binary-husky/gpt_academic · error · RuntimeError

Failed to generate image, please try again later: {str(e)}

Error message

Failed to generate image, please try again later: {str(e)}

What it means

This is the catch-all wrapper around gen_image_banana(). Every exception in the try block is shown as a generic failure message and re-raised as RuntimeError with only str(e). It hides whether the real failure was error 7, error 8, requests.post, response.json(), base64 decoding, or writing the output file.

Source

Thrown at crazy_functions/Image_Generate.py:279

        logger.info(f'Generated image.')
        yield from update_ui_latest_msg(lastmsg=f"Downloading image", chatbot=chatbot, history=history, delay=0)

        if ';base64,' in image_url:
            base64_string = image_url.split('base64,')[-1]
            image_data = base64.b64decode(base64_string)
            file_path = f'{get_log_folder()}/image_gen/'
            os.makedirs(file_path, exist_ok=True)
            file_name = 'Image' + time.strftime("%Y-%m-%d-%H-%M-%S", time.localtime()) + '.png'
            fp = file_path+file_name
            with open(fp, 'wb+') as f: f.write(image_data)
        else:
            raise ValueError("Invalid image URL format.")

        return image_url, fp

    except Exception as e:
        yield from update_ui_latest_msg(lastmsg=f"Generate failed, please try again later.", chatbot=chatbot, history=history, delay=0)
        raise RuntimeError(f"Failed to generate image, please try again later: {str(e)}")









@CatchException
def 图片生成_NanoBanana(prompt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
    history = []    # 清空历史,以免输入溢出

    if prompt.strip() == "":
        chatbot.append((prompt, "[Local Message] 图像生成提示为空白"))
        yield from update_ui(chatbot=chatbot, history=history)
        return
    chatbot.append((

View on GitHub (pinned to d6bde0fa54)

Solutions

1. Capture the full exception chain and log response details instead of relying on the generic message.
2. Verify GEMINI/ONE_API configuration and test the endpoint with the same payload.
3. Handle both https and base64 image URLs.
4. Retry only transient network/5xx failures with backoff.
5. Ensure get_log_folder()/image_gen is writable.

Example fix

# before
except Exception as e:
    yield from update_ui_latest_msg(...)
    raise RuntimeError(f"Failed to generate image, please try again later: {str(e)}")

# after
except Exception as e:
    logger.exception("NanoBanana image generation failed")
    yield from update_ui_latest_msg(...)
    raise RuntimeError(
        f"Failed to generate image: {type(e).__name__}: {e}"
    ) from e

api_key = get_conf("GEMINI_API_KEY") if not get_conf("REROUTE_ALL_TO_ONE_API") else get_conf("ONE_API_KEY")
if not api_key:
    raise ValueError("Image API key is not configured")
if not get_conf("REROUTE_ALL_TO_ONE_API") and not get_conf("GEMINI_BASE_URL"):
    raise ValueError("GEMINI_BASE_URL is not configured")

try:
    yield from gen_image_banana(...)
except RuntimeError as e:
    logger.exception("Image plugin failed")
    chatbot.append(["图像生成失败", str(e)])
    yield from update_ui(chatbot=chatbot, history=history)

When it happens

Trigger: Any network/request exception; missing or malformed JSON; missing choices/message/images/image_url fields; a non-base64 URL; invalid resolution/aspect ratio; quota/authentication failure; inability to create gpt_log/image_gen or write the PNG.

Common situations: Wrong GEMINI_BASE_URL/GEMINI_API_KEY or ONE_API_URL/ONE_API_KEY; model not enabled for images; provider returns https rather than base64; disk permission issues; transient network failure.

Related errors

• response.content.decode()
• No image URL found in the response.
• Invalid image URL format.
• 在线搜索失败！\n{Exceptions}
• 转换PDF失败: {str(e)}

AI-assisted analysis of binary-husky/gpt_academic@d6bde0fa54 (2026-08-14). Data as JSON: /api/errors/715646770e2bd948. Report an issue: GitHub.