logs/rigid_500rep.log

┌──────────────────────────────────────────────────────────────────────┐
│ DiffSynth-Studio Model Downloader Configuration:                     │
│                                                                      │
│ [√] Download from https://modelscope.cn/                             │
│     (default behavior)                                               │
│ [ ] Download from https://modelscope.ai/                             │
│     (enabled via `export MODELSCOPE_ENDPOINT=https://modelscope.ai`) │
│ [ ] Download from https://huggingface.co/                            │
│     (enabled via `export DIFFSYNTH_DOWNLOAD_SOURCE=HuggingFace`)     │
│ [ ] Skip download and load only pre-downloaded model files           │
│     (enabled via `export DIFFSYNTH_SKIP_DOWNLOAD=True`)              │
└──────────────────────────────────────────────────────────────────────┘
Loading models from: "/home/quang/.cache/huggingface/hub/models--Wan-AI--Wan2.1-VACE-1.3B/snapshots/574e6a744642ce3bee319afc31496b88bde8aac4/diffusion_pytorch_model.safetensors"
Loaded model: {
    "model_name": "wan_video_dit",
    "model_class": "diffsynth.models.wan_video_dit.WanModel",
    "extra_kwargs": {
        "has_image_input": false,
        "patch_size": [
            1,
            2,
            2
        ],
        "in_dim": 16,
        "dim": 1536,
        "ffn_dim": 8960,
        "freq_dim": 256,
        "text_dim": 4096,
        "out_dim": 16,
        "num_heads": 12,
        "num_layers": 30,
        "eps": 1e-06
    }
}
Loaded model: {
    "model_name": "wan_video_vace",
    "model_class": "diffsynth.models.wan_video_vace.VaceWanModel",
    "extra_kwargs": null
}
Loading models from: "/home/quang/.cache/huggingface/hub/models--Wan-AI--Wan2.1-VACE-1.3B/snapshots/574e6a744642ce3bee319afc31496b88bde8aac4/models_t5_umt5-xxl-enc-bf16.pth"
Detected non-safetensors files, which may cause slower loading. It's recommended to convert it to a safetensors file.
Loaded model: {
    "model_name": "wan_video_text_encoder",
    "model_class": "diffsynth.models.wan_video_text_encoder.WanTextEncoder",
    "extra_kwargs": null
}
Loading models from: "/home/quang/.cache/huggingface/hub/models--Wan-AI--Wan2.1-VACE-1.3B/snapshots/574e6a744642ce3bee319afc31496b88bde8aac4/Wan2.1_VAE.pth"
Detected non-safetensors files, which may cause slower loading. It's recommended to convert it to a safetensors file.
Loaded model: {
    "model_name": "wan_video_vae",
    "model_class": "diffsynth.models.wan_video_vae.WanVideoVAE",
    "extra_kwargs": null
}
Using wan_video_text_encoder from "/home/quang/.cache/huggingface/hub/models--Wan-AI--Wan2.1-VACE-1.3B/snapshots/574e6a744642ce3bee319afc31496b88bde8aac4/models_t5_umt5-xxl-enc-bf16.pth".
Using wan_video_dit from "/home/quang/.cache/huggingface/hub/models--Wan-AI--Wan2.1-VACE-1.3B/snapshots/574e6a744642ce3bee319afc31496b88bde8aac4/diffusion_pytorch_model.safetensors".
Using wan_video_vae from "/home/quang/.cache/huggingface/hub/models--Wan-AI--Wan2.1-VACE-1.3B/snapshots/574e6a744642ce3bee319afc31496b88bde8aac4/Wan2.1_VAE.pth".
No wan_video_image_encoder models available. This is not an error.
No wan_video_motion_controller models available. This is not an error.
Using wan_video_vace from "/home/quang/.cache/huggingface/hub/models--Wan-AI--Wan2.1-VACE-1.3B/snapshots/574e6a744642ce3bee319afc31496b88bde8aac4/diffusion_pytorch_model.safetensors".
No wan_video_vap models available. This is not an error.
No wans2v_audio_encoder models available. This is not an error.
No wan_video_animate_adapter models available. This is not an error.
0 LoRA layers are cleared.
150 tensors are fused by LoRA. Fused LoRA layers cannot be cleared by `pipe.clear_lora()`.
LoRA fused: max |delta| on vace_blocks.0.cross_attn.q = 5.463e-03

VAE encoding:   0%|          | 0/9 [00:00<?, ?it/s]
VAE encoding:  11%|█         | 1/9 [00:00<00:05,  1.45it/s]
VAE encoding:  22%|██▏       | 2/9 [00:01<00:03,  1.97it/s]
VAE encoding:  33%|███▎      | 3/9 [00:01<00:02,  2.25it/s]
VAE encoding:  44%|████▍     | 4/9 [00:01<00:02,  2.49it/s]
VAE encoding:  56%|█████▌    | 5/9 [00:02<00:01,  2.62it/s]
VAE encoding:  67%|██████▋   | 6/9 [00:02<00:01,  2.67it/s]
VAE encoding:  78%|███████▊  | 7/9 [00:02<00:00,  2.67it/s]
VAE encoding:  89%|████████▉ | 8/9 [00:03<00:00,  2.74it/s]
VAE encoding: 100%|██████████| 9/9 [00:03<00:00,  2.76it/s]
VAE encoding: 100%|██████████| 9/9 [00:03<00:00,  2.53it/s]

VAE encoding:   0%|          | 0/9 [00:00<?, ?it/s]
VAE encoding:  11%|█         | 1/9 [00:00<00:02,  2.87it/s]
VAE encoding:  22%|██▏       | 2/9 [00:00<00:02,  2.76it/s]
VAE encoding:  33%|███▎      | 3/9 [00:01<00:02,  2.73it/s]
VAE encoding:  44%|████▍     | 4/9 [00:01<00:01,  2.77it/s]
VAE encoding:  56%|█████▌    | 5/9 [00:01<00:01,  2.85it/s]
VAE encoding:  67%|██████▋   | 6/9 [00:02<00:01,  2.84it/s]
VAE encoding:  78%|███████▊  | 7/9 [00:02<00:00,  2.84it/s]
VAE encoding:  89%|████████▉ | 8/9 [00:02<00:00,  2.84it/s]
VAE encoding: 100%|██████████| 9/9 [00:03<00:00,  2.83it/s]
VAE encoding: 100%|██████████| 9/9 [00:03<00:00,  2.82it/s]

VAE encoding:   0%|          | 0/9 [00:00<?, ?it/s]
VAE encoding:  33%|███▎      | 3/9 [00:00<00:00, 24.74it/s]
VAE encoding:  67%|██████▋   | 6/9 [00:00<00:00, 27.44it/s]
VAE encoding: 100%|██████████| 9/9 [00:00<00:00, 26.48it/s]
VAE encoding: 100%|██████████| 9/9 [00:00<00:00, 26.43it/s]

  0%|          | 0/30 [00:00<?, ?it/s]
  3%|▎         | 1/30 [00:02<01:21,  2.81s/it]
  7%|▋         | 2/30 [00:05<01:20,  2.89s/it]
 10%|█         | 3/30 [00:08<01:19,  2.93s/it]
 13%|█▎        | 4/30 [00:11<01:16,  2.95s/it]
 17%|█▋        | 5/30 [00:14<01:14,  2.96s/it]
 20%|██        | 6/30 [00:17<01:11,  2.97s/it]
 23%|██▎       | 7/30 [00:20<01:08,  2.97s/it]
 27%|██▋       | 8/30 [00:23<01:05,  2.97s/it]
 30%|███       | 9/30 [00:26<01:02,  2.97s/it]
 33%|███▎      | 10/30 [00:29<00:59,  2.98s/it]
 37%|███▋      | 11/30 [00:32<00:56,  2.98s/it]
 40%|████      | 12/30 [00:35<00:53,  2.98s/it]
 43%|████▎     | 13/30 [00:38<00:50,  2.99s/it]
 47%|████▋     | 14/30 [00:41<00:47,  2.99s/it]
 50%|█████     | 15/30 [00:44<00:44,  2.99s/it]
 53%|█████▎    | 16/30 [00:47<00:41,  2.98s/it]
 57%|█████▋    | 17/30 [00:50<00:38,  2.99s/it]
 60%|██████    | 18/30 [00:53<00:35,  2.99s/it]
 63%|██████▎   | 19/30 [00:56<00:32,  2.99s/it]