checkpointing_offload
# The learning rate is kept consistent with the settings in the original paper

5
examples/wanvideo/model_training/full/Wan2.1-VACE-1.3B.sh
View File

@@ -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
--use_gradient_checkpointing_offload
# The learning rate is kept consistent with the settings in the original paper

5
examples/wanvideo/model_training/full/Wan2.1-VACE-14B.sh
View File

@@ -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
--use_gradient_checkpointing_offload
# The learning rate is kept consistent with the settings in the original paper

8
examples/wanvideo/model_training/full/Wan2.2-VACE-Fun-A14B.sh
View File

@@ -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]
# boundary corresponds to timesteps [0, 900]
# The learning rate is kept consistent with the settings in the original paper