3 papers
cs.CV2024
The Power of Next-Frame Prediction for Learning Physical Laws
Thomas Winterbottom, G. Thomas Hudson, Daniel Kluvanec +6
Next-frame prediction is a useful and powerful method for modelling and understanding the dynamics of video data. Inspired by the empirical success of causal language modelling and…
cs.CV2024
AttenCraft: Attention-guided Disentanglement of Multiple Concepts for Text-to-Image Customization
Junjie Shentu, Matthew Watson, Noura Al Moubayed
Text-to-image (T2I) customization empowers users to adapt the T2I diffusion model to new concepts absent in the pre-training dataset. On this basis, capturing multiple new concepts…
cs.CV2024
Textual Localization: Decomposing Multi-concept Images for Subject-Driven Text-to-Image Generation
Junjie Shentu, Matthew Watson, Noura Al Moubayed
Subject-driven text-to-image diffusion models empower users to tailor the model to new concepts absent in the pre-training dataset using a few sample images. However, prevalent sub…