Open
Description
metadata.csv
video,prompt
test.png,"dog"
accelerate launch examples/wanvideo/model_training/train.py \
--dataset_base_path data/wan/train_datav6 \
--dataset_metadata_path data/wan/train_datav6/metadata.csv \
--height 512 \
--width 512 \
--num_frames 1 \
--dataset_repeat 100 \
--model_paths '[
[
"models/Wan-AI/Wan2.1-T2V-14B/diffusion_pytorch_model-00001-of-00006.safetensors",
"models/Wan-AI/Wan2.1-T2V-14B/diffusion_pytorch_model-00002-of-00006.safetensors",
"models/Wan-AI/Wan2.1-T2V-14B/diffusion_pytorch_model-00003-of-00006.safetensors",
"models/Wan-AI/Wan2.1-T2V-14B/diffusion_pytorch_model-00004-of-00006.safetensors",
"models/Wan-AI/Wan2.1-T2V-14B/diffusion_pytorch_model-00005-of-00006.safetensors",
"models/Wan-AI/Wan2.1-T2V-14B/diffusion_pytorch_model-00006-of-00006.safetensors"
],
"models/Wan-AI/Wan2.1-T2V-14B/models_t5_umt5-xxl-enc-bf16.pth",
"models/Wan-AI/Wan2.1-T2V-14B/Wan2.1_VAE.pth"
]' \
--learning_rate 1e-4 \
--num_epochs 10 \
--remove_prefix_in_ckpt "pipe.dit." \
--output_path "./models/train/Wan2.1-T2V-14B_lora" \
--lora_base_model "dit" \
--lora_target_modules "q,k,v,o,ffn.0,ffn.2" \
--lora_rank 32(wan) root@iv-ydxqk42iv4qbxys524xd:~/DiffSynth-Studio# ./Wan2.1-T2V-14B_train.sh
The following values were not passed to `accelerate launch` and had defaults used instead:
`--num_processes` was set to a value of `1`
`--num_machines` was set to a value of `1`
`--mixed_precision` was set to a value of `'no'`
`--dynamo_backend` was set to a value of `'no'`
To avoid this warning pass in values for each of the problematic parameters or run `accelerate config`.
Height and width are fixed. Setting `dynamic_resolution` to False.
Loading models from: ['models/Wan-AI/Wan2.1-T2V-14B/diffusion_pytorch_model-00001-of-00006.safetensors', 'models/Wan-AI/Wan2.1-T2V-14B/diffusion_pytorch_model-00002-of-00006.safetensors', 'models/Wan-AI/Wan2.1-T2V-14B/diffusion_pytorch_model-00003-of-00006.safetensors', 'models/Wan-AI/Wan2.1-T2V-14B/diffusion_pytorch_model-00004-of-00006.safetensors', 'models/Wan-AI/Wan2.1-T2V-14B/diffusion_pytorch_model-00005-of-00006.safetensors', 'models/Wan-AI/Wan2.1-T2V-14B/diffusion_pytorch_model-00006-of-00006.safetensors']
model_name: wan_video_dit model_class: WanModel
This model is initialized with extra kwargs: {'has_image_input': False, 'patch_size': [1, 2, 2], 'in_dim': 16, 'dim': 5120, 'ffn_dim': 13824, 'freq_dim': 256, 'text_dim': 4096, 'out_dim': 16, 'num_heads': 40, 'num_layers': 40, 'eps': 1e-06}
The following models are loaded: ['wan_video_dit'].
Loading models from: models/Wan-AI/Wan2.1-T2V-14B/models_t5_umt5-xxl-enc-bf16.pth
model_name: wan_video_text_encoder model_class: WanTextEncoder
The following models are loaded: ['wan_video_text_encoder'].
Loading models from: models/Wan-AI/Wan2.1-T2V-14B/Wan2.1_VAE.pth
model_name: wan_video_vae model_class: WanVideoVAE
The following models are loaded: ['wan_video_vae'].
Using wan_video_text_encoder from models/Wan-AI/Wan2.1-T2V-14B/models_t5_umt5-xxl-enc-bf16.pth.
Using wan_video_dit from ['models/Wan-AI/Wan2.1-T2V-14B/diffusion_pytorch_model-00001-of-00006.safetensors', 'models/Wan-AI/Wan2.1-T2V-14B/diffusion_pytorch_model-00002-of-00006.safetensors', 'models/Wan-AI/Wan2.1-T2V-14B/diffusion_pytorch_model-00003-of-00006.safetensors', 'models/Wan-AI/Wan2.1-T2V-14B/diffusion_pytorch_model-00004-of-00006.safetensors', 'models/Wan-AI/Wan2.1-T2V-14B/diffusion_pytorch_model-00005-of-00006.safetensors', 'models/Wan-AI/Wan2.1-T2V-14B/diffusion_pytorch_model-00006-of-00006.safetensors'].
Using wan_video_vae from models/Wan-AI/Wan2.1-T2V-14B/Wan2.1_VAE.pth.
No wan_video_image_encoder models available.
No wan_video_motion_controller models available.
No wan_video_vace models available.
Downloading Model from https://www.modelscope.cn to directory: /root/DiffSynth-Studio/models/Wan-AI/Wan2.1-T2V-1.3B
2025-06-13 17:37:23,743 - modelscope - INFO - Target directory already exists, skipping creation.
0%| | 0/1600 [00:00<?, ?it/s]
Traceback (most recent call last):
File "/root/DiffSynth-Studio/examples/wanvideo/model_training/train.py", line 113, in <module>
launch_training_task(model, dataset, args=args)
File "/root/DiffSynth-Studio/diffsynth/trainers/utils.py", line 202, in launch_training_task
loss = model(data)
File "/root/Wan2.1/wan/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1739, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "/root/Wan2.1/wan/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1750, in _call_impl
return forward_call(*args, **kwargs)
File "/root/DiffSynth-Studio/examples/wanvideo/model_training/train.py", line 93, in forward
if inputs is None: inputs = self.forward_preprocess(data)
File "/root/DiffSynth-Studio/examples/wanvideo/model_training/train.py", line 63, in forward_preprocess
"height": data["video"][0].size[1],
TypeError: 'Image' object is not subscriptable
Traceback (most recent call last):
File "/root/Wan2.1/wan/bin/accelerate", line 8, in <module>
sys.exit(main())
File "/root/Wan2.1/wan/lib/python3.10/site-packages/accelerate/commands/accelerate_cli.py", line 50, in main
args.func(args)
File "/root/Wan2.1/wan/lib/python3.10/site-packages/accelerate/commands/launch.py", line 1198, in launch_command
simple_launcher(args)
File "/root/Wan2.1/wan/lib/python3.10/site-packages/accelerate/commands/launch.py", line 785, in simple_launcher
raise subprocess.CalledProcessError(returncode=process.returncode, cmd=cmd)
subprocess.CalledProcessError: Command '['/root/Wan2.1/wan/bin/python3', 'examples/wanvideo/model_training/train.py', '--dataset_base_path', 'data/wan/train_datav6', '--dataset_metadata_path', 'data/wan/train_datav6/metadata.csv', '--height', '512', '--width', '512', '--num_frames', '1', '--dataset_repeat', '100', '--model_paths', '[\n [\n "models/Wan-AI/Wan2.1-T2V-14B/diffusion_pytorch_model-00001-of-00006.safetensors",\n "models/Wan-AI/Wan2.1-T2V-14B/diffusion_pytorch_model-00002-of-00006.safetensors",\n "models/Wan-AI/Wan2.1-T2V-14B/diffusion_pytorch_model-00003-of-00006.safetensors",\n "models/Wan-AI/Wan2.1-T2V-14B/diffusion_pytorch_model-00004-of-00006.safetensors",\n "models/Wan-AI/Wan2.1-T2V-14B/diffusion_pytorch_model-00005-of-00006.safetensors",\n "models/Wan-AI/Wan2.1-T2V-14B/diffusion_pytorch_model-00006-of-00006.safetensors"\n ],\n "models/Wan-AI/Wan2.1-T2V-14B/models_t5_umt5-xxl-enc-bf16.pth",\n "models/Wan-AI/Wan2.1-T2V-14B/Wan2.1_VAE.pth"\n]', '--learning_rate', '1e-4', '--num_epochs', '10', '--remove_prefix_in_ckpt', 'pipe.dit.', '--output_path', './models/train/Wan2.1-T2V-14B_lora', '--lora_base_model', 'dit', '--lora_target_modules', 'q,k,v,o,ffn.0,ffn.2', '--lora_rank', '32']' returned non-zero exit status 1.
(wan) root@iv-ydxqk42iv4qbxys524xd:~/DiffSynth-Studio# Metadata
Metadata
Assignees
Labels
No labels