Comfy-Org/ComfyUI · error · ValueError

'manga' style requires a portrait aspect ratio ({allowed_man

Error message

'manga' style requires a portrait aspect ratio ({allowed_manga_ratios}) or 'auto'; got '{aspect_ratio}'.

What it means

Raised by the Luma 2 image node (comfy_api_nodes/nodes_luma.py:842) when style is 'manga' but the chosen aspect_ratio is neither 'auto' nor one of the portrait ratios {1:2, 1:3, 2:3, 9:16}. The manga style upstream only renders portrait compositions, so landscape/square ratios are rejected client-side.

Source

Thrown at comfy_api_nodes/nodes_luma.py:842

                  {"type":"usd","usd": $round($base + 0.003 * $refs, 4)}
                )
                """,
            ),
        )

    @classmethod
    async def execute(
        cls,
        prompt: str,
        model: dict,
        seed: int,
    ) -> IO.NodeOutput:
        validate_string(prompt, min_length=1, max_length=6000)
        aspect_ratio = model["aspect_ratio"]
        style = model["style"]
        allowed_manga_ratios = {"2:3", "9:16", "1:2", "1:3"}
        if style == "manga" and aspect_ratio != "auto" and aspect_ratio not in allowed_manga_ratios:
            raise ValueError(
                f"'manga' style requires a portrait aspect ratio "
                f"({', '.join(sorted(allowed_manga_ratios))}) or 'auto'; got '{aspect_ratio}'."
            )
        request = Luma2GenerationRequest(
            prompt=prompt,
            model=model["model"],
            type="image",
            aspect_ratio=aspect_ratio if aspect_ratio != "auto" else None,
            style=style if style != "auto" else None,
            output_format="png",
            web_search=model["web_search"],
            image_ref=await _luma2_upload_image_refs(cls, model.get("image_ref"), max_count=9),
        )
        final = await _luma2_submit_and_poll(cls, request)
        return IO.NodeOutput(await download_url_to_image_tensor(final.output[0].url))


class LumaImageEditNode(IO.ComfyNode):

View on GitHub (pinned to 1c6d8d45b3)

Solutions

1. Set aspect_ratio to a portrait ratio: 2:3, 9:16, 1:2, or 1:3.
2. Or set aspect_ratio to 'auto' and let the model pick a portrait ratio.
3. Or switch style away from 'manga' if landscape output is required.

ALLOWED_MANGA = {"2:3", "9:16", "1:2", "1:3"}
if style == "manga" and aspect_ratio != "auto" and aspect_ratio not in ALLOWED_MANGA:
    aspect_ratio = "2:3"  # or raise, or switch style

When it happens

Trigger: Setting the model widget style='manga' together with aspect_ratio='16:9', '4:3', '1:1', '3:2', etc. in LumaImageNode2.

Common situations: User switches style to manga while keeping a landscape ratio from a previous render; workflows shared with different default widget values; UI defaulting to 16:9.

Related errors

• 1080p is not available for vertical aspect ratios (9:16, 3:4
• Custom aspect ratio is only allowed when multiple images are
• At least one of first_image and last_image requires an input
• Maximum {max_count} reference images are allowed.
• Looping is only available with 5s duration on Ray 3.2.

AI-assisted analysis of Comfy-Org/ComfyUI@1c6d8d45b3 (2026-08-14). Data as JSON: /api/errors/02d671e2b8c730d1. Report an issue: GitHub.