Make-A-Scene

2000년 도입 · 논문 1편에서 사용

Make-A-Scene is a text-to-image method that (i) enables a simple control mechanism complementary to text in the form of a scene, (ii) introduces elements that improve the tokenization process by employing domain-specific knowledge over key image regions (faces and salient objects), and (iii) adapts classifier-free guidance for the transformer use case.

출처: Make-A-Scene: Scene-Based Text-to-Image Generation with Human Priors

소개 논문: Make-A-Scene: Scene-Based Text-to-Image Generation with Human Priors