Got KeyError: `video_fps`

Previously it ran for the same input video, but after that for next inferences gave error.
```
(seedvr) root@98cb7f06e6e4:/workspace/SeedVR# torchrun --nproc-per-node=$NUM_GPUS projects/inference_seedvr2_7b.py --video_path $INPUT_FOLDER --output_dir $OUTPUT_FOLDER --seed $SEED_NUM --res_h $OUTPUT_HEIGHT --res_w $OUTPUT_WIDTH --sp_size $NUM_SP
/workspace/SeedVR
Note!!!!!! Color fix is not avaliable!
2025-07-08 08:18:53,887 [MainThread][common.decorators][INFO] Entering configure_dit_model
Loading pretrained ckpt from ./ckpts/seedvr2_ema_7b.pth
Loading info:
DiT trainable parameters: 8,239,607,872
2025-07-08 08:19:52,337 [MainThread][common.decorators][INFO] Completed configure_dit_model in 58.047 seconds.
2025-07-08 08:19:52,337 [MainThread][common.decorators][INFO] Entering configure_vae_model
/root/miniconda3/envs/seedvr/lib/python3.10/site-packages/diffusers/models/transformers/transformer_2d.py:34: FutureWarning: `Transformer2DModelOutput` is deprecated and will be removed in version 1.0.0. Importing `Transformer2DModelOutput` from `diffusers.models.transformer_2d` is deprecated and this will be removed in a future version. Please use `from diffusers.models.modeling_outputs import Transformer2DModelOutput`, instead.
deprecate("Transformer2DModelOutput", "1.0.0", deprecation_message)
slicing_up_num: 0
2025-07-08 08:19:55,167 [MainThread][common.decorators][INFO] Completed configure_vae_model in 2.829 seconds.
Total prompts to be generated: 2
100%|███████████████████████████████████████████████████████████████████| 2/2 [00:00<00:00, 2026.72it/s]
0it [00:00, ?it/s]
[rank0]: Traceback (most recent call last):
[rank0]: File "/workspace/SeedVR/projects/inference_seedvr2_7b.py", line 336, in
[rank0]: generation_loop(runner, **vars(args))
[rank0]: File "/workspace/SeedVR/projects/inference_seedvr2_7b.py", line 263, in generation_loop
[rank0]: fps_lists.append(info["video_fps"] if out_fps is None else out_fps)
[rank0]: KeyError: 'video_fps'
E0708 08:20:01.457000 124280254744384 torch/distributed/elastic/multiprocessing/api.py:826] failed (exitcode: 1) local_rank: 0 (pid: 5634) of binary: /root/miniconda3/envs/seedvr/bin/python3.10
Traceback (most recent call last):
File "/root/miniconda3/envs/seedvr/bin/torchrun", line 8, in
sys.exit(main())
File "/root/miniconda3/envs/seedvr/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/errors/__init__.py", line 347, in wrapper
return f(*args, **kwargs)
File "/root/miniconda3/envs/seedvr/lib/python3.10/site-packages/torch/distributed/run.py", line 879, in main
run(args)
File "/root/miniconda3/envs/seedvr/lib/python3.10/site-packages/torch/distributed/run.py", line 870, in run
elastic_launch(
File "/root/miniconda3/envs/seedvr/lib/python3.10/site-packages/torch/distributed/launcher/api.py", line 132, in __call__
return launch_agent(self._config, self._entrypoint, list(args))
File "/root/miniconda3/envs/seedvr/lib/python3.10/site-packages/torch/distributed/launcher/api.py", line 263, in launch_agent
raise ChildFailedError(
torch.distributed.elastic.multiprocessing.errors.ChildFailedError:
============================================================
projects/inference_seedvr2_7b.py FAILED
------------------------------------------------------------
Failures:

------------------------------------------------------------
Root Cause (first observed failure):
[0]:
time : 2025-07-08_08:20:01
host : 98cb7f06e6e4
rank : 0 (local_rank: 0)
exitcode : 1 (pid: 5634)
error_file:
traceback : To enable traceback see: https://pytorch.org/docs/stable/elastic/errors.html
============================================================
```