Unverified50% confidenceFactExact time
DALL-E于2021年由OpenAI发布，将Transformer与图像生成结合，首次展示从文本描述直接生成图像
1
Sources
50%
Confidence
Long-term
Relevance
8/12/2026
First Seen
Sources
Related Claims
UnverifiedDALL·E 1基于离散VAE和Transformer架构实现文本到图像生成72% similarVerifiedOpenAI's Sora uses a diffusion Transformer architecture and is known for high-quality text-to-video generation.71% similarPartially VerifiedThe CLIP architecture was proposed by OpenAI in 2021 and maps images and text to the same high-dimensional vector space through contrastive learning.65% similarVerifiedCLIP was released by OpenAI in 2021, simultaneously training an image encoder and a text encoder through contrastive learning to achieve zero-shot image classification.65% similarUnverifiedThe second phase of AI video generation tools, represented by models such as Sora and Kling in 2023–2024, achieved direct text-to-video generation.62% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/736785API
curl https://kongchang.com/api/v1/knowledge/claims/736785MCP
get_claim(id=736785)