BerriAI/litellm · error · ValueError

Nova Canvas image edit requires an image input

Error message

Nova Canvas image edit requires an image input

What it means

Nova Canvas image edit on Bedrock is an edit API: it always needs a source image, encoded to base64 by _file_types_to_b64. That helper raises immediately when image is None (the handler also maps an empty image list to None via image[0] if image else None), before any request is built.

Solutions

  1. Pass the source image: image=open('cat.png', 'rb'), raw bytes, a base64 string, or a pathlib.Path
  2. For text-to-image without an input image use litellm.image(model='bedrock/amazon.nova-canvas-v1:0', ...) instead
  3. Assert image is not None before the call in code where the file is optional

Example fix

# before
resp = litellm.image_edit(
    model="bedrock/amazon.nova-canvas-v1:0",
    prompt="make the sky sunset-colored",
)

# after
resp = litellm.image_edit(
    model="bedrock/amazon.nova-canvas-v1:0",
    image=open("scene.png", "rb"),
    prompt="make the sky sunset-colored",
)
Defensive patterns

Strategy: validation

Validate before calling

def require_image(image):
    if image is None:
        raise ValueError("image_edit requires a source image; use litellm.image() for generation")
    return image

img = require_image(maybe_none_image)

Type guard

def is_supplied(image) -> bool:
    """True when a source image/mask value is present and non-empty."""
    if image is None:
        return False
    if isinstance(image, (list, tuple)):
        return len(image) > 0
    return True

Try / catch

try:
    resp = litellm.image_edit(...)
except ValueError as e:
    if "requires an image input" in str(e):
        raise UserInputError("Upload a source image to edit") from e
    raise

Prevention

When it happens

Trigger: litellm.image_edit(model='bedrock/amazon.nova-canvas-v1:0', prompt='a sunset') with image omitted or image=[]; the variable holding the file object is None because an earlier upload/open failed.

Common situations: Using image_edit for pure text-to-image generation (that is litellm.image()); optional-image code paths where the file may legitimately be absent; silent failures from open()/requests producing None.

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/f49555bb974ed1f0. Report an issue: GitHub.

Appendix: source

Thrown at litellm/llms/bedrock/image_edit/amazon_nova_canvas_image_edit_transformation.py:134

        return {"taskType": "INPAINTING", "inPaintingParams": in_params}
    var_params: Final[dict[str, Any]] = {
        "images": [image_b64],
        "text": text,
    }
    if negative_text is not None:
        var_params["negativeText"] = negative_text
    if similarity_strength is not None:
        var_params["similarityStrength"] = similarity_strength
    return {
        "taskType": "IMAGE_VARIATION",
        "imageVariationParams": var_params,
    }


def _file_types_to_b64(image: FileTypes | None) -> str:
    """Encode OpenAI image input to base64 string for Nova Canvas."""
    if image is None:
        raise ValueError("Nova Canvas image edit requires an image input")
    if hasattr(image, "read") and callable(getattr(image, "read", None)):
        if hasattr(image, "seek"):
            image.seek(0)
        image_bytes: Final = image.read()
        return base64.b64encode(image_bytes).decode("utf-8")
    if isinstance(image, bytes):
        return base64.b64encode(image).decode("utf-8")
    if isinstance(image, str):
        return image
    if isinstance(image, os.PathLike):
        with open(image, "rb") as f:
            return base64.b64encode(f.read()).decode("utf-8")
    if isinstance(image, tuple):
        raise ValueError(
            "Nova Canvas image edit does not support tuple FileTypes. "
            "Pass a file-like object, bytes, or a base64-encoded string."
        )
    return base64.b64encode(bytes(image)).decode("utf-8")

View on GitHub (pinned to 77b7c6c40c)