HKUDS/nanobot · error · ImageGenerationError

Gemini Imagen generation failed

Error message

Gemini Imagen generation failed (HTTP {response.status_code}): {detail}

What it means

Raised in GeminiImageGenerator._generate_imagen when the POST to {api_base}/models/{model}:predict returns a non-2xx status. Wraps httpx.HTTPStatusError with status code and upstream detail, meaning the Gemini Imagen (predict) endpoint rejected the request — typically an invalid API key, unsupported model, or invalid parameters.

Solutions

  1. Verify the Gemini/Imagen API key is set and valid (x-goog-api-key header)
  2. Confirm the model name is a valid Imagen model available to the key
  3. Check the detail text for quota or parameter errors and adjust prompt/parameters
  4. Retry after correcting configuration; review extra_body/extra_headers overrides
Defensive patterns

Strategy: try-catch

When it happens

Trigger: Thrown at nanobot/providers/image_generation.py:778 when the library encounters an invalid state.

Common situations: See trigger scenarios.

AI-assisted analysis of HKUDS/nanobot@42f37dc4c0 (2026-08-26). Data as JSON: /api/errors/69bdc5cc8719b362. Report an issue: GitHub.

Appendix: source

Thrown at nanobot/providers/image_generation.py:778

            "instances": [{"prompt": prompt}],
            "parameters": parameters,
        }
        body.update(self.extra_body)

        url = f"{self.api_base}/models/{model}:predict"
        headers = {
            "x-goog-api-key": self.api_key or "",
            "Content-Type": "application/json",
            **self.extra_headers,
        }
        response = await self._http_post(url, headers=headers, body=body)

        try:
            response.raise_for_status()
        except httpx.HTTPStatusError as exc:
            detail = _http_error_detail(response)
            logger.error("Gemini Imagen generation failed (HTTP {}): {}", response.status_code, detail)
            raise ImageGenerationError(
                f"Gemini Imagen generation failed (HTTP {response.status_code}): {detail}"
            ) from exc

        data = _as_json_object(response.json()) or {}
        images: list[str] = []
        for prediction in _as_json_objects(data.get("predictions")):
            b64 = prediction.get("bytesBase64Encoded")
            mime = prediction.get("mimeType", "image/png")
            if isinstance(b64, str) and b64 and isinstance(mime, str):
                images.append(f"data:{mime};base64,{b64}")

        self._require_images(images, data)

        return GeneratedImageResponse(images=images, content="", raw=data)

    async def _generate_gemini_flash(
        self,
        *,

View on GitHub (pinned to 42f37dc4c0)