DALL-E 3 Error: Content Policy Violation on Image Generation

Apoorv Circus 0

When attempting to generate an image using the prompt "depict goku versus naruto," the following error occurs:

openai.BadRequestError: Error code: 400 - {'error': {'code': 'content_policy_violation', 'inner_error': {'code': 'ResponsibleAIPolicyViolation', 'content_filter_results': {'jailbreak': {'detected': False, 'filtered': False}}}, 'message': 'Your request was rejected as a result of our safety system. Your prompt may contain text that is not allowed by our safety system.', 'type': 'invalid_request_error'}}

Despite this, no violation of the content filters or the Responsible AIPolicy is evident as noted in the documentation: Content Filter Documentation.

Additionally, the same image can be successfully created using Microsoft's publicly available DALL-E 3 service: Bing Image Creation.

AshokPeddakotla-MSFT 34,016 Reputation points

2024-10-10T06:11:13.93+00:00

Apoorv Circus Greetings & Welcome to Microsoft Q&A forum!

I'm also getting the same error as response. Did you try adjusting the severity levels?

I understand that it is not intended behavior. If Azure OpenAI recognizes your prompt as harmful content, it doesn't return a generated image. For more information, see Content filtering and adjust the Severity.

The word "Goku" is triggering content filter. Can you try modifying the prompt and see if that works.

Do let me know if that helps.
AshokPeddakotla-MSFT 34,016 Reputation points

2024-10-14T14:57:11.53+00:00

Apoorv Circus Did you get a chance to see my response?

Do let me know if that helps or have any further queries.

Share via

DALL-E 3 Error: Content Policy Violation on Image Generation

Your answer