DALL-E
The original DALL-E research framed text-to-image generation as modeling image tokens conditioned on text. Later products carrying the name are versioned systems and should not be assumed identical to the original paper.
Overview. The original DALL-E research framed text-to-image generation as modeling image tokens conditioned on text.
Context. Later products carrying the name are versioned systems and should not be assumed identical to the original paper.
Claims and evidence
Claim ledger, 2The original DALL-E research framed text-to-image generation as modeling image tokens conditioned on text.
Later products carrying the name are versioned systems and should not be assumed identical to the original paper.