calesthio/OpenMontage · error · ValueError

prompt references <<<image_{max(existing_numbers)}>>> but on

Error message

prompt references <<<image_{max(existing_numbers)}>>> but only {len(references)} image(s) were provided

What it means

Raised by build_image_references()/prompt validation in tools/_kling/omni.py when the prompt already contains <<<image_N>>> placeholders and the largest N exceeds the number of image references supplied. The guard prevents sending a prompt that references an image the backend cannot resolve.

Source

Thrown at tools/_kling/omni.py:32

) -> tuple[str, list[dict[str, Any]]]:
    """Bind image_list entries to stable Image Omni placeholders."""

    references = [
        {
            "index": index,
            "placeholder": f"<<<image_{index}>>>",
            "source": item.get("source") or item.get("image") or item.get("image_url"),
            "source_type": item.get("source_type", "unknown"),
        }
        for index, item in enumerate(image_list, start=1)
    ]
    if not references:
        return prompt, []

    existing_numbers = [int(value) for value in PLACEHOLDER_RE.findall(prompt)]
    if existing_numbers:
        if max(existing_numbers) > len(references):
            raise ValueError(
                f"prompt references <<<image_{max(existing_numbers)}>>> but only {len(references)} image(s) were provided"
            )
        if min(existing_numbers) < 1:
            raise ValueError("Image Omni prompt placeholders must start at <<<image_1>>>")
        return prompt, references

    placeholders = " ".join(item["placeholder"] for item in references)
    return f"{prompt}\nReferences: {placeholders}", references

View on GitHub (pinned to 95e1c3d0ab)

Solutions

1. Add the missing reference image(s) so the count matches the highest placeholder
2. Or renumber the placeholders down to match the actual image count
3. Prefer omitting placeholders entirely — the function auto-appends a 'References:' line when no placeholders exist

Example fix

// before
prompt, refs = build_image_references('use <<<image_2>>> as the character', images=[img1])

// after
prompt, refs = build_image_references('use <<<image_2>>> as the character', images=[img1, img2])

import re

PLACEHOLDER_RE = re.compile(r'<<<image_(\-?\d+)>>>')

def placeholders_match_refs(prompt: str, image_count: int) -> bool:
    nums = [int(n) for n in PLACEHOLDER_RE.findall(prompt)]
    return not nums or (max(nums) <= image_count and min(nums) >= 1)

try:
    prompt, refs = build_image_references(prompt, images)
except ValueError as e:
    if 'but only' in str(e):
        # add images or rewrite prompt without high-numbered placeholders
        raise ValueError(f'reference/prompt mismatch: {len(images)} images vs placeholders in prompt') from e
    raise

When it happens

Trigger: Prompt text contains <<<image_3>>> but only 2 images are passed in image_list; images were removed from the list but the prompt was not updated; index-based prompt written by hand off-by-one.

Common situations: Iterating on prompts while adding/removing reference images; LLM generating the prompt with hardcoded placeholder numbers that drift from the actual image count.

Related errors

• Image Omni prompt placeholders must start at <<<image_1>>>
• model_name {model_name!r} is not supported for api_family=om
• element_list must be a list of element ids or objects
• each element_list item must include element_id
• element_id must be an integer-compatible value: {raw_id!r}

AI-assisted analysis of calesthio/OpenMontage@95e1c3d0ab (2026-08-15). Data as JSON: /api/errors/20d78baf51a743f9. Report an issue: GitHub.