Method execute

iclora.py:348–466

(
        cls,
        positive,
        negative,
        vae,
        latent,
        image,
        frame_idx,
        strength,
        latent_downscale_factor,
        crop,
        use_tiled_encode,
        tile_size,
        tile_overlap,
        attention_strength=1.0,
        attention_mask=None,
    )

    @classmethod
    def execute(
        cls,
        positive,
        negative,
        vae,
        latent,
        image,
        frame_idx,
        strength,
        latent_downscale_factor,
        crop,
        use_tiled_encode,
        tile_size,
        tile_overlap,
        attention_strength=1.0,
        attention_mask=None,
    ) -> io.NodeOutput:
        from .iclora_attention import normalize_mask
        from .latents import LTXVDilateLatent

        scale_factors = vae.downscale_index_formula
        latent_image = latent["samples"]
        noise_mask = nodes_lt.get_noise_mask(latent)

        _, _, latent_length, latent_height, latent_width = latent_image.shape

        time_scale_factor = scale_factors[0]
        num_frames_to_keep = (
            (image.shape[0] - 1) // time_scale_factor
        ) * time_scale_factor + 1
        causal_fix = frame_idx == 0 or num_frames_to_keep == 1
        if not causal_fix:
            image = torch.cat([image[:1], image], dim=0)

        image, guide_latent = cls.encode(
            vae,
            latent_width,
            latent_height,
            image,
            scale_factors,
            latent_downscale_factor,
            crop,
            use_tiled_encode,
            tile_size,
            tile_overlap,
        )

        if not causal_fix:
            guide_latent = guide_latent[:, :, 1:, :, :]
            image = image[1:]

        guide_orig_shape = list(guide_latent.shape[2:])
        guide_mask = None

        if latent_downscale_factor > 1:
            if (
                latent_width % latent_downscale_factor != 0
                or latent_height % latent_downscale_factor != 0