wan-series

examples/wanvideo/model_training/full/LongCat-Video.sh

@@ -0,0 +1,12 @@
+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 "meituan-longcat/LongCat-Video:dit/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/LongCat-Video_full" \
+  --trainable_models "dit"

examples/wanvideo/model_training/full/Video-As-Prompt-Wan2.1-14B.sh

@@ -0,0 +1,16 @@
+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_vap.csv \
+  --data_file_keys "video,vap_video" \
+  --height 480 \
+  --width 832 \
+  --num_frames 49 \
+  --dataset_repeat 100 \
+  --model_id_with_origin_paths "ByteDance/Video-As-Prompt-Wan2.1-14B:transformer/diffusion_pytorch_model*.safetensors,Wan-AI/Wan2.1-I2V-14B-720P:models_t5_umt5-xxl-enc-bf16.pth,Wan-AI/Wan2.1-I2V-14B-720P:Wan2.1_VAE.pth,Wan-AI/Wan2.1-I2V-14B-720P:models_clip_open-clip-xlm-roberta-large-vit-huge-14.pth" \
+  --learning_rate 1e-5 \
+  --num_epochs 2 \
+  --remove_prefix_in_ckpt "pipe.vap." \
+  --output_path "./models/train/Video-As-Prompt-Wan2.1-14B_full" \
+  --trainable_models "vap" \
+  --extra_inputs "vap_video,input_image" \
+  --use_gradient_checkpointing_offload

examples/wanvideo/model_training/full/Wan2.1-1.3b-speedcontrol-v1.sh

@@ -0,0 +1,13 @@
+accelerate launch examples/wanvideo/model_training/train.py \
+  --dataset_base_path data/example_video_dataset \
+  --dataset_metadata_path data/example_video_dataset/metadata_motion_bucket_id.csv \
+  --height 480 \
+  --width 832 \
+  --dataset_repeat 100 \
+  --model_id_with_origin_paths "Wan-AI/Wan2.1-T2V-1.3B:diffusion_pytorch_model*.safetensors,Wan-AI/Wan2.1-T2V-1.3B:models_t5_umt5-xxl-enc-bf16.pth,Wan-AI/Wan2.1-T2V-1.3B:Wan2.1_VAE.pth,DiffSynth-Studio/Wan2.1-1.3b-speedcontrol-v1:model.safetensors" \
+  --learning_rate 1e-5 \
+  --num_epochs 2 \
+  --remove_prefix_in_ckpt "pipe.motion_controller." \
+  --output_path "./models/train/Wan2.1-1.3b-speedcontrol-v1_full" \
+  --trainable_models "motion_controller" \
+  --extra_inputs "motion_bucket_id"

examples/wanvideo/model_training/full/Wan2.1-FLF2V-14B-720P.sh

@@ -0,0 +1,13 @@
+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-FLF2V-14B-720P:diffusion_pytorch_model*.safetensors,Wan-AI/Wan2.1-FLF2V-14B-720P:models_t5_umt5-xxl-enc-bf16.pth,Wan-AI/Wan2.1-FLF2V-14B-720P:Wan2.1_VAE.pth,Wan-AI/Wan2.1-FLF2V-14B-720P:models_clip_open-clip-xlm-roberta-large-vit-huge-14.pth" \
+  --learning_rate 1e-5 \
+  --num_epochs 2 \
+  --remove_prefix_in_ckpt "pipe.dit." \
+  --output_path "./models/train/Wan2.1-FLF2V-14B-720P_full" \
+  --trainable_models "dit" \
+  --extra_inputs "input_image,end_image"

examples/wanvideo/model_training/full/Wan2.1-Fun-1.3B-Control.sh

@@ -0,0 +1,14 @@
+accelerate launch examples/wanvideo/model_training/train.py \
+  --dataset_base_path data/example_video_dataset \
+  --dataset_metadata_path data/example_video_dataset/metadata_control.csv \
+  --data_file_keys "video,control_video" \
+  --height 480 \
+  --width 832 \
+  --dataset_repeat 100 \
+  --model_id_with_origin_paths "PAI/Wan2.1-Fun-1.3B-Control:diffusion_pytorch_model*.safetensors,PAI/Wan2.1-Fun-1.3B-Control:models_t5_umt5-xxl-enc-bf16.pth,PAI/Wan2.1-Fun-1.3B-Control:Wan2.1_VAE.pth,PAI/Wan2.1-Fun-1.3B-Control:models_clip_open-clip-xlm-roberta-large-vit-huge-14.pth" \
+  --learning_rate 1e-5 \
+  --num_epochs 2 \
+  --remove_prefix_in_ckpt "pipe.dit." \
+  --output_path "./models/train/Wan2.1-Fun-1.3B-Control_full" \
+  --trainable_models "dit" \
+  --extra_inputs "control_video"

examples/wanvideo/model_training/full/Wan2.1-Fun-1.3B-InP.sh

@@ -0,0 +1,13 @@
+accelerate launch 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 "PAI/Wan2.1-Fun-1.3B-InP:diffusion_pytorch_model*.safetensors,PAI/Wan2.1-Fun-1.3B-InP:models_t5_umt5-xxl-enc-bf16.pth,PAI/Wan2.1-Fun-1.3B-InP:Wan2.1_VAE.pth,PAI/Wan2.1-Fun-1.3B-InP:models_clip_open-clip-xlm-roberta-large-vit-huge-14.pth" \
+  --learning_rate 1e-5 \
+  --num_epochs 2 \
+  --remove_prefix_in_ckpt "pipe.dit." \
+  --output_path "./models/train/Wan2.1-Fun-1.3B-InP_full" \
+  --trainable_models "dit" \
+  --extra_inputs "input_image,end_image"

examples/wanvideo/model_training/full/Wan2.1-Fun-14B-Control.sh

@@ -0,0 +1,14 @@
+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_control.csv \
+  --data_file_keys "video,control_video" \
+  --height 480 \
+  --width 832 \
+  --dataset_repeat 100 \
+  --model_id_with_origin_paths "PAI/Wan2.1-Fun-14B-Control:diffusion_pytorch_model*.safetensors,PAI/Wan2.1-Fun-14B-Control:models_t5_umt5-xxl-enc-bf16.pth,PAI/Wan2.1-Fun-14B-Control:Wan2.1_VAE.pth,PAI/Wan2.1-Fun-14B-Control:models_clip_open-clip-xlm-roberta-large-vit-huge-14.pth" \
+  --learning_rate 1e-5 \
+  --num_epochs 2 \
+  --remove_prefix_in_ckpt "pipe.dit." \
+  --output_path "./models/train/Wan2.1-Fun-14B-Control_full" \
+  --trainable_models "dit" \
+  --extra_inputs "control_video"

examples/wanvideo/model_training/full/Wan2.1-Fun-14B-InP.sh

@@ -0,0 +1,13 @@
+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 "PAI/Wan2.1-Fun-14B-InP:diffusion_pytorch_model*.safetensors,PAI/Wan2.1-Fun-14B-InP:models_t5_umt5-xxl-enc-bf16.pth,PAI/Wan2.1-Fun-14B-InP:Wan2.1_VAE.pth,PAI/Wan2.1-Fun-14B-InP:models_clip_open-clip-xlm-roberta-large-vit-huge-14.pth" \
+  --learning_rate 1e-5 \
+  --num_epochs 2 \
+  --remove_prefix_in_ckpt "pipe.dit." \
+  --output_path "./models/train/Wan2.1-Fun-14B-InP_full" \
+  --trainable_models "dit" \
+  --extra_inputs "input_image,end_image"

examples/wanvideo/model_training/full/Wan2.1-Fun-V1.1-1.3B-Control-Camera.sh

@@ -0,0 +1,13 @@
+accelerate launch examples/wanvideo/model_training/train.py \
+  --dataset_base_path data/example_video_dataset \
+  --dataset_metadata_path data/example_video_dataset/metadata_camera_control.csv \
+  --height 480 \
+  --width 832 \
+  --dataset_repeat 100 \
+  --model_id_with_origin_paths "PAI/Wan2.1-Fun-V1.1-1.3B-Control-Camera:diffusion_pytorch_model*.safetensors,PAI/Wan2.1-Fun-V1.1-1.3B-Control-Camera:models_t5_umt5-xxl-enc-bf16.pth,PAI/Wan2.1-Fun-V1.1-1.3B-Control-Camera:Wan2.1_VAE.pth,PAI/Wan2.1-Fun-V1.1-1.3B-Control-Camera:models_clip_open-clip-xlm-roberta-large-vit-huge-14.pth" \
+  --learning_rate 1e-5 \
+  --num_epochs 2 \
+  --remove_prefix_in_ckpt "pipe.dit." \
+  --output_path "./models/train/Wan2.1-Fun-V1.1-1.3B-Control-Camera_full" \
+  --trainable_models "dit" \
+  --extra_inputs "input_image,camera_control_direction,camera_control_speed"

examples/wanvideo/model_training/full/Wan2.1-Fun-V1.1-1.3B-Control.sh

@@ -0,0 +1,14 @@
+accelerate launch examples/wanvideo/model_training/train.py \
+  --dataset_base_path data/example_video_dataset \
+  --dataset_metadata_path data/example_video_dataset/metadata_reference_control.csv \
+  --data_file_keys "video,control_video,reference_image" \
+  --height 480 \
+  --width 832 \
+  --dataset_repeat 100 \
+  --model_id_with_origin_paths "PAI/Wan2.1-Fun-V1.1-1.3B-Control:diffusion_pytorch_model*.safetensors,PAI/Wan2.1-Fun-V1.1-1.3B-Control:models_t5_umt5-xxl-enc-bf16.pth,PAI/Wan2.1-Fun-V1.1-1.3B-Control:Wan2.1_VAE.pth,PAI/Wan2.1-Fun-V1.1-1.3B-Control:models_clip_open-clip-xlm-roberta-large-vit-huge-14.pth" \
+  --learning_rate 1e-5 \
+  --num_epochs 2 \
+  --remove_prefix_in_ckpt "pipe.dit." \
+  --output_path "./models/train/Wan2.1-Fun-V1.1-1.3B-Control_full" \
+  --trainable_models "dit" \
+  --extra_inputs "control_video,reference_image"

examples/wanvideo/model_training/full/Wan2.1-Fun-V1.1-1.3B-InP.sh

@@ -0,0 +1,13 @@
+accelerate launch 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 "PAI/Wan2.1-Fun-V1.1-1.3B-InP:diffusion_pytorch_model*.safetensors,PAI/Wan2.1-Fun-V1.1-1.3B-InP:models_t5_umt5-xxl-enc-bf16.pth,PAI/Wan2.1-Fun-V1.1-1.3B-InP:Wan2.1_VAE.pth,PAI/Wan2.1-Fun-V1.1-1.3B-InP:models_clip_open-clip-xlm-roberta-large-vit-huge-14.pth" \
+  --learning_rate 1e-5 \
+  --num_epochs 2 \
+  --remove_prefix_in_ckpt "pipe.dit." \
+  --output_path "./models/train/Wan2.1-Fun-V1.1-1.3B-InP_full" \
+  --trainable_models "dit" \
+  --extra_inputs "input_image,end_image"

examples/wanvideo/model_training/full/Wan2.1-Fun-V1.1-14B-Control-Camera.sh

@@ -0,0 +1,13 @@
+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_camera_control.csv \
+  --height 480 \
+  --width 832 \
+  --dataset_repeat 100 \
+  --model_id_with_origin_paths "PAI/Wan2.1-Fun-V1.1-14B-Control-Camera:diffusion_pytorch_model*.safetensors,PAI/Wan2.1-Fun-V1.1-14B-Control-Camera:models_t5_umt5-xxl-enc-bf16.pth,PAI/Wan2.1-Fun-V1.1-14B-Control-Camera:Wan2.1_VAE.pth,PAI/Wan2.1-Fun-V1.1-14B-Control-Camera:models_clip_open-clip-xlm-roberta-large-vit-huge-14.pth" \
+  --learning_rate 1e-5 \
+  --num_epochs 2 \
+  --remove_prefix_in_ckpt "pipe.dit." \
+  --output_path "./models/train/Wan2.1-Fun-V1.1-14B-Control-Camera_full" \
+  --trainable_models "dit" \
+  --extra_inputs "input_image,camera_control_direction,camera_control_speed"

examples/wanvideo/model_training/full/Wan2.1-Fun-V1.1-14B-Control.sh

@@ -0,0 +1,14 @@
+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_reference_control.csv \
+  --data_file_keys "video,control_video,reference_image" \
+  --height 480 \
+  --width 832 \
+  --dataset_repeat 100 \
+  --model_id_with_origin_paths "PAI/Wan2.1-Fun-V1.1-14B-Control:diffusion_pytorch_model*.safetensors,PAI/Wan2.1-Fun-V1.1-14B-Control:models_t5_umt5-xxl-enc-bf16.pth,PAI/Wan2.1-Fun-V1.1-14B-Control:Wan2.1_VAE.pth,PAI/Wan2.1-Fun-V1.1-14B-Control:models_clip_open-clip-xlm-roberta-large-vit-huge-14.pth" \
+  --learning_rate 1e-5 \
+  --num_epochs 2 \
+  --remove_prefix_in_ckpt "pipe.dit." \
+  --output_path "./models/train/Wan2.1-Fun-V1.1-14B-Control_full" \
+  --trainable_models "dit" \
+  --extra_inputs "control_video,reference_image"

examples/wanvideo/model_training/full/Wan2.1-Fun-V1.1-14B-InP.sh

@@ -0,0 +1,13 @@
+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 "PAI/Wan2.1-Fun-V1.1-14B-InP:diffusion_pytorch_model*.safetensors,PAI/Wan2.1-Fun-V1.1-14B-InP:models_t5_umt5-xxl-enc-bf16.pth,PAI/Wan2.1-Fun-V1.1-14B-InP:Wan2.1_VAE.pth,PAI/Wan2.1-Fun-V1.1-14B-InP:models_clip_open-clip-xlm-roberta-large-vit-huge-14.pth" \
+  --learning_rate 1e-5 \
+  --num_epochs 2 \
+  --remove_prefix_in_ckpt "pipe.dit." \
+  --output_path "./models/train/Wan2.1-Fun-V1.1-14B-InP_full" \
+  --trainable_models "dit" \
+  --extra_inputs "input_image,end_image"

examples/wanvideo/model_training/full/Wan2.1-I2V-14B-480P.sh

@@ -0,0 +1,13 @@
+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-I2V-14B-480P:diffusion_pytorch_model*.safetensors,Wan-AI/Wan2.1-I2V-14B-480P:models_t5_umt5-xxl-enc-bf16.pth,Wan-AI/Wan2.1-I2V-14B-480P:Wan2.1_VAE.pth,Wan-AI/Wan2.1-I2V-14B-480P:models_clip_open-clip-xlm-roberta-large-vit-huge-14.pth" \
+  --learning_rate 1e-5 \
+  --num_epochs 2 \
+  --remove_prefix_in_ckpt "pipe.dit." \
+  --output_path "./models/train/Wan2.1-I2V-14B-480P_full" \
+  --trainable_models "dit" \
+  --extra_inputs "input_image"

examples/wanvideo/model_training/full/Wan2.1-I2V-14B-720P.sh

@@ -0,0 +1,15 @@
+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 720 \
+  --width 1280 \
+  --num_frames 49 \
+  --dataset_repeat 100 \
+  --model_id_with_origin_paths "Wan-AI/Wan2.1-I2V-14B-720P:diffusion_pytorch_model*.safetensors,Wan-AI/Wan2.1-I2V-14B-720P:models_t5_umt5-xxl-enc-bf16.pth,Wan-AI/Wan2.1-I2V-14B-720P:Wan2.1_VAE.pth,Wan-AI/Wan2.1-I2V-14B-720P:models_clip_open-clip-xlm-roberta-large-vit-huge-14.pth" \
+  --learning_rate 1e-5 \
+  --num_epochs 2 \
+  --remove_prefix_in_ckpt "pipe.dit." \
+  --output_path "./models/train/Wan2.1-I2V-14B-720P_full" \
+  --trainable_models "dit" \
+  --extra_inputs "input_image" \
+  --use_gradient_checkpointing_offload

examples/wanvideo/model_training/full/Wan2.1-T2V-1.3B.sh

@@ -0,0 +1,12 @@
+accelerate launch 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-1.3B:diffusion_pytorch_model*.safetensors,Wan-AI/Wan2.1-T2V-1.3B:models_t5_umt5-xxl-enc-bf16.pth,Wan-AI/Wan2.1-T2V-1.3B:Wan2.1_VAE.pth" \
+  --learning_rate 1e-5 \
+  --num_epochs 2 \
+  --remove_prefix_in_ckpt "pipe.dit." \
+  --output_path "./models/train/Wan2.1-T2V-1.3B_full" \
+  --trainable_models "dit"

examples/wanvideo/model_training/full/Wan2.1-T2V-14B.sh

@@ -0,0 +1,12 @@
+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"

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

@@ -0,0 +1,16 @@
+accelerate launch 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 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 \
+  --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

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

@@ -0,0 +1,16 @@
+accelerate launch 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 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 \
+  --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

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

@@ -0,0 +1,16 @@
+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 "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 \
+  --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

examples/wanvideo/model_training/full/Wan2.2-Animate-14B.sh

@@ -0,0 +1,16 @@
+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_animate.csv \
+  --data_file_keys "video,animate_pose_video,animate_face_video" \
+  --height 480 \
+  --width 832 \
+  --num_frames 81 \
+  --dataset_repeat 100 \
+  --model_id_with_origin_paths "Wan-AI/Wan2.2-Animate-14B:diffusion_pytorch_model*.safetensors,Wan-AI/Wan2.2-Animate-14B:models_t5_umt5-xxl-enc-bf16.pth,Wan-AI/Wan2.2-Animate-14B:Wan2.1_VAE.pth,Wan-AI/Wan2.2-Animate-14B:models_clip_open-clip-xlm-roberta-large-vit-huge-14.pth" \
+  --learning_rate 1e-5 \
+  --num_epochs 2 \
+  --remove_prefix_in_ckpt "pipe.animate_adapter." \
+  --output_path "./models/train/Wan2.2-Animate-14B_full" \
+  --trainable_models "animate_adapter" \
+  --extra_inputs "input_image,animate_pose_video,animate_face_video" \
+  --use_gradient_checkpointing_offload

examples/wanvideo/model_training/full/Wan2.2-Fun-A14B-Control-Camera.sh

@@ -0,0 +1,35 @@
+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_camera_control.csv \
+  --data_file_keys "video,control_video,reference_image" \
+  --height 480 \
+  --width 832 \
+  --dataset_repeat 100 \
+  --model_id_with_origin_paths "PAI/Wan2.2-Fun-A14B-Control-Camera:high_noise_model/diffusion_pytorch_model*.safetensors,PAI/Wan2.2-Fun-A14B-Control-Camera:models_t5_umt5-xxl-enc-bf16.pth,PAI/Wan2.2-Fun-A14B-Control-Camera:Wan2.1_VAE.pth" \
+  --learning_rate 1e-4 \
+  --num_epochs 5 \
+  --remove_prefix_in_ckpt "pipe.dit." \
+  --output_path "./models/train/Wan2.2-Fun-A14B-Control-Camera_high_niose_full" \
+  --trainable_models "dit" \
+  --extra_inputs "input_image,camera_control_direction,camera_control_speed" \
+  --max_timestep_boundary 0.358 \
+  --min_timestep_boundary 0
+# 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_camera_control.csv \
+  --data_file_keys "video,control_video,reference_image" \
+  --height 480 \
+  --width 832 \
+  --dataset_repeat 100 \
+  --model_id_with_origin_paths "PAI/Wan2.2-Fun-A14B-Control-Camera:low_noise_model/diffusion_pytorch_model*.safetensors,PAI/Wan2.2-Fun-A14B-Control-Camera:models_t5_umt5-xxl-enc-bf16.pth,PAI/Wan2.2-Fun-A14B-Control-Camera:Wan2.1_VAE.pth" \
+  --learning_rate 1e-4 \
+  --num_epochs 5 \
+  --remove_prefix_in_ckpt "pipe.dit." \
+  --output_path "./models/train/Wan2.2-Fun-A14B-Control-Camera_low_noise_full" \
+  --trainable_models "dit" \
+  --extra_inputs "input_image,camera_control_direction,camera_control_speed" \
+  --max_timestep_boundary 1 \
+  --min_timestep_boundary 0.358
+# boundary corresponds to timesteps [0, 900]

examples/wanvideo/model_training/full/Wan2.2-Fun-A14B-Control.sh

@@ -0,0 +1,35 @@
+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_reference_control.csv \
+  --data_file_keys "video,control_video,reference_image" \
+  --height 480 \
+  --width 832 \
+  --dataset_repeat 100 \
+  --model_id_with_origin_paths "PAI/Wan2.2-Fun-A14B-Control:high_noise_model/diffusion_pytorch_model*.safetensors,PAI/Wan2.2-Fun-A14B-Control:models_t5_umt5-xxl-enc-bf16.pth,PAI/Wan2.2-Fun-A14B-Control:Wan2.1_VAE.pth" \
+  --learning_rate 1e-4 \
+  --num_epochs 5 \
+  --remove_prefix_in_ckpt "pipe.dit." \
+  --output_path "./models/train/Wan2.2-Fun-A14B-Control_high_niose_full" \
+  --trainable_models "dit" \
+  --extra_inputs "control_video,reference_image" \
+  --max_timestep_boundary 0.358 \
+  --min_timestep_boundary 0
+# 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_reference_control.csv \
+  --data_file_keys "video,control_video,reference_image" \
+  --height 480 \
+  --width 832 \
+  --dataset_repeat 100 \
+  --model_id_with_origin_paths "PAI/Wan2.2-Fun-A14B-Control:low_noise_model/diffusion_pytorch_model*.safetensors,PAI/Wan2.2-Fun-A14B-Control:models_t5_umt5-xxl-enc-bf16.pth,PAI/Wan2.2-Fun-A14B-Control:Wan2.1_VAE.pth" \
+  --learning_rate 1e-4 \
+  --num_epochs 5 \
+  --remove_prefix_in_ckpt "pipe.dit." \
+  --output_path "./models/train/Wan2.2-Fun-A14B-Control_low_noise_full" \
+  --trainable_models "dit" \
+  --extra_inputs "control_video,reference_image" \
+  --max_timestep_boundary 1 \
+  --min_timestep_boundary 0.358
+# boundary corresponds to timesteps [0, 900]

examples/wanvideo/model_training/full/Wan2.2-Fun-A14B-InP.sh

@@ -0,0 +1,33 @@
+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 "PAI/Wan2.2-Fun-A14B-InP:high_noise_model/diffusion_pytorch_model*.safetensors,PAI/Wan2.2-Fun-A14B-InP:models_t5_umt5-xxl-enc-bf16.pth,PAI/Wan2.2-Fun-A14B-InP:Wan2.1_VAE.pth" \
+  --learning_rate 1e-4 \
+  --num_epochs 5 \
+  --remove_prefix_in_ckpt "pipe.dit." \
+  --output_path "./models/train/Wan2.2-Fun-A14B-InP_high_niose_full" \
+  --trainable_models "dit" \
+  --extra_inputs "input_image,end_image" \
+  --max_timestep_boundary 0.358 \
+  --min_timestep_boundary 0
+# 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.csv \
+  --height 480 \
+  --width 832 \
+  --dataset_repeat 100 \
+  --model_id_with_origin_paths "PAI/Wan2.2-Fun-A14B-InP:low_noise_model/diffusion_pytorch_model*.safetensors,PAI/Wan2.2-Fun-A14B-InP:models_t5_umt5-xxl-enc-bf16.pth,PAI/Wan2.2-Fun-A14B-InP:Wan2.1_VAE.pth" \
+  --learning_rate 1e-4 \
+  --num_epochs 5 \
+  --remove_prefix_in_ckpt "pipe.dit." \
+  --output_path "./models/train/Wan2.2-Fun-A14B-InP_low_noise_full" \
+  --trainable_models "dit" \
+  --extra_inputs "input_image,end_image" \
+  --max_timestep_boundary 1 \
+  --min_timestep_boundary 0.358
+# boundary corresponds to timesteps [0, 900]

examples/wanvideo/model_training/full/Wan2.2-I2V-A14B.sh

@@ -0,0 +1,37 @@
+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-I2V-A14B:high_noise_model/diffusion_pytorch_model*.safetensors,Wan-AI/Wan2.2-I2V-A14B:models_t5_umt5-xxl-enc-bf16.pth,Wan-AI/Wan2.2-I2V-A14B:Wan2.1_VAE.pth" \
+  --learning_rate 1e-5 \
+  --num_epochs 2 \
+  --remove_prefix_in_ckpt "pipe.dit." \
+  --output_path "./models/train/Wan2.2-I2V-A14B_high_noise_full" \
+  --trainable_models "dit" \
+  --extra_inputs "input_image" \
+  --use_gradient_checkpointing_offload \
+  --max_timestep_boundary 0.358 \
+  --min_timestep_boundary 0
+# 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.csv \
+  --height 480 \
+  --width 832 \
+  --num_frames 49 \
+  --dataset_repeat 100 \
+  --model_id_with_origin_paths "Wan-AI/Wan2.2-I2V-A14B:low_noise_model/diffusion_pytorch_model*.safetensors,Wan-AI/Wan2.2-I2V-A14B:models_t5_umt5-xxl-enc-bf16.pth,Wan-AI/Wan2.2-I2V-A14B:Wan2.1_VAE.pth" \
+  --learning_rate 1e-5 \
+  --num_epochs 2 \
+  --remove_prefix_in_ckpt "pipe.dit." \
+  --output_path "./models/train/Wan2.2-I2V-A14B_low_noise_full" \
+  --trainable_models "dit" \
+  --extra_inputs "input_image" \
+  --use_gradient_checkpointing_offload \
+  --max_timestep_boundary 1 \
+  --min_timestep_boundary 0.358
+# boundary corresponds to timesteps [0, 900)

examples/wanvideo/model_training/full/Wan2.2-S2V-14B.sh

@@ -0,0 +1,17 @@
+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/wans2v \
+  --dataset_metadata_path data/example_video_dataset/wans2v/metadata.csv \
+  --data_file_keys "video,input_audio,s2v_pose_video" \
+  --height 448 \
+  --width 832 \
+  --num_frames 81 \
+  --dataset_repeat 100 \
+  --model_id_with_origin_paths "Wan-AI/Wan2.2-S2V-14B:diffusion_pytorch_model*.safetensors,Wan-AI/Wan2.2-S2V-14B:wav2vec2-large-xlsr-53-english/model.safetensors,Wan-AI/Wan2.2-S2V-14B:models_t5_umt5-xxl-enc-bf16.pth,Wan-AI/Wan2.2-S2V-14B:Wan2.1_VAE.pth" \
+  --audio_processor_config "Wan-AI/Wan2.2-S2V-14B:wav2vec2-large-xlsr-53-english/" \
+  --learning_rate 1e-5 \
+  --num_epochs 1 \
+  --trainable_models "dit" \
+  --remove_prefix_in_ckpt "pipe.dit." \
+  --output_path "./models/train/Wan2.2-S2V-14B_full" \
+  --extra_inputs "input_image,input_audio,s2v_pose_video" \
+  --use_gradient_checkpointing_offload

examples/wanvideo/model_training/full/Wan2.2-T2V-A14B.sh

@@ -0,0 +1,33 @@
+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
+# 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
+# boundary corresponds to timesteps [0, 875)

examples/wanvideo/model_training/full/Wan2.2-TI2V-5B.sh

@@ -0,0 +1,14 @@
+accelerate launch 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-TI2V-5B:diffusion_pytorch_model*.safetensors,Wan-AI/Wan2.2-TI2V-5B:models_t5_umt5-xxl-enc-bf16.pth,Wan-AI/Wan2.2-TI2V-5B:Wan2.2_VAE.pth" \
+  --learning_rate 1e-5 \
+  --num_epochs 2 \
+  --remove_prefix_in_ckpt "pipe.dit." \
+  --output_path "./models/train/Wan2.2-TI2V-5B_full" \
+  --trainable_models "dit" \
+  --extra_inputs "input_image"

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

@@ -0,0 +1,40 @@
+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
+# 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
+# boundary corresponds to timesteps [0, 900]

examples/wanvideo/model_training/full/accelerate_config_14B.yaml

@@ -0,0 +1,22 @@
+compute_environment: LOCAL_MACHINE
+debug: false
+deepspeed_config:
+  gradient_accumulation_steps: 1
+  offload_optimizer_device: cpu
+  offload_param_device: cpu
+  zero3_init_flag: false
+  zero_stage: 2
+distributed_type: DEEPSPEED
+downcast_bf16: 'no'
+enable_cpu_affinity: false
+machine_rank: 0
+main_training_function: main
+mixed_precision: bf16
+num_machines: 1
+num_processes: 8
+rdzv_backend: static
+same_network: true
+tpu_env: []
+tpu_use_cluster: false
+tpu_use_sudo: false
+use_cpu: false

examples/wanvideo/model_training/full/krea-realtime-video.sh

@@ -0,0 +1,12 @@
+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 "krea/krea-realtime-video:krea-realtime-video-14b.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/krea-realtime-video_full" \
+  --trainable_models "dit"