Replace deprecated v2.ToTensor() in wan_matrix_game2_runner.py with v2.ToImage() + v2.ToDtype(scale=True)

[xyf5432]

Summary

lightx2v/models/runners/wan/wan_matrix_game2_runner.py:160 (WanSFMtxg2Runner.__init__) instantiates torchvision.transforms.v2.ToTensor(), which is a deprecated alias: constructing it emits a UserWarning on every instantiation:

self.frame_process = v2.Compose(
    [
        v2.Resize(size=(352, 640), antialias=True),
        v2.ToTensor(),          # ← emits UserWarning on construction
        v2.Normalize(mean=[0.5, 0.5, 0.5], std=[0.5, 0.5, 0.5]),
    ]
)

Warning text (verified on torchvision 0.26.0):

The transform ToTensor() is deprecated and will be removed in a future release. Instead, please use v2.Compose([v2.ToImage(), v2.ToDtype(torch.float32, scale=True)]).

This warning has been present since torchvision 0.15 (when the v2 namespace was introduced) — torchvision/transforms/v2/_deprecated.py has called warnings.warn in ToTensor.__init__ since the first release. Because WanSFMtxg2Runner is constructed when the runner is registered, every run of this runner surfaces the warning.

Proposed fix

Replace v2.ToTensor() with the officially recommended equivalent inside the same v2.Compose:

self.frame_process = v2.Compose(
    [
        v2.Resize(size=(352, 640), antialias=True),
        v2.ToImage(),
        v2.ToDtype(torch.float32, scale=True),
        v2.Normalize(mean=[0.5, 0.5, 0.5], std=[0.5, 0.5, 0.5]),
    ]
)

Validation (torchvision 0.26.0+cpu)

• v2.ToTensor()(img) and v2.Compose([v2.ToImage(), v2.ToDtype(torch.float32, scale=True)])(img) produce identical output up to float precision: max abs diff = 5.96e-8 (a single last-bit rounding difference on uint8→float32 scaling; the official deprecation message itself states "Output is equivalent up to float precision").
• The full pipeline (Resize + ToTensor/ToImage+ToDtype + Normalize) produces the same outputs (max diff 5.96e-8).
• With warnings.simplefilter("error", UserWarning): the current code raises the deprecation UserWarning; the proposed pipeline constructs and runs cleanly.

Impact

• No deprecation UserWarning when instantiating the Matrix-Game-2 runner; no behavior change to preprocessing.

References

• torchvision docs: v2.ToTensor (deprecated) — "[DEPRECATED] Use v2.Compose([v2.ToImage(), v2.ToDtype(torch.float32, scale=True)]) instead."
• torchvision 0.16 release notes — v2 transforms design stabilized; ToImage/ToDtype introduced as the recommended replacement.
• torchvision source torchvision/transforms/v2/_deprecated.py — warnings.warn in ToTensor.__init__, present since 0.15.