Comfy-Org/ComfyUI · error · ValueError

Masks must be provided if two audio encoder outputs are used

Error message

Masks must be provided if two audio encoder outputs are used.

What it means

In the two-speaker mode of the Wan audio node, two audio encoder outputs (one per speaker) require a corresponding mask per speaker so the model knows which region each audio stream drives. If audio_encoder_output_2 is set (via the mode dict or directly) but either mask is missing, the node raises before building ref_masks.

Source

Thrown at comfy_extras/nodes_wan.py:1517

                io.Int.Output(display_name="trim_image"),
            ],
        )

    @classmethod
    def execute(cls, mode: DCValues, model, model_patch, positive, negative, vae, width, height, length, audio_encoder_output_1, motion_frame_count,
                start_image=None, previous_frames=None, audio_scale=None, clip_vision_output=None, audio_encoder_output_2=None, mask_1=None, mask_2=None) -> io.NodeOutput:

        if previous_frames is not None and previous_frames.shape[0] < motion_frame_count:
            raise ValueError("Not enough previous frames provided.")

        if mode["mode"] == "two_speakers":
            audio_encoder_output_2 = mode["audio_encoder_output_2"]
            mask_1 = mode["mask_1"]
            mask_2 = mode["mask_2"]

        if audio_encoder_output_2 is not None:
            if mask_1 is None or mask_2 is None:
                raise ValueError("Masks must be provided if two audio encoder outputs are used.")

        ref_masks = None
        if mask_1 is not None and mask_2 is not None:
            if audio_encoder_output_2 is None:
                raise ValueError("Second audio encoder output must be provided if two masks are used.")
            ref_masks = torch.cat([mask_1, mask_2])

        latent = torch.zeros([1, 16, ((length - 1) // 4) + 1, height // 8, width // 8], device=comfy.model_management.intermediate_device())
        if start_image is not None:
            start_image = comfy.utils.common_upscale(start_image[:length].movedim(-1, 1), width, height, "bilinear", "center").movedim(1, -1)
            image = torch.ones((length, height, width, start_image.shape[-1]), device=start_image.device, dtype=start_image.dtype) * 0.5
            image[:start_image.shape[0]] = start_image

            concat_latent_image = vae.encode(image[:, :, :, :3])
            concat_mask = torch.ones((1, 1, latent.shape[2], concat_latent_image.shape[-2], concat_latent_image.shape[-1]), device=start_image.device, dtype=start_image.dtype)
            concat_mask[:, :, :((start_image.shape[0] - 1) // 4) + 1] = 0.0

            positive = node_helpers.conditioning_set_values(positive, {"concat_latent_image": concat_latent_image, "concat_mask": concat_mask})

View on GitHub (pinned to 1c6d8d45b3)

Solutions

1. Provide both mask_1 and mask_2 (one speaker region each) when using two audio encoder outputs
2. If only one speaker, switch the mode back to single-speaker so no second audio/masks are expected
3. Check the mode component actually populated mask_1/mask_2 when assembling the DCValues mode dict

if audio_encoder_output_2 is not None:
    assert mask_1 is not None and mask_2 is not None, "two audio streams need two masks"
elif mask_1 is not None or mask_2 is not None:
    mask_1 = mask_2 = None  # drop orphan masks for single-speaker mode

When it happens

Trigger: Selecting mode 'two_speakers' (which injects audio_encoder_output_2, mask_1, mask_2 from the mode dict) where masks were not provided; or wiring a second audio encoder output while leaving mask_1/mask_2 unconnected.

Common situations: Configuring a two-speaker talking-head workflow but forgetting the two region masks; mode dict built without mask entries; testing with a single speaker while the mode string still says two_speakers.

Related errors

• Second audio encoder output must be provided if two masks ar
• Not enough previous frames provided.
• Norm layer {norm_layer} is not implemented
• pose branch has {} latent frames, expected {} (generation fr
• Invalid input shape: {x.shape}

AI-assisted analysis of Comfy-Org/ComfyUI@1c6d8d45b3 (2026-08-14). Data as JSON: /api/errors/45e5302141b37650. Report an issue: GitHub.