$ /lustre/fsw/portfolios/nvr/users/shyang/miniconda3/envs/diffusion-pipe/bin/python /lustre/fs1/portfolios/nvr/projects/nvr_elm_llm/users/shyang/FastVideo_LoRA/SCOPE/inference.py --model_dir /lustre/fs1/portfolios/nvr/projects/nvr_elm_llm/users/shyang/FastVideo_LoRA/models/SCOPE --input_image /lustre/fs1/portfolios/nvr/projects/nvr_elm_llm/users/shyang/FastVideo_LoRA/SCOPE/examples/example_2/image.png --action_path /lustre/fs1/portfolios/nvr/projects/nvr_elm_llm/users/shyang/FastVideo_LoRA/SCOPE/examples/example_2/action.parquet --prompt 'In a mist-shrouded, rain-soaked mountain valley, a tactical rifle is held firmly in the player'"'"'s hand, aiming down a stone-paved path towards a monumental gate. The scene is filled with ancient stone statues, lanterns, and a distant Asian-style temple framed by towering cliffs, all shrouded in fog and lit by the glow of torches, creating an atmosphere of mystery and looming danger.' --output_dir /lustre/fs1/portfolios/nvr/projects/nvr_elm_llm/users/shyang/FastVideo_LoRA/outputs/scope_fastvideo/full/runs/example_2/scope_30step --height 480 --width 832 --max_frames 81 --num_inference_steps 30 --seed 0 --fps 20 --dmd_denoising_steps 1000,757,522 --comparison_mode

/lustre/fsw/portfolios/nvr/users/shyang/miniconda3/envs/diffusion-pipe/lib/python3.12/site-packages/torch/cuda/__init__.py:61: FutureWarning: The pynvml package is deprecated. Please install nvidia-ml-py instead. If you did not install pynvml directly, please report this to the maintainers of the package that installed pynvml for you.
  import pynvml  # type: ignore[import]
Loading models from: "/lustre/fs1/portfolios/nvr/projects/nvr_elm_llm/users/shyang/FastVideo_LoRA/models/SCOPE/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: "/lustre/fs1/portfolios/nvr/projects/nvr_elm_llm/users/shyang/FastVideo_LoRA/models/SCOPE/Wan2.2_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.WanVideoVAE38",
    "extra_kwargs": null
}
Using wan_video_text_encoder from "/lustre/fs1/portfolios/nvr/projects/nvr_elm_llm/users/shyang/FastVideo_LoRA/models/SCOPE/models_t5_umt5-xxl-enc-bf16.pth".
No wan_video_dit models available. This is not an error.
Using wan_video_vae from "/lustre/fs1/portfolios/nvr/projects/nvr_elm_llm/users/shyang/FastVideo_LoRA/models/SCOPE/Wan2.2_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.
No wan_video_vace models available. This is not an error.
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.

VAE encoding:   0%|          | 0/1 [00:00<?, ?it/s]
VAE encoding: 100%|██████████| 1/1 [00:00<00:00,  8.15it/s]
VAE encoding: 100%|██████████| 1/1 [00:00<00:00,  8.13it/s]

  0%|          | 0/30 [00:00<?, ?it/s]
  3%|▎         | 1/30 [00:00<00:25,  1.13it/s]
  7%|▋         | 2/30 [00:01<00:24,  1.14it/s]
 10%|█         | 3/30 [00:02<00:23,  1.15it/s]
 13%|█▎        | 4/30 [00:03<00:22,  1.15it/s]
 17%|█▋        | 5/30 [00:04<00:21,  1.15it/s]
 20%|██        | 6/30 [00:05<00:20,  1.15it/s]
 23%|██▎       | 7/30 [00:06<00:20,  1.15it/s]
 27%|██▋       | 8/30 [00:06<00:19,  1.15it/s]
 30%|███       | 9/30 [00:07<00:18,  1.15it/s]
 33%|███▎      | 10/30 [00:08<00:17,  1.15it/s]
 37%|███▋      | 11/30 [00:09<00:16,  1.15it/s]
 40%|████      | 12/30 [00:10<00:15,  1.15it/s]
 43%|████▎     | 13/30 [00:11<00:14,  1.14it/s]
 47%|████▋     | 14/30 [00:12<00:13,  1.14it/s]
 50%|█████     | 15/30 [00:13<00:13,  1.14it/s]
 53%|█████▎    | 16/30 [00:13<00:12,  1.15it/s]
 57%|█████▋    | 17/30 [00:14<00:11,  1.15it/s]
 60%|██████    | 18/30 [00:15<00:10,  1.14it/s]
 63%|██████▎   | 19/30 [00:16<00:09,  1.14it/s]
 67%|██████▋   | 20/30 [00:17<00:08,  1.14it/s]
 70%|███████   | 21/30 [00:18<00:07,  1.14it/s]
 73%|███████▎  | 22/30 [00:19<00:06,  1.14it/s]
 77%|███████▋  | 23/30 [00:20<00:06,  1.14it/s]
 80%|████████  | 24/30 [00:20<00:05,  1.14it/s]
 83%|████████▎ | 25/30 [00:21<00:04,  1.14it/s]
 87%|████████▋ | 26/30 [00:22<00:03,  1.14it/s]
 90%|█████████ | 27/30 [00:23<00:02,  1.14it/s]
 93%|█████████▎| 28/30 [00:24<00:01,  1.14it/s]
 97%|█████████▋| 29/30 [00:25<00:00,  1.14it/s]
100%|██████████| 30/30 [00:26<00:00,  1.14it/s]
100%|██████████| 30/30 [00:26<00:00,  1.14it/s]

VAE decoding:   0%|          | 0/1 [00:00<?, ?it/s]
VAE decoding: 100%|██████████| 1/1 [00:02<00:00,  2.02s/it]
VAE decoding: 100%|██████████| 1/1 [00:02<00:00,  2.02s/it]

Saving video:   0%|          | 0/81 [00:00<?, ?it/s]
Saving video:   1%|          | 1/81 [00:00<00:08,  9.36it/s]
Saving video:  79%|███████▉  | 64/81 [00:00<00:00, 361.23it/s]
Saving video: 100%|██████████| 81/81 [00:00<00:00, 301.06it/s]