Merge pull request #856 from lzws/main

add wan2.2-fun training scripts

README.md

@@ -205,6 +205,9 @@ save_video(video, "video1.mp4", fps=15, quality=5)
 |[Wan-AI/Wan2.2-I2V-A14B](https://modelscope.cn/models/Wan-AI/Wan2.2-I2V-A14B)|`input_image`|[code](./examples/wanvideo/model_inference/Wan2.2-I2V-A14B.py)|[code](./examples/wanvideo/model_training/full/Wan2.2-I2V-A14B.sh)|[code](./examples/wanvideo/model_training/validate_full/Wan2.2-I2V-A14B.py)|[code](./examples/wanvideo/model_training/lora/Wan2.2-I2V-A14B.sh)|[code](./examples/wanvideo/model_training/validate_lora/Wan2.2-I2V-A14B.py)|
 |[Wan-AI/Wan2.2-T2V-A14B](https://modelscope.cn/models/Wan-AI/Wan2.2-T2V-A14B)||[code](./examples/wanvideo/model_inference/Wan2.2-T2V-A14B.py)|[code](./examples/wanvideo/model_training/full/Wan2.2-T2V-A14B.sh)|[code](./examples/wanvideo/model_training/validate_full/Wan2.2-T2V-A14B.py)|[code](./examples/wanvideo/model_training/lora/Wan2.2-T2V-A14B.sh)|[code](./examples/wanvideo/model_training/validate_lora/Wan2.2-T2V-A14B.py)|
 |[Wan-AI/Wan2.2-TI2V-5B](https://modelscope.cn/models/Wan-AI/Wan2.2-TI2V-5B)|`input_image`|[code](./examples/wanvideo/model_inference/Wan2.2-TI2V-5B.py)|[code](./examples/wanvideo/model_training/full/Wan2.2-TI2V-5B.sh)|[code](./examples/wanvideo/model_training/validate_full/Wan2.2-TI2V-5B.py)|[code](./examples/wanvideo/model_training/lora/Wan2.2-TI2V-5B.sh)|[code](./examples/wanvideo/model_training/validate_lora/Wan2.2-TI2V-5B.py)|
+|[PAI/Wan2.2-Fun-A14B-InP](https://modelscope.cn/models/PAI/Wan2.2-Fun-A14B-InP)|`input_image`, `end_image`|[code](./examples/wanvideo/model_inference/Wan2.2-Fun-A14B-InP.py)|[code](./examples/wanvideo/model_training/full/Wan2.2-Fun-A14B-InP.sh)|[code](./examples/wanvideo/model_training/validate_full/Wan2.2-Fun-A14B-InP.py)|[code](./examples/wanvideo/model_training/lora/Wan2.2-Fun-A14B-InP.sh)|[code](./examples/wanvideo/model_training/validate_lora/Wan2.2-Fun-A14B-InP.py)|
+|[PAI/Wan2.2-Fun-A14B-Control](https://modelscope.cn/models/PAI/Wan2.2-Fun-A14B-Control)|`control_video`, `reference_image`|[code](./examples/wanvideo/model_inference/Wan2.2-Fun-A14B-Control.py)|[code](./examples/wanvideo/model_training/full/Wan2.2-Fun-A14B-Control.sh)|[code](./examples/wanvideo/model_training/validate_full/Wan2.2-Fun-A14B-Control.py)|[code](./examples/wanvideo/model_training/lora/Wan2.2-Fun-A14B-Control.sh)|[code](./examples/wanvideo/model_training/validate_lora/Wan2.2-Fun-A14B-Control.py)|
+|[PAI/Wan2.2-Fun-A14B-Control-Camera](https://modelscope.cn/models/PAI/Wan2.2-Fun-A14B-Control-Camera)|`control_camera_video`, `input_image`|[code](./examples/wanvideo/model_inference/Wan2.2-Fun-A14B-Control-Camera.py)|[code](./examples/wanvideo/model_training/full/Wan2.2-Fun-A14B-Control-Camera.sh)|[code](./examples/wanvideo/model_training/validate_full/Wan2.2-Fun-A14B-Control-Camera.py)|[code](./examples/wanvideo/model_training/lora/Wan2.2-Fun-A14B-Control-Camera.sh)|[code](./examples/wanvideo/model_training/validate_lora/Wan2.2-Fun-A14B-Control-Camera.py)|
 |[Wan-AI/Wan2.1-T2V-1.3B](https://modelscope.cn/models/Wan-AI/Wan2.1-T2V-1.3B)||[code](./examples/wanvideo/model_inference/Wan2.1-T2V-1.3B.py)|[code](./examples/wanvideo/model_training/full/Wan2.1-T2V-1.3B.sh)|[code](./examples/wanvideo/model_training/validate_full/Wan2.1-T2V-1.3B.py)|[code](./examples/wanvideo/model_training/lora/Wan2.1-T2V-1.3B.sh)|[code](./examples/wanvideo/model_training/validate_lora/Wan2.1-T2V-1.3B.py)|
 |[Wan-AI/Wan2.1-T2V-14B](https://modelscope.cn/models/Wan-AI/Wan2.1-T2V-14B)||[code](./examples/wanvideo/model_inference/Wan2.1-T2V-14B.py)|[code](./examples/wanvideo/model_training/full/Wan2.1-T2V-14B.sh)|[code](./examples/wanvideo/model_training/validate_full/Wan2.1-T2V-14B.py)|[code](./examples/wanvideo/model_training/lora/Wan2.1-T2V-14B.sh)|[code](./examples/wanvideo/model_training/validate_lora/Wan2.1-T2V-14B.py)|
 |[Wan-AI/Wan2.1-I2V-14B-480P](https://modelscope.cn/models/Wan-AI/Wan2.1-I2V-14B-480P)|`input_image`|[code](./examples/wanvideo/model_inference/Wan2.1-I2V-14B-480P.py)|[code](./examples/wanvideo/model_training/full/Wan2.1-I2V-14B-480P.sh)|[code](./examples/wanvideo/model_training/validate_full/Wan2.1-I2V-14B-480P.py)|[code](./examples/wanvideo/model_training/lora/Wan2.1-I2V-14B-480P.sh)|[code](./examples/wanvideo/model_training/validate_lora/Wan2.1-I2V-14B-480P.py)|

README_zh.md

@@ -205,6 +205,9 @@ save_video(video, "video1.mp4", fps=15, quality=5)
 |[Wan-AI/Wan2.2-I2V-A14B](https://modelscope.cn/models/Wan-AI/Wan2.2-I2V-A14B)|`input_image`|[code](./examples/wanvideo/model_inference/Wan2.2-I2V-A14B.py)|[code](./examples/wanvideo/model_training/full/Wan2.2-I2V-A14B.sh)|[code](./examples/wanvideo/model_training/validate_full/Wan2.2-I2V-A14B.py)|[code](./examples/wanvideo/model_training/lora/Wan2.2-I2V-A14B.sh)|[code](./examples/wanvideo/model_training/validate_lora/Wan2.2-I2V-A14B.py)|
 |[Wan-AI/Wan2.2-T2V-A14B](https://modelscope.cn/models/Wan-AI/Wan2.2-T2V-A14B)||[code](./examples/wanvideo/model_inference/Wan2.2-T2V-A14B.py)|[code](./examples/wanvideo/model_training/full/Wan2.2-T2V-A14B.sh)|[code](./examples/wanvideo/model_training/validate_full/Wan2.2-T2V-A14B.py)|[code](./examples/wanvideo/model_training/lora/Wan2.2-T2V-A14B.sh)|[code](./examples/wanvideo/model_training/validate_lora/Wan2.2-T2V-A14B.py)|
 |[Wan-AI/Wan2.2-TI2V-5B](https://modelscope.cn/models/Wan-AI/Wan2.2-TI2V-5B)|`input_image`|[code](./examples/wanvideo/model_inference/Wan2.2-TI2V-5B.py)|[code](./examples/wanvideo/model_training/full/Wan2.2-TI2V-5B.sh)|[code](./examples/wanvideo/model_training/validate_full/Wan2.2-TI2V-5B.py)|[code](./examples/wanvideo/model_training/lora/Wan2.2-TI2V-5B.sh)|[code](./examples/wanvideo/model_training/validate_lora/Wan2.2-TI2V-5B.py)|
+|[PAI/Wan2.2-Fun-A14B-InP](https://modelscope.cn/models/PAI/Wan2.2-Fun-A14B-InP)|`input_image`, `end_image`|[code](./examples/wanvideo/model_inference/Wan2.2-Fun-A14B-InP.py)|[code](./examples/wanvideo/model_training/full/Wan2.2-Fun-A14B-InP.sh)|[code](./examples/wanvideo/model_training/validate_full/Wan2.2-Fun-A14B-InP.py)|[code](./examples/wanvideo/model_training/lora/Wan2.2-Fun-A14B-InP.sh)|[code](./examples/wanvideo/model_training/validate_lora/Wan2.2-Fun-A14B-InP.py)|
+|[PAI/Wan2.2-Fun-A14B-Control](https://modelscope.cn/models/PAI/Wan2.2-Fun-A14B-Control)|`control_video`, `reference_image`|[code](./examples/wanvideo/model_inference/Wan2.2-Fun-A14B-Control.py)|[code](./examples/wanvideo/model_training/full/Wan2.2-Fun-A14B-Control.sh)|[code](./examples/wanvideo/model_training/validate_full/Wan2.2-Fun-A14B-Control.py)|[code](./examples/wanvideo/model_training/lora/Wan2.2-Fun-A14B-Control.sh)|[code](./examples/wanvideo/model_training/validate_lora/Wan2.2-Fun-A14B-Control.py)|
+|[PAI/Wan2.2-Fun-A14B-Control-Camera](https://modelscope.cn/models/PAI/Wan2.2-Fun-A14B-Control-Camera)|`control_camera_video`, `input_image`|[code](./examples/wanvideo/model_inference/Wan2.2-Fun-A14B-Control-Camera.py)|[code](./examples/wanvideo/model_training/full/Wan2.2-Fun-A14B-Control-Camera.sh)|[code](./examples/wanvideo/model_training/validate_full/Wan2.2-Fun-A14B-Control-Camera.py)|[code](./examples/wanvideo/model_training/lora/Wan2.2-Fun-A14B-Control-Camera.sh)|[code](./examples/wanvideo/model_training/validate_lora/Wan2.2-Fun-A14B-Control-Camera.py)|
 |[Wan-AI/Wan2.1-T2V-1.3B](https://modelscope.cn/models/Wan-AI/Wan2.1-T2V-1.3B)||[code](./examples/wanvideo/model_inference/Wan2.1-T2V-1.3B.py)|[code](./examples/wanvideo/model_training/full/Wan2.1-T2V-1.3B.sh)|[code](./examples/wanvideo/model_training/validate_full/Wan2.1-T2V-1.3B.py)|[code](./examples/wanvideo/model_training/lora/Wan2.1-T2V-1.3B.sh)|[code](./examples/wanvideo/model_training/validate_lora/Wan2.1-T2V-1.3B.py)|
 |[Wan-AI/Wan2.1-T2V-14B](https://modelscope.cn/models/Wan-AI/Wan2.1-T2V-14B)||[code](./examples/wanvideo/model_inference/Wan2.1-T2V-14B.py)|[code](./examples/wanvideo/model_training/full/Wan2.1-T2V-14B.sh)|[code](./examples/wanvideo/model_training/validate_full/Wan2.1-T2V-14B.py)|[code](./examples/wanvideo/model_training/lora/Wan2.1-T2V-14B.sh)|[code](./examples/wanvideo/model_training/validate_lora/Wan2.1-T2V-14B.py)|
 |[Wan-AI/Wan2.1-I2V-14B-480P](https://modelscope.cn/models/Wan-AI/Wan2.1-I2V-14B-480P)|`input_image`|[code](./examples/wanvideo/model_inference/Wan2.1-I2V-14B-480P.py)|[code](./examples/wanvideo/model_training/full/Wan2.1-I2V-14B-480P.sh)|[code](./examples/wanvideo/model_training/validate_full/Wan2.1-I2V-14B-480P.py)|[code](./examples/wanvideo/model_training/lora/Wan2.1-I2V-14B-480P.sh)|[code](./examples/wanvideo/model_training/validate_lora/Wan2.1-I2V-14B-480P.py)|

examples/wanvideo/README.md

@@ -52,6 +52,9 @@ save_video(video, "video1.mp4", fps=15, quality=5)
 |[Wan-AI/Wan2.2-I2V-A14B](https://modelscope.cn/models/Wan-AI/Wan2.2-I2V-A14B)|`input_image`|[code](./model_inference/Wan2.2-I2V-A14B.py)|[code](./model_training/full/Wan2.2-I2V-A14B.sh)|[code](./model_training/validate_full/Wan2.2-I2V-A14B.py)|[code](./model_training/lora/Wan2.2-I2V-A14B.sh)|[code](./model_training/validate_lora/Wan2.2-I2V-A14B.py)|
 |[Wan-AI/Wan2.2-T2V-A14B](https://modelscope.cn/models/Wan-AI/Wan2.2-T2V-A14B)||[code](./model_inference/Wan2.2-T2V-A14B.py)|[code](./model_training/full/Wan2.2-T2V-A14B.sh)|[code](./model_training/validate_full/Wan2.2-T2V-A14B.py)|[code](./model_training/lora/Wan2.2-T2V-A14B.sh)|[code](./model_training/validate_lora/Wan2.2-T2V-A14B.py)|
 |[Wan-AI/Wan2.2-TI2V-5B](https://modelscope.cn/models/Wan-AI/Wan2.2-TI2V-5B)|`input_image`|[code](./model_inference/Wan2.2-TI2V-5B.py)|[code](./model_training/full/Wan2.2-TI2V-5B.sh)|[code](./model_training/validate_full/Wan2.2-TI2V-5B.py)|[code](./model_training/lora/Wan2.2-TI2V-5B.sh)|[code](./model_training/validate_lora/Wan2.2-TI2V-5B.py)|
+|[PAI/Wan2.2-Fun-A14B-InP](https://modelscope.cn/models/PAI/Wan2.2-Fun-A14B-InP)|`input_image`, `end_image`|[code](./model_inference/Wan2.2-Fun-A14B-InP.py)|[code](./model_training/full/Wan2.2-Fun-A14B-InP.sh)|[code](./model_training/validate_full/Wan2.2-Fun-A14B-InP.py)|[code](./model_training/lora/Wan2.2-Fun-A14B-InP.sh)|[code](./model_training/validate_lora/Wan2.2-Fun-A14B-InP.py)|
+|[PAI/Wan2.2-Fun-A14B-Control](https://modelscope.cn/models/PAI/Wan2.2-Fun-A14B-Control)|`control_video`, `reference_image`|[code](./model_inference/Wan2.2-Fun-A14B-Control.py)|[code](./model_training/full/Wan2.2-Fun-A14B-Control.sh)|[code](./model_training/validate_full/Wan2.2-Fun-A14B-Control.py)|[code](./model_training/lora/Wan2.2-Fun-A14B-Control.sh)|[code](./model_training/validate_lora/Wan2.2-Fun-A14B-Control.py)|
+|[PAI/Wan2.2-Fun-A14B-Control-Camera](https://modelscope.cn/models/PAI/Wan2.2-Fun-A14B-Control-Camera)|`control_camera_video`, `input_image`|[code](./model_inference/Wan2.2-Fun-A14B-Control-Camera.py)|[code](./model_training/full/Wan2.2-Fun-A14B-Control-Camera.sh)|[code](./model_training/validate_full/Wan2.2-Fun-A14B-Control-Camera.py)|[code](./model_training/lora/Wan2.2-Fun-A14B-Control-Camera.sh)|[code](./model_training/validate_lora/Wan2.2-Fun-A14B-Control-Camera.py)|
 |[Wan-AI/Wan2.1-T2V-1.3B](https://modelscope.cn/models/Wan-AI/Wan2.1-T2V-1.3B)||[code](./model_inference/Wan2.1-T2V-1.3B.py)|[code](./model_training/full/Wan2.1-T2V-1.3B.sh)|[code](./model_training/validate_full/Wan2.1-T2V-1.3B.py)|[code](./model_training/lora/Wan2.1-T2V-1.3B.sh)|[code](./model_training/validate_lora/Wan2.1-T2V-1.3B.py)|
 |[Wan-AI/Wan2.1-T2V-14B](https://modelscope.cn/models/Wan-AI/Wan2.1-T2V-14B)||[code](./model_inference/Wan2.1-T2V-14B.py)|[code](./model_training/full/Wan2.1-T2V-14B.sh)|[code](./model_training/validate_full/Wan2.1-T2V-14B.py)|[code](./model_training/lora/Wan2.1-T2V-14B.sh)|[code](./model_training/validate_lora/Wan2.1-T2V-14B.py)|
 |[Wan-AI/Wan2.1-I2V-14B-480P](https://modelscope.cn/models/Wan-AI/Wan2.1-I2V-14B-480P)|`input_image`|[code](./model_inference/Wan2.1-I2V-14B-480P.py)|[code](./model_training/full/Wan2.1-I2V-14B-480P.sh)|[code](./model_training/validate_full/Wan2.1-I2V-14B-480P.py)|[code](./model_training/lora/Wan2.1-I2V-14B-480P.sh)|[code](./model_training/validate_lora/Wan2.1-I2V-14B-480P.py)|

examples/wanvideo/README_zh.md

@@ -52,6 +52,9 @@ save_video(video, "video1.mp4", fps=15, quality=5)
 |[Wan-AI/Wan2.2-I2V-A14B](https://modelscope.cn/models/Wan-AI/Wan2.2-I2V-A14B)|`input_image`|[code](./model_inference/Wan2.2-I2V-A14B.py)|[code](./model_training/full/Wan2.2-I2V-A14B.sh)|[code](./model_training/validate_full/Wan2.2-I2V-A14B.py)|[code](./model_training/lora/Wan2.2-I2V-A14B.sh)|[code](./model_training/validate_lora/Wan2.2-I2V-A14B.py)|
 |[Wan-AI/Wan2.2-T2V-A14B](https://modelscope.cn/models/Wan-AI/Wan2.2-T2V-A14B)||[code](./model_inference/Wan2.2-T2V-A14B.py)|[code](./model_training/full/Wan2.2-T2V-A14B.sh)|[code](./model_training/validate_full/Wan2.2-T2V-A14B.py)|[code](./model_training/lora/Wan2.2-T2V-A14B.sh)|[code](./model_training/validate_lora/Wan2.2-T2V-A14B.py)|
 |[Wan-AI/Wan2.2-TI2V-5B](https://modelscope.cn/models/Wan-AI/Wan2.2-TI2V-5B)|`input_image`|[code](./model_inference/Wan2.2-TI2V-5B.py)|[code](./model_training/full/Wan2.2-TI2V-5B.sh)|[code](./model_training/validate_full/Wan2.2-TI2V-5B.py)|[code](./model_training/lora/Wan2.2-TI2V-5B.sh)|[code](./model_training/validate_lora/Wan2.2-TI2V-5B.py)|
+|[PAI/Wan2.2-Fun-A14B-InP](https://modelscope.cn/models/PAI/Wan2.2-Fun-A14B-InP)|`input_image`, `end_image`|[code](./model_inference/Wan2.2-Fun-A14B-InP.py)|[code](./model_training/full/Wan2.2-Fun-A14B-InP.sh)|[code](./model_training/validate_full/Wan2.2-Fun-A14B-InP.py)|[code](./model_training/lora/Wan2.2-Fun-A14B-InP.sh)|[code](./model_training/validate_lora/Wan2.2-Fun-A14B-InP.py)|
+|[PAI/Wan2.2-Fun-A14B-Control](https://modelscope.cn/models/PAI/Wan2.2-Fun-A14B-Control)|`control_video`, `reference_image`|[code](./model_inference/Wan2.2-Fun-A14B-Control.py)|[code](./model_training/full/Wan2.2-Fun-A14B-Control.sh)|[code](./model_training/validate_full/Wan2.2-Fun-A14B-Control.py)|[code](./model_training/lora/Wan2.2-Fun-A14B-Control.sh)|[code](./model_training/validate_lora/Wan2.2-Fun-A14B-Control.py)|
+|[PAI/Wan2.2-Fun-A14B-Control-Camera](https://modelscope.cn/models/PAI/Wan2.2-Fun-A14B-Control-Camera)|`control_camera_video`, `input_image`|[code](./model_inference/Wan2.2-Fun-A14B-Control-Camera.py)|[code](./model_training/full/Wan2.2-Fun-A14B-Control-Camera.sh)|[code](./model_training/validate_full/Wan2.2-Fun-A14B-Control-Camera.py)|[code](./model_training/lora/Wan2.2-Fun-A14B-Control-Camera.sh)|[code](./model_training/validate_lora/Wan2.2-Fun-A14B-Control-Camera.py)|
 |[Wan-AI/Wan2.1-T2V-1.3B](https://modelscope.cn/models/Wan-AI/Wan2.1-T2V-1.3B)||[code](./model_inference/Wan2.1-T2V-1.3B.py)|[code](./model_training/full/Wan2.1-T2V-1.3B.sh)|[code](./model_training/validate_full/Wan2.1-T2V-1.3B.py)|[code](./model_training/lora/Wan2.1-T2V-1.3B.sh)|[code](./model_training/validate_lora/Wan2.1-T2V-1.3B.py)|
 |[Wan-AI/Wan2.1-T2V-14B](https://modelscope.cn/models/Wan-AI/Wan2.1-T2V-14B)||[code](./model_inference/Wan2.1-T2V-14B.py)|[code](./model_training/full/Wan2.1-T2V-14B.sh)|[code](./model_training/validate_full/Wan2.1-T2V-14B.py)|[code](./model_training/lora/Wan2.1-T2V-14B.sh)|[code](./model_training/validate_lora/Wan2.1-T2V-14B.py)|
 |[Wan-AI/Wan2.1-I2V-14B-480P](https://modelscope.cn/models/Wan-AI/Wan2.1-I2V-14B-480P)|`input_image`|[code](./model_inference/Wan2.1-I2V-14B-480P.py)|[code](./model_training/full/Wan2.1-I2V-14B-480P.sh)|[code](./model_training/validate_full/Wan2.1-I2V-14B-480P.py)|[code](./model_training/lora/Wan2.1-I2V-14B-480P.sh)|[code](./model_training/validate_lora/Wan2.1-I2V-14B-480P.py)|

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/lora/Wan2.2-Fun-A14B-Control-Camera.sh

@@ -0,0 +1,39 @@
+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 \
+  --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_lora" \
+  --lora_base_model "dit" \
+  --lora_target_modules "q,k,v,o,ffn.0,ffn.2" \
+  --lora_rank 32 \
+  --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 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_lora" \
+  --lora_base_model "dit" \
+  --lora_target_modules "q,k,v,o,ffn.0,ffn.2" \
+  --lora_rank 32 \
+  --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/lora/Wan2.2-Fun-A14B-Control.sh

@@ -0,0 +1,39 @@
+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/Wan2.2-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_lora" \
+  --lora_base_model "dit" \
+  --lora_target_modules "q,k,v,o,ffn.0,ffn.2" \
+  --lora_rank 32 \
+  --extra_inputs "control_video,reference_image" \
+  --max_timestep_boundary 0.358 \
+  --min_timestep_boundary 0
+# boundary corresponds to timesteps [900, 1000]
+
+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/Wan2.2-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_lora" \
+  --lora_base_model "dit" \
+  --lora_target_modules "q,k,v,o,ffn.0,ffn.2" \
+  --lora_rank 32 \
+  --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/lora/Wan2.2-Fun-A14B-InP.sh

@@ -0,0 +1,37 @@
+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/Wan2.2-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_lora" \
+  --lora_base_model "dit" \
+  --lora_target_modules "q,k,v,o,ffn.0,ffn.2" \
+  --lora_rank 32 \
+  --extra_inputs "input_image,end_image" \
+  --max_timestep_boundary 0.358 \
+  --min_timestep_boundary 0
+# boundary corresponds to timesteps [900, 1000]
+
+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/Wan2.2-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_lora" \
+  --lora_base_model "dit" \
+  --lora_target_modules "q,k,v,o,ffn.0,ffn.2" \
+  --lora_rank 32 \
+  --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/validate_full/Wan2.2-Fun-A14B-Control-Camera.py

@@ -0,0 +1,34 @@
+import torch
+from PIL import Image
+from diffsynth import save_video, VideoData, load_state_dict
+from diffsynth.pipelines.wan_video_new import WanVideoPipeline, ModelConfig
+from modelscope import dataset_snapshot_download
+
+
+pipe = WanVideoPipeline.from_pretrained(
+    torch_dtype=torch.bfloat16,
+    device="cuda",
+    model_configs=[
+        ModelConfig(model_id="PAI/Wan2.2-Fun-A14B-Control-Camera", origin_file_pattern="high_noise_model/diffusion_pytorch_model*.safetensors", offload_device="cpu"),
+        ModelConfig(model_id="PAI/Wan2.2-Fun-A14B-Control-Camera", origin_file_pattern="low_noise_model/diffusion_pytorch_model*.safetensors", offload_device="cpu"),
+        ModelConfig(model_id="PAI/Wan2.2-Fun-A14B-Control-Camera", origin_file_pattern="models_t5_umt5-xxl-enc-bf16.pth", offload_device="cpu"),
+        ModelConfig(model_id="PAI/Wan2.2-Fun-A14B-Control-Camera", origin_file_pattern="Wan2.1_VAE.pth", offload_device="cpu"),
+    ],
+)
+state_dict = load_state_dict("models/train/Wan2.2-Fun-A14B-Control-Camera_high_noise_full/epoch-1.safetensors")
+pipe.dit.load_state_dict(state_dict)
+state_dict = load_state_dict("models/train/Wan2.2-Fun-A14B-Control-Camera_low_noise_full/epoch-1.safetensors")
+pipe.dit2.load_state_dict(state_dict)
+pipe.enable_vram_management()
+
+video = VideoData("data/example_video_dataset/video1.mp4", height=480, width=832)
+
+# First and last frame to video
+video = pipe(
+    prompt="from sunset to night, a small town, light, house, river",
+    negative_prompt="色调艳丽，过曝，静态，细节模糊不清，字幕，风格，作品，画作，画面，静止，整体发灰，最差质量，低质量，JPEG压缩残留，丑陋的，残缺的，多余的手指，画得不好的手部，画得不好的脸部，畸形的，毁容的，形态畸形的肢体，手指融合，静止不动的画面，杂乱的背景，三条腿，背景人很多，倒着走",
+    input_image=video[0],
+    camera_control_direction="Left", camera_control_speed=0.0,
+    seed=0, tiled=True
+)
+save_video(video, "video_Wan2.2-Fun-A14B-Control-Camera.mp4", fps=15, quality=5)

examples/wanvideo/model_training/validate_full/Wan2.2-Fun-A14B-Control.py

@@ -0,0 +1,35 @@
+import torch
+from PIL import Image
+from diffsynth import save_video, VideoData, load_state_dict
+from diffsynth.pipelines.wan_video_new import WanVideoPipeline, ModelConfig
+from modelscope import dataset_snapshot_download
+
+
+pipe = WanVideoPipeline.from_pretrained(
+    torch_dtype=torch.bfloat16,
+    device="cuda",
+    model_configs=[
+        ModelConfig(model_id="PAI/Wan2.2-Fun-A14B-Control", origin_file_pattern="high_noise_model/diffusion_pytorch_model*.safetensors", offload_device="cpu"),
+        ModelConfig(model_id="PAI/Wan2.2-Fun-A14B-Control", origin_file_pattern="low_noise_model/diffusion_pytorch_model*.safetensors", offload_device="cpu"),
+        ModelConfig(model_id="PAI/Wan2.2-Fun-A14B-Control", origin_file_pattern="models_t5_umt5-xxl-enc-bf16.pth", offload_device="cpu"),
+        ModelConfig(model_id="PAI/Wan2.2-Fun-A14B-Control", origin_file_pattern="Wan2.1_VAE.pth", offload_device="cpu"),
+    ],
+)
+state_dict = load_state_dict("models/train/Wan2.2-Fun-A14B-Control_high_noise_full/epoch-1.safetensors")
+pipe.dit.load_state_dict(state_dict)
+state_dict = load_state_dict("models/train/Wan2.2-Fun-A14B-Control_low_noise_full/epoch-1.safetensors")
+pipe.dit2.load_state_dict(state_dict)
+pipe.enable_vram_management()
+
+video = VideoData("data/example_video_dataset/video1_softedge.mp4", height=480, width=832)
+video = [video[i] for i in range(81)]
+reference_image = VideoData("data/example_video_dataset/video1.mp4", height=480, width=832)[0]
+
+# Control video
+video = pipe(
+    prompt="from sunset to night, a small town, light, house, river",
+    negative_prompt="色调艳丽，过曝，静态，细节模糊不清，字幕，风格，作品，画作，画面，静止，整体发灰，最差质量，低质量，JPEG压缩残留，丑陋的，残缺的，多余的手指，画得不好的手部，画得不好的脸部，畸形的，毁容的，形态畸形的肢体，手指融合，静止不动的画面，杂乱的背景，三条腿，背景人很多，倒着走",
+    control_video=video, reference_image=reference_image,
+    seed=1, tiled=True
+)
+save_video(video, "video_Wan2.2-Fun-A14B-Control.mp4", fps=15, quality=5)

examples/wanvideo/model_training/validate_full/Wan2.2-Fun-A14B-InP.py

@@ -0,0 +1,32 @@
+import torch
+from PIL import Image
+from diffsynth import save_video, VideoData, load_state_dict
+from diffsynth.pipelines.wan_video_new import WanVideoPipeline, ModelConfig
+from modelscope import dataset_snapshot_download
+
+
+pipe = WanVideoPipeline.from_pretrained(
+    torch_dtype=torch.bfloat16,
+    device="cuda",
+    model_configs=[
+        ModelConfig(model_id="PAI/Wan2.2-Fun-A14B-InP", origin_file_pattern="high_noise_model/diffusion_pytorch_model*.safetensors", offload_device="cpu"),
+        ModelConfig(model_id="PAI/Wan2.2-Fun-A14B-InP", origin_file_pattern="low_noise_model/diffusion_pytorch_model*.safetensors", offload_device="cpu"),
+        ModelConfig(model_id="PAI/Wan2.2-Fun-A14B-InP", origin_file_pattern="models_t5_umt5-xxl-enc-bf16.pth", offload_device="cpu"),
+        ModelConfig(model_id="PAI/Wan2.2-Fun-A14B-InP", origin_file_pattern="Wan2.1_VAE.pth", offload_device="cpu"),
+    ],
+)
+state_dict = load_state_dict("models/train/Wan2.2-Fun-A14B-InP_high_noise_full/epoch-1.safetensors")
+pipe.dit.load_state_dict(state_dict)
+state_dict = load_state_dict("models/train/Wan2.2-Fun-A14B-InP_low_noise_full/epoch-1.safetensors")
+pipe.dit2.load_state_dict(state_dict)
+pipe.enable_vram_management()
+video = VideoData("data/example_video_dataset/video1.mp4", height=480, width=832)
+
+# First and last frame to video
+video = pipe(
+    prompt="from sunset to night, a small town, light, house, river",
+    negative_prompt="色调艳丽，过曝，静态，细节模糊不清，字幕，风格，作品，画作，画面，静止，整体发灰，最差质量，低质量，JPEG压缩残留，丑陋的，残缺的，多余的手指，画得不好的手部，画得不好的脸部，畸形的，毁容的，形态畸形的肢体，手指融合，静止不动的画面，杂乱的背景，三条腿，背景人很多，倒着走",
+    input_image=video[0], end_image=video[80],
+    seed=0, tiled=True
+)
+save_video(video, "video_Wan2.2-Fun-A14B-InP.mp4", fps=15, quality=5)

examples/wanvideo/model_training/validate_lora/Wan2.2-Fun-A14B-Control-Camera.py

@@ -0,0 +1,32 @@
+import torch
+from PIL import Image
+from diffsynth import save_video, VideoData, load_state_dict
+from diffsynth.pipelines.wan_video_new import WanVideoPipeline, ModelConfig
+from modelscope import dataset_snapshot_download
+
+
+pipe = WanVideoPipeline.from_pretrained(
+    torch_dtype=torch.bfloat16,
+    device="cuda",
+    model_configs=[
+        ModelConfig(model_id="PAI/Wan2.2-Fun-A14B-Control-Camera", origin_file_pattern="high_noise_model/diffusion_pytorch_model*.safetensors", offload_device="cpu"),
+        ModelConfig(model_id="PAI/Wan2.2-Fun-A14B-Control-Camera", origin_file_pattern="low_noise_model/diffusion_pytorch_model*.safetensors", offload_device="cpu"),
+        ModelConfig(model_id="PAI/Wan2.2-Fun-A14B-Control-Camera", origin_file_pattern="models_t5_umt5-xxl-enc-bf16.pth", offload_device="cpu"),
+        ModelConfig(model_id="PAI/Wan2.2-Fun-A14B-Control-Camera", origin_file_pattern="Wan2.1_VAE.pth", offload_device="cpu"),
+    ],
+)
+pipe.load_lora(pipe.dit, "models/train/Wan2.2-Fun-A14B-Control-Camera_high_noise_lora/epoch-4.safetensors", alpha=1)
+pipe.load_lora(pipe.dit2, "models/train/Wan2.2-Fun-A14B-Control-Camera_low_noise_lora/epoch-4.safetensors", alpha=1)
+pipe.enable_vram_management()
+
+video = VideoData("data/example_video_dataset/video1.mp4", height=480, width=832)
+
+# First and last frame to video
+video = pipe(
+    prompt="from sunset to night, a small town, light, house, river",
+    negative_prompt="色调艳丽，过曝，静态，细节模糊不清，字幕，风格，作品，画作，画面，静止，整体发灰，最差质量，低质量，JPEG压缩残留，丑陋的，残缺的，多余的手指，画得不好的手部，画得不好的脸部，畸形的，毁容的，形态畸形的肢体，手指融合，静止不动的画面，杂乱的背景，三条腿，背景人很多，倒着走",
+    input_image=video[0],
+    camera_control_direction="Left", camera_control_speed=0.0,
+    seed=0, tiled=True
+)
+save_video(video, "video_Wan2.2-Fun-A14B-Control-Camera.mp4", fps=15, quality=5)

examples/wanvideo/model_training/validate_lora/Wan2.2-Fun-A14B-Control.py

@@ -0,0 +1,33 @@
+import torch
+from PIL import Image
+from diffsynth import save_video, VideoData
+from diffsynth.pipelines.wan_video_new import WanVideoPipeline, ModelConfig
+from modelscope import dataset_snapshot_download
+
+
+pipe = WanVideoPipeline.from_pretrained(
+    torch_dtype=torch.bfloat16,
+    device="cuda",
+    model_configs=[
+        ModelConfig(model_id="PAI/Wan2.2-Fun-A14B-Control", origin_file_pattern="high_noise_model/diffusion_pytorch_model*.safetensors", offload_device="cpu"),
+        ModelConfig(model_id="PAI/Wan2.2-Fun-A14B-Control", origin_file_pattern="low_noise_model/diffusion_pytorch_model*.safetensors", offload_device="cpu"),
+        ModelConfig(model_id="PAI/Wan2.2-Fun-A14B-Control", origin_file_pattern="models_t5_umt5-xxl-enc-bf16.pth", offload_device="cpu"),
+        ModelConfig(model_id="PAI/Wan2.2-Fun-A14B-Control", origin_file_pattern="Wan2.1_VAE.pth", offload_device="cpu"),
+    ],
+)
+pipe.load_lora(pipe.dit, "models/train/Wan2.2-Fun-A14B-Control_high_noise_lora/epoch-4.safetensors", alpha=1)
+pipe.load_lora(pipe.dit2, "models/train/Wan2.2-Fun-A14B-Control_low_noise_lora/epoch-4.safetensors", alpha=1)
+pipe.enable_vram_management()
+
+video = VideoData("data/example_video_dataset/video1_softedge.mp4", height=480, width=832)
+video = [video[i] for i in range(81)]
+reference_image = VideoData("data/example_video_dataset/video1.mp4", height=480, width=832)[0]
+
+# Control video
+video = pipe(
+    prompt="from sunset to night, a small town, light, house, river",
+    negative_prompt="色调艳丽，过曝，静态，细节模糊不清，字幕，风格，作品，画作，画面，静止，整体发灰，最差质量，低质量，JPEG压缩残留，丑陋的，残缺的，多余的手指，画得不好的手部，画得不好的脸部，畸形的，毁容的，形态畸形的肢体，手指融合，静止不动的画面，杂乱的背景，三条腿，背景人很多，倒着走",
+    control_video=video, reference_image=reference_image,
+    seed=1, tiled=True
+)
+save_video(video, "video_Wan2.2-Fun-A14B-Control.mp4", fps=15, quality=5)

examples/wanvideo/model_training/validate_lora/Wan2.2-Fun-A14B-InP.py

@@ -0,0 +1,31 @@
+import torch
+from PIL import Image
+from diffsynth import save_video, VideoData
+from diffsynth.pipelines.wan_video_new import WanVideoPipeline, ModelConfig
+from modelscope import dataset_snapshot_download
+
+
+pipe = WanVideoPipeline.from_pretrained(
+    torch_dtype=torch.bfloat16,
+    device="cuda",
+    model_configs=[
+        ModelConfig(model_id="PAI/Wan2.2-Fun-A14B-InP", origin_file_pattern="high_noise_model/diffusion_pytorch_model*.safetensors", offload_device="cpu"),
+        ModelConfig(model_id="PAI/Wan2.2-Fun-A14B-InP", origin_file_pattern="low_noise_model/diffusion_pytorch_model*.safetensors", offload_device="cpu"),
+        ModelConfig(model_id="PAI/Wan2.2-Fun-A14B-InP", origin_file_pattern="models_t5_umt5-xxl-enc-bf16.pth", offload_device="cpu"),
+        ModelConfig(model_id="PAI/Wan2.2-Fun-A14B-InP", origin_file_pattern="Wan2.1_VAE.pth", offload_device="cpu"),
+    ],
+)
+pipe.load_lora(pipe.dit, "models/train/Wan2.2-Fun-A14B-InP_high_noise_lora/epoch-4.safetensors", alpha=1)
+pipe.load_lora(pipe.dit2, "models/train/Wan2.2-Fun-A14B-InP_low_noise_lora/epoch-4.safetensors", alpha=1)
+pipe.enable_vram_management()
+
+video = VideoData("data/example_video_dataset/video1.mp4", height=480, width=832)
+
+# First and last frame to video
+video = pipe(
+    prompt="from sunset to night, a small town, light, house, river",
+    negative_prompt="色调艳丽，过曝，静态，细节模糊不清，字幕，风格，作品，画作，画面，静止，整体发灰，最差质量，低质量，JPEG压缩残留，丑陋的，残缺的，多余的手指，画得不好的手部，画得不好的脸部，畸形的，毁容的，形态畸形的肢体，手指融合，静止不动的画面，杂乱的背景，三条腿，背景人很多，倒着走",
+    input_image=video[0], end_image=video[80],
+    seed=0, tiled=True
+)
+save_video(video, "video_Wan2.2-Fun-A14B-InP.mp4", fps=15, quality=5)