Comfy-Org/ComfyUI · error · ValueError

Minimum image resolution for the selected model is 3.68MP, b

Error message

Minimum image resolution for the selected model is 3.68MP, but {mp_provided:.2f}MP provided.

What it means

Seedream 4.5 / 5.0 models enforce a minimum output of 3,686,400 pixels (3.68MP). After resolving the preset or custom width/height, the node rejects requests below that floor before calling the API.

Source

Thrown at comfy_api_nodes/nodes_bytedance.py:706

        seed: int = 0,
        watermark: bool = False,
        fail_on_partial: bool = True,
    ) -> IO.NodeOutput:
        model = SEEDREAM_MODELS[model]
        validate_string(prompt, strip_whitespace=True, min_length=1)
        w = h = None
        for label, tw, th in RECOMMENDED_PRESETS_SEEDREAM_4:
            if label == size_preset:
                w, h = tw, th
                break

        if w is None or h is None:
            w, h = width, height

        out_num_pixels = w * h
        mp_provided = out_num_pixels / 1_000_000.0
        if ("seedream-4-5" in model or "seedream-5-0" in model) and out_num_pixels < 3686400:
            raise ValueError(
                f"Minimum image resolution for the selected model is 3.68MP, " f"but {mp_provided:.2f}MP provided."
            )
        if "seedream-4-0" in model and out_num_pixels < 921600:
            raise ValueError(
                f"Minimum image resolution that the selected model can generate is 0.92MP, "
                f"but {mp_provided:.2f}MP provided."
            )
        max_pixels = 10_404_496 if "seedream-5-0" in model else 16_777_216
        if out_num_pixels > max_pixels:
            raise ValueError(
                f"Maximum image resolution for the selected model is {max_pixels / 1_000_000:.2f}MP, "
                f"but {mp_provided:.2f}MP provided."
            )
        n_input_images = get_number_of_images(image) if image is not None else 0
        max_num_of_images = 14 if model == "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."

View on GitHub (pinned to 1c6d8d45b3)

Solutions

1. Raise width*height to at least 3686400 pixels (e.g. 1920x1920 or larger preset).
2. Switch the model widget to seedream-4-0 if you need sub-3.68MP outputs.
3. Downscale the generated image afterwards if you need a smaller final asset.

Example fix

// before
model: 'seedream-4-5', width: 1024, height: 1024
// after
model: 'seedream-4-5', width: 2048, height: 2048

MIN_PX = 3_686_400 if 'seedream-4-5' in model or 'seedream-5-0' in model else None
if MIN_PX and width * height < MIN_PX:
    width = height = int(MIN_PX ** 0.5)  # or bump to a compliant preset

When it happens

Trigger: Model string contains 'seedream-4-5' or 'seedream-5-0' and w*h < 3686400 - e.g. a 1024x1024 (1MP) custom size or a small preset carried over from Seedream 4.0.

Common situations: Workflow built for seedream-4-0 (0.92MP floor) reused with a 4.5/5.0 model id; user assumes 1K presets are universal across the family.

Related errors

• Minimum image resolution that the selected model can generat
• Maximum image resolution for the selected model is {max_pixe
• Custom size out of range: {w}x{h}. Both width and height mus
• Maximum of {max_num_of_images} reference images are supporte
• The maximum number of generated images plus the number of re

AI-assisted analysis of Comfy-Org/ComfyUI@1c6d8d45b3 (2026-08-14). Data as JSON: /api/errors/584afd7079e67a60. Report an issue: GitHub.