English
← Back to timeline

DALL-E & CLIP

Era: The LLM Era · 2020s–Present

OpenAI released DALL-E (image generation) and CLIP (image-text contrastive learning). These models demonstrated AI’s ability to understand and generate multimodal content.

OpenAI

Status
Verified
Content type
fact
Sources reviewed

Sources and support

  1. DALL·E: Creating Images from Text

    OpenAI · Source type: primary-announcement

    OpenAI introduces DALL·E for text-to-image generation.

    Published: ·Accessed:

  2. CLIP: Connecting Text and Images

    OpenAI · Source type: primary-announcement

    OpenAI introduces CLIP’s contrastive language-image training approach.

    Published: ·Accessed: