Comfy-Org/ComfyUI · error · ValueError

Maximum image resolution for the selected model is 16.78MP,

Error message

Maximum image resolution for the selected model is 16.78MP, but {mp_provided:.2f}MP provided.

What it means

Raised by ByteDanceSeedreamNodeV2 in the non-Pro branch when the output size exceeds 16,777,216 pixels (16.78MP), the hard ceiling for Seedream 4.0/4.5/5.0 lite. (Seedream 5.0 Pro has its own lower 4.19MP cap handled earlier.)

Source

Thrown at comfy_api_nodes/nodes_bytedance.py:994

                raise ValueError(
                    f"Minimum image resolution for the selected model is 0.92MP, but {mp_provided:.2f}MP provided."
                )
            if out_num_pixels > 4_194_304:
                raise ValueError(
                    f"Maximum image resolution for the selected model is 4.19MP, but {mp_provided:.2f}MP provided."
                )
        else:
            if ("seedream-4-5" in model_id or "seedream-5-0" in model_id) and out_num_pixels < 3_686_400:
                raise ValueError(
                    f"Minimum image resolution for the selected model is 3.68MP, but {mp_provided:.2f}MP provided."
                )
            if "seedream-4-0" in model_id and out_num_pixels < 921_600:
                raise ValueError(
                    f"Minimum image resolution that the selected model can generate is 0.92MP, "
                    f"but {mp_provided:.2f}MP provided."
                )
            if out_num_pixels > 16_777_216:
                raise ValueError(
                    f"Maximum image resolution for the selected model is 16.78MP, but {mp_provided:.2f}MP provided."
                )

        image_tensors: list[Input.Image] = [t for t in images_dict.values() if t is not None]
        n_input_images = sum(get_number_of_images(t) for t in image_tensors)
        max_num_of_images = 14 if model_id == "seedream-5-0-260128" else 10
        if n_input_images > max_num_of_images:
            raise ValueError(
                f"Maximum of {max_num_of_images} reference images are supported, but {n_input_images} received."
            )
        if sequential_image_generation == "auto" and n_input_images + max_images > 15:
            raise ValueError(
                "The maximum number of generated images plus the number of reference images cannot exceed 15."
            )
        if not thinking and n_input_images > 0:
            raise ValueError(
                "'thinking' can only be disabled for text-to-image; enable it when using reference images."
            )

View on GitHub (pinned to 1c6d8d45b3)

Solutions

  1. Cap width*height at 16.78MP, e.g. 4096x4096 or 4992x3360.
  2. Tile the generation (generate at max size, then upscale locally) instead of exceeding the ceiling.
  3. Double-check custom width/height for accidental large values.

Example fix

// before
size_preset: Custom
width: 6240, height: 4992 // 31.1MP -> raises

// after
size_preset: Custom
width: 4096, height: 4096 // 16.78MP at the limit -> passes
Defensive patterns

Strategy: validation

Validate before calling

NON_PRO_MAX = 16_777_216
if w * h > NON_PRO_MAX:
    scale = (NON_PRO_MAX / (w * h)) ** 0.5
    w, h = int(w * scale), int(h * scale)

Prevention

When it happens

Trigger: Any non-Pro model with width*height > 16777216, e.g. custom 5120x3840 (19.66MP) or an extreme custom preset.

Common situations: Pushing for print-resolution single-shot outputs; typo in width/height (e.g. 6240x4992 exceeds the cap despite being the widget maximums for some presets).

Related errors

AI-assisted analysis of Comfy-Org/ComfyUI@1c6d8d45b3 (2026-08-14). Data as JSON: /api/errors/3d2e2450d58dd9b3. Report an issue: GitHub.