EIDT-V: Exploiting Intersections in Diffusion Trajectories for Model-Agnostic, Zero-Shot, Training-Free Text-to-Video Generation

Diljeet Jagpal; Xi Chen; Vinay P. Namboodiri

doi:10.1109/cvpr52734.2025.01698

CVPR2025顶会

EIDT-V: Exploiting Intersections in Diffusion Trajectories for Model-Agnostic, Zero-Shot, Training-Free Text-to-Video Generation

Diljeet Jagpal, Xi Chen, Vinay P. Namboodiri

DOI 出版方

2025年份

摘要

Eight equally spaced frames from 24-frame GIFs generated by our EIDT-V model. Top row shows SD3 Medium [8] results for prompt: "A peacock displaying its feathers". Bottom row shows SDXL [32] results for prompt: "A child blowing bubbles that float and pop gently". These examples highlight the model's ability to generate high-quality videos with semantic and temporal coherence.

问问这篇 Paper

智能体会读完全文。

Lune 把这篇 Paper 索引到了每一个公式，引用它的顶会 Paper 也一样。你提问，回答直接引用原文。

核心论断
横向对比
局限

你的问题

智能体调用

Luneget_paper_fulltext

在 Lune 里问

免费开始，无需绑卡

它引用的顶会 Paper22

Language Models are Few-Shot LearnersTom B. Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah 等NeurIPS 2020 · 被引用 64,255 次
Learning Transferable Visual Models From Natural Language SupervisionAlec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh 等ICML 2021 · 被引用 47,906 次
Denoising Diffusion Probabilistic ModelsJonathan Ho, Ajay Jain, Pieter AbbeelNeurIPS 2020 · 被引用 35,902 次
Diffusion Models Beat GANs on Image SynthesisPrafulla Dhariwal, Alexander Quinn NicholNeurIPS 2021 · 被引用 13,211 次
High-Resolution Image Synthesis with Latent Diffusion ModelsRobin Rombach, Andreas Blattmann, Dominik Lorenz, Patrick Esser 等CVPR 2022 · 被引用 13,123 次

摘要

问问这篇 Paper

智能体会读完全文。

它引用的顶会 Paper22

相关 Paper