Share via

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

Apoorv Circus 0 Reputation points
2024-10-10T05:03:26.7266667+00:00

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.

Azure OpenAI Service
Azure OpenAI Service
An Azure service that provides access to OpenAI’s GPT-3 models with enterprise capabilities.
3,455 questions
Azure AI services
Azure AI services
A group of Azure services, SDKs, and APIs designed to make apps more intelligent, engaging, and discoverable.
3,004 questions
Azure AI Content Safety
Azure AI Content Safety
An Azure service that enables users to identify content that is potentially offensive, risky, or otherwise undesirable. Previously known as Azure Content Moderator.
26 questions
Azure Startups
Azure Startups
Azure: A cloud computing platform and infrastructure for building, deploying and managing applications and services through a worldwide network of Microsoft-managed datacenters.Startups: Companies that are in their initial stages of business and typically developing a business model and seeking financing.
484 questions

1 answer

Sort by: Most helpful
Most helpful Newest Oldest
  1. AshokPeddakotla-MSFT 35,576 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.

    User's image

    Do let me know if that helps.

    0 comments

Your answer

Answers can be marked as Accepted Answers by the question author, which helps users to know the answer solved the author's problem.