Image inference Error

[ImmNaruto]

Hello, how can I use stdit-v3/v4 weights for image inference in versions 1.2 and 1.3? In version 1.1, it’s possible to specify the parameters image-size and num_frames=1 for inference, but in versions 1.2 and 1.3, this causes an error. Attached are the command and the error.

command：

python scripts/inference.py configs/opensora-v1-2/inference/sample.py --num-frames 1  --image-size 720 1280 --prompt "A beautiful sunset over the city"

error:

Traceback (most recent call last):
  File "/data/home/Open-Sora/scripts/inference.py", line 383, in <module>
    main()
  File "/data/home/Open-Sora/scripts/inference.py", line 47, in main
    cfg = parse_configs(training=False)
  File "/data/home/.conda/envs/opensora/lib/python3.9/site-packages/opensora/utils/config_utils.py", line 188, in parse_configs
    cfg = merge_args(cfg, args, training)
  File "/data/home/.conda/envs/opensora/lib/python3.9/site-packages/opensora/utils/config_utils.py", line 171, in merge_args
    assert int(args.num_frames) in [49, 65, 81, 97, 113], f"--num-frames must be any of [49, 65, 81, 97, 113]"
AssertionError: --num-frames must be any of [49, 65, 81, 97, 113

[github-actions[bot]]

This issue is stale because it has been open for 7 days with no activity.

[github-actions[bot]]

This issue was closed because it has been inactive for 7 days since being marked as stale.