https://github.com/OnomaAi101/CAT
공식 코드CAT: Contrastive Adapter Training for Personalized Image Generation
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
Given a text prompt describing a character, we need to distill a representation that enables consistent depiction of the same character in novel contexts.
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
CAT: Contrastive Adapter Training for Personalized Image Generation
Character-Adapter: Prompt-Guided Region Control for High-Fidelity Character Customization
CharacterFactory: Sampling Consistent Characters with GANs for Diffusion Models
Ada-VE: Training-Free Consistent Video Editing Using Adaptive Motion Prior
The Chosen One: Consistent Characters in Text-to-Image Diffusion Models
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.