§ feed · storyline
DALL·E 2 pre-training mitigations
OpenAI details pre-training mitigations applied to DALL·E 2 to reduce risks from powerful image generation and prevent content policy violations.
In order to share the magic of DALL·E 2 with a broad audience, we needed to reduce the risks associated with powerful image generation models.
To this end, we put various guardrails in place to prevent generated images from violating our content policy.
§ sources1 publication · timeline below
- openai.comDALL·E 2 pre-training mitigationsprimary