assafelovic/gpt-researcher · error · TimeoutError

ModelsLab image generation timed out after polling.

Error message

ModelsLab image generation timed out after polling.

What it means

TimeoutError raised after _poll_for_result exhausts MAX_POLL_ATTEMPTS without the ModelsLab job reaching status "success" with output. The job stays in "processing" (or returns transient statuses) for the entire polling window, so the code gives up.

Source

Thrown at gpt_researcher/llm_provider/image/modelslab_image_generator.py:121

                            )
        except ImportError:
            import requests

            for _ in range(MAX_POLL_ATTEMPTS):
                await asyncio.sleep(POLL_INTERVAL_SECONDS)
                resp = await asyncio.to_thread(
                    requests.post,
                    f"{FETCH_BASE_URL}/{request_id}",
                    json={"key": self.api_key},
                    timeout=15,
                )
                body = resp.json()
                if body.get("status") == "success" and body.get("output"):
                    return body["output"]
                if body.get("status") == "error":
                    raise RuntimeError(body.get("messege", "ModelsLab generation error"))

        raise TimeoutError("ModelsLab image generation timed out after polling.")

    async def generate_image(
        self,
        prompt: str,
        context: str = "",
        research_id: str = "",
        aspect_ratio: str = "1:1",
        num_images: int = 1,
        style: str = "dark",
    ) -> List[Dict[str, Any]]:
        """Generate images using ModelsLab's text-to-image API.

        Args:
            prompt: The image generation prompt.
            context: Additional context (appended to prompt).
            research_id: Research ID for organizing output directories.
            aspect_ratio: Ignored (ModelsLab uses width/height).
            num_images: Number of images to generate (1–4).

View on GitHub (pinned to 6f998577d5)

Solutions

1. Retry the generation — transient ModelsLab congestion is the most common cause.
2. Reduce image count / steps / resolution in the payload to shorten generation time.
3. Raise MAX_POLL_ATTEMPTS or the per-request timeout if you control the module.
4. Check ModelsLab status page / your job id in their dashboard to see if the job eventually finished.

Example fix

// before
images = await generator.generate_image(prompt)

// after
for attempt in range(3):
    try:
        images = await generator.generate_image(prompt)
        break
    except TimeoutError:
        images = []
        await asyncio.sleep(5)

null

null

for attempt in range(3):
    try:
        images = await generator.generate_image(prompt); break
    except TimeoutError:
        await asyncio.sleep(5)
else:
    images = []

When it happens

Trigger: Initial text2img POST returns status "processing" with an id; every subsequent poll for MAX_POLL_ATTEMPTS iterations fails to return success/output; the loop exits and raises TimeoutError.

Common situations: Heavy prompt/large batch queueing long generation times, slow ModelsLab service, network latency stretching poll round-trips, or an id from a job that died silently server-side.

Understand the failure class

• Timeouts: ETIMEDOUT, deadlines, and hung requests — what actually expires when a request times out.

Related errors

• ModelsLab generation error
• ModelsLab API error

AI-assisted analysis of assafelovic/gpt-researcher@6f998577d5 (2026-08-28). Data as JSON: /api/errors/d16b01d4306f5e27. Report an issue: GitHub.