ATH-MaaS/Pixelle-Video · error · Exception

Max attempts reached, failed to generate image. Last error:

Error message

Max attempts reached, failed to generate image. Last error: {last_error}

What it means

generate_image loops through attempts (and models); when every attempt fails, it raises a generic Exception reporting the number of attempts and the last underlying error. This is the terminal wrapper around failures like [51]/[52], network errors, or auth errors.

Source

Thrown at pixelle_video/services/api_services/image_gpt.py:137

                    url = img_data.url
                    if save_dir:
                        os.makedirs(save_dir, exist_ok=True)
                        file_name = f"gpt_{int(time.time())}_{uuid.uuid4().hex[:6]}.png"
                        file_path = os.path.join(save_dir, file_name)
                        if self.image_processor.download_image(url, file_path):
                            return file_path
                        return url
                
                raise RuntimeError("未在响应中找到 url 或 b64_json")
            except Exception as e:
                last_error = e
                msg = str(e)
                # Other errors: wait before retry
                print(f"Image generation error: {e}. Retrying in 10 seconds.")
                time.sleep(10)
                break  # Break inner loop to retry all models
            attempts += 1
        raise Exception(f"Max attempts reached, failed to generate image. Last error: {last_error}")

    def generate_images(self, prompt, count=4, size="1024x1024", quality="standard", model=None):
        """Generate multiple image URLs by calling Images API 'count' times."""
        urls = []
        for _ in range(count):
            url = self.generate_image(prompt=prompt, size=size, quality=quality, model=model)
            urls.append(url)
        return urls


if __name__ == "__main__":
    import sys
    import tempfile
    sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
    from config import Config

    MODELS = ["gpt-image-2"]
    save_dir = "code/result/image/test_avail"

View on GitHub (pinned to 848b054e4f)

Solutions

1. Inspect 'Last error: ...' in the message — fix that root cause first (key, quota, model, connectivity).
2. Increase retry attempts or backoff interval if failures are rate-limit related.
3. Verify API key validity and remaining quota on the provider dashboard.
4. Add a fallback provider/model, or circuit-break and schedule the job for later during outages.

Example fix

// before
url = client.generate_image(prompt)  # raises after retries

// after
try:
    url = client.generate_image(prompt)
except Exception as e:
    logging.error(f"Image generation exhausted retries: {e}")
    url = fallback_provider.generate_image(prompt)

import os
assert os.environ.get("OPENAI_API_KEY") or os.environ.get("RELAY_API_KEY"), "no image API key configured"

def can_attempt(client) -> bool:
    return bool(getattr(client, "api_key", None)) and bool(getattr(client, "base_url", None))

try:
    out = client.generate_image(prompt)
except Exception as e:
    logging.error(f"All generation attempts failed: {e}")
    out = None  # degrade gracefully or use fallback provider
    if out is None:
        raise

When it happens

Trigger: All retry attempts of generate_image exhausted: every call to client.images.generate either returned empty data, had no url/b64_json, raised a network/timeout error, or returned a rate-limit error.

Common situations: Sustained provider outage or relay downtime, exhausted rate limits/quota across all retries, invalid API key failing every attempt, network connectivity issues from the host.

Related errors

• OpenAI API 返回数据为空
• 未在响应中找到 url 或 b64_json
• str(e)
• API image generation returned no result: provider={provider}
• DashScope generation failed: {e}

AI-assisted analysis of ATH-MaaS/Pixelle-Video@848b054e4f (2026-08-30). Data as JSON: /api/errors/e0860e1cb9567538. Report an issue: GitHub.