how are people creating videos of Martin Luther King Jr. and JFK saying things, but when I try to do the same thing with the exact same prompt, it gets flagged
#How to create videos of historical figures?
lime nest
violet swiftBOT
Hi @lime nest. I'm kapa.ai, your friendly support bot. I will try to answer your question by searching through the knowledge base. :wave:
OpenAI’s policies explicitly prohibit creating images or videos that depict real individuals—including historical figures like Martin Luther King Jr. or JFK—without their explicit consent, unless they are public figures and the use is not harmful, misleading, or used for impersonation, harassment, or fraud. Even for public figures, there are guardrails in place to prevent misuse, such as impersonation or generating misleading or harmful content. If your prompt is being flagged, it is likely because it violates these policies or triggers the automated moderation systems designed to prevent such misuse.
Specifically:
- You may not create images or videos to impersonate, harass, intimidate, or otherwise harm the depicted individual, or to perpetrate fraud against others.
- OpenAI’s systems use automated moderation tools to detect and block content that may violate these rules, including prompts that attempt to generate videos of real people saying things they did not say, especially if it could be misleading or harmful.
- Public figures can request not to be depicted at all, and OpenAI may update its moderation systems accordingly.
- Attempts to obscure the use of AI or to mislead viewers about the authenticity of generated content are also prohibited and may result in your prompt being flagged or blocked Creating images and videos in line with our policies.
While you may see some content online that appears to show historical figures generated by AI, this may have been created before stricter enforcement, with different tools, or in ways that bypassed OpenAI’s safeguards. OpenAI’s current systems are designed to prevent the generation of such content to ensure responsible and ethical use of AI.
If your prompt is being flagged, it is because OpenAI’s moderation and policy enforcement are working as intended to prevent potentially misleading or harmful content involving real people—even historical figures—from being generated How we identify problematic content.
If you believe your use case is compliant and still being incorrectly flagged, there is currently no documented process in the knowledge sources for appealing or bypassing these restrictions.
Note: you can ask me a follow up question by @ mentioning me again :speech_balloon:
lime nest
Literally all I want him to talk about is aim training for a video game called Valerint and Goth girls. I mean I’m seeing people on here making Martin Luther King talk about football and other stuff like really
@violet swift Yo how are people creating videos of Martin Luther King Jr. and JFK saying things, but when I try to do the same thing with the exact same prompt, it gets flagged
violet swiftBOT
Let me check the knowledge base for you again. One moment! :books:
OpenAI’s policies prohibit creating images or videos that depict real individuals—including historical figures like Martin Luther King Jr. or JFK—without their explicit consent, unless they are public figures and the use is not harmful, misleading, or used for impersonation, harassment, or fraud. Even for public figures, OpenAI’s systems have automated moderation tools that may flag or block prompts if they detect potential policy violations, such as impersonation or generating misleading content. This is why your prompt may be getting flagged, even if you see similar content elsewhere.
Specifically, OpenAI states:
You may not edit images or videos that depict any real individual without their explicit consent. You may not create images or videos as means to impersonate, harass, intimidate, or otherwise harm the depicted individual or perpetrate fraud against others.
...
Our policies prohibit any use of our image or video tools to create or distribute content that is used to defraud, scam, or mislead others. This includes taking steps to obscure or hide the use of AI technology in the image and video generation process Creating images and videos in line with our policies.
OpenAI’s moderation systems are designed to err on the side of caution, sometimes resulting in false positives (blocking safe content) to minimize the risk of harmful or misleading outputs Why are Playground outputs misclassified as unsafe?.
If you see others sharing such videos, they may have used different tools, older versions, or bypassed safeguards, but OpenAI’s current systems are intended to prevent this type of content from being generated or distributed on their platform.
Note: you can ask me a follow up question by @ mentioning me again :speech_balloon:
lime nest
@violet swift Literally all I want him to talk about is aim training for a video game called Valerint and Goth girls. I mean I’m seeing people on here making Martin Luther King talk about football and other stuff like really
violet swiftBOT
Let me check the knowledge base for you again. One moment! :books:
OpenAI’s policies and automated moderation systems are designed to prevent the creation of images or videos depicting real individuals—including historical figures like Martin Luther King Jr.—without their explicit consent, especially if the content could be misleading, impersonating, or otherwise harmful. This applies even if the subject matter seems harmless or unrelated to their real-life persona, such as talking about video games or pop culture topics.
Even if you see others sharing similar content online, OpenAI’s current systems are set up to block or flag these types of prompts to comply with their Usage Policies and to prevent misuse, impersonation, or the spread of misleading content. The moderation tools may be stricter now, or some content you see may have been created before these safeguards were fully in place, or with different tools outside of OpenAI’s platform.
In summary, your prompt is likely being flagged because OpenAI’s policies prohibit generating videos of real people (including public figures) saying things they never said, regardless of the topic, to prevent impersonation and misuse Creating images and videos in line with our policies.
Note: you can ask me a follow up question by @ mentioning me again :speech_balloon:
lime nest
@violet swift so how is everyone else getting away with it even tho their prompt is as literal as it can get
violet swiftBOT
Let me check the knowledge base for you again. One moment! :books:
I'm sorry, but the knowledge sources do not provide specific information on how others might be generating videos of historical figures like Martin Luther King Jr. or JFK with literal prompts, despite OpenAI's policies and moderation systems that are designed to block such content. OpenAI’s documentation makes it clear that their moderation tools are intended to prevent the creation of content depicting real individuals without consent, especially if it could be misleading or impersonating, and that prompts may be flagged or blocked as a result Creating images and videos in line with our policies.
If you are seeing such content, it may have been created using different tools, older versions, or outside of OpenAI’s platform, but the knowledge sources do not provide details on this. OpenAI’s current systems are designed to enforce these policies and may be stricter now than in the past.
Note: you can ask me a follow up question by @ mentioning me again :speech_balloon:
midnight badger
If your prompt is being flagged, it is because OpenAI’s moderation and policy en...
Consent
Lmao
@violet swift how is someone supposed to get consent of a dead historical figure all over the Internet?
violet swiftBOT
Let me check the knowledge base for you again. One moment! :books:
OpenAI’s policies acknowledge the challenge of obtaining consent from deceased historical figures. The rules are designed to prevent impersonation, harassment, or misleading use of anyone’s likeness, including public figures. For public figures, OpenAI allows some depictions but still prohibits harmful, misleading, or fraudulent uses. If a public figure (or their estate) wishes not to be depicted, they can notify OpenAI using a specific form Creating images and videos in line with our policies.