LTXV can produce latents with odd H or W (e.g. 11x20) which can't be
divided into 2x2 patches. Patchify now pads odd dims to even using
replicate padding before rearranging, and unpatchify crops back to the
original size. This keeps patch_size=2 consistent between calibration
and inference for all models.
LTXAV uses a flattened 1D latent layout (e.g. [1, 1, 466048]) where
spatial H/W < 2, making 2x2 patchification impossible. patchify() now
returns None for such formats, and all hooks skip intervention cleanly.
Video VAEs output [B, C, T, H, W]. Patchify now merges T into batch,
processes all frames, and unpatchify restores the 5D shape.
Updated all callers to pass extra_shape through.
facok