all AI news
Cross-Attention Makes Inference Cumbersome in Text-to-Image Diffusion Models
April 4, 2024, 4:45 a.m. | Wentian Zhang, Haozhe Liu, Jinheng Xie, Francesco Faccio, Mike Zheng Shou, J\"urgen Schmidhuber
cs.CV updates on arXiv.org arxiv.org
Abstract: This study explores the role of cross-attention during inference in text-conditional diffusion models. We find that cross-attention outputs converge to a fixed point after few inference steps. Accordingly, the time point of convergence naturally divides the entire inference process into two stages: an initial semantics-planning stage, during which, the model relies on cross-attention to plan text-oriented visual semantics, and a subsequent fidelity-improving stage, during which the model tries to generate images from previously planned semantics. …
arxiv attention cs.cv diffusion diffusion models image image diffusion inference text text-to-image type
More from arxiv.org / cs.CV updates on arXiv.org
Multi-View Spectrogram Transformer for Respiratory Sound Classification
2 days, 23 hours ago |
arxiv.org
GaussianHead: High-fidelity Head Avatars with Learnable Gaussian Derivation
2 days, 23 hours ago |
arxiv.org
OTMatch: Improving Semi-Supervised Learning with Optimal Transport
2 days, 23 hours ago |
arxiv.org
Jobs in AI, ML, Big Data
Senior Machine Learning Engineer
@ GPTZero | Toronto, Canada
ML/AI Engineer / NLP Expert - Custom LLM Development (x/f/m)
@ HelloBetter | Remote
Doctoral Researcher (m/f/div) in Automated Processing of Bioimages
@ Leibniz Institute for Natural Product Research and Infection Biology (Leibniz-HKI) | Jena
Seeking Developers and Engineers for AI T-Shirt Generator Project
@ Chevon Hicks | Remote
Senior Applied Data Scientist
@ dunnhumby | London
Principal Data Architect - Azure & Big Data
@ MGM Resorts International | Home Office - US, NV