BerriAI/litellm · error · ValueError

Amazon Nova Canvas requires a text prompt. Pass a non-empty…

Error message

Amazon Nova Canvas {task_type} requires a text prompt. Pass a non-empty `prompt` in your request.

What it means

AWS requires a non-empty text prompt for Nova Canvas INPAINTING and OUTPAINTING tasks (the prompt describes the edit to apply inside/outside the mask). LiteLLM checks this after popping taskType; for other task types an empty prompt is silently replaced with a single space, but for these two it raises before building the body.

Solutions

Pass a descriptive non-empty prompt, e.g. prompt='fill the masked area with foliage'
If you only want background removal, use taskType='BACKGROUND_REMOVAL', which needs no prompt
Guard prompt construction: prompt = user_text or default_edit_instruction

Example fix

# before
resp = litellm.image_edit(
    model="bedrock/amazon.nova-canvas-v1:0",
    image=open("cat.png", "rb"),
    mask=open("mask.png", "rb"),
    taskType="INPAINTING",
    prompt="",
)

# after
resp = litellm.image_edit(
    model="bedrock/amazon.nova-canvas-v1:0",
    image=open("cat.png", "rb"),
    mask=open("mask.png", "rb"),
    taskType="INPAINTING",
    prompt="replace the masked area with flowers",
)

Defensive patterns

Strategy: validation

Validate before calling

PROMPT_REQUIRED_TASKS = {"INPAINTING", "OUTPAINTING"}
if kwargs.get("taskType") in PROMPT_REQUIRED_TASKS and not (prompt or "").strip():
    raise ValueError("INPAINTING/OUTPAINTING need a non-empty prompt")

Type guard

def has_required_prompt(task_type: str | None, prompt: str | None) -> bool:
    """True when the prompt satisfies the task's requirement."""
    if task_type in ("INPAINTING", "OUTPAINTING"):
        return bool(prompt and prompt.strip())
    return True

Try / catch

try:
    resp = litellm.image_edit(...)
except ValueError as e:
    if "requires a text prompt" in str(e):
        raise UserInputError("Describe the edit you want applied to the masked area") from e
    raise

Prevention

Default empty prompts to a task-appropriate instruction string in your UI layer
Add form validation that blocks empty instructions for mask-based edits
Skip prompt validation only for BACKGROUND_REMOVAL

When it happens

Trigger: taskType='INPAINTING' or 'OUTPAINTING' with prompt=None or prompt='' in litellm.image_edit (e.g. mask-only call with no edit instruction).

Common situations: Assuming the mask alone drives the edit; prompt variables rendered empty by templating/i18n; code paths that pass '' as a placeholder.

Understand the failure class

Background: "missing required argument" and "the following required arguments were not provided": what required-argument errors mean and how to fix them — this error's family across 20 libraries.

Related errors

AI-assisted analysis of BerriAI/litellm@77b7c6c40c (2026-08-18). Data as JSON: /api/errors/fc73a68afe95b709. Report an issue: GitHub.

Appendix: source

Thrown at litellm/llms/bedrock/image_edit/amazon_nova_canvas_image_edit_transformation.py:352

        if width is not None:
            image_generation_config["width"] = width
        if height is not None:
            image_generation_config["height"] = height
        if number_of_images is not None:
            image_generation_config["numberOfImages"] = number_of_images
        if quality is not None:
            image_generation_config["quality"] = quality
        if cfg_scale is not None:
            image_generation_config["cfgScale"] = cfg_scale
        if seed is not None:
            image_generation_config["seed"] = seed

        task_type: Final = op.pop("taskType", None)
        if (prompt is None or prompt == "") and task_type in (
            "INPAINTING",
            "OUTPAINTING",
        ):
            raise ValueError(
                f"Amazon Nova Canvas {task_type} requires a text prompt. Pass a non-empty `prompt` in your request."
            )
        text: Final = prompt if prompt is not None and prompt != "" else " "
        negative_text: Final = op.pop("negativeText", None)
        similarity_strength: Final = op.pop("similarityStrength", None)
        mask_prompt: Final = op.pop("maskPrompt", None)
        out_painting_mode: Final = op.pop("outPaintingMode", None)

        body: Final = _nova_canvas_task_body(
            image_b64=image_b64,
            mask_b64=mask_b64,
            text=text,
            negative_text=negative_text,
            similarity_strength=similarity_strength,
            task_type=task_type,
            mask_prompt=mask_prompt,
            out_painting_mode=out_painting_mode,
        )

View on GitHub (pinned to 77b7c6c40c)