Vidu: a Highly Consistent, Dynamic and Skilled Text-to-Video Generator with Diffusion Models — HN submission

Wed, 28 Aug 2024 13:59:11 GMT

Show HN: Vidu – The New text/image-to-video MultiModal LLM

Hi HN, Vidu team here. We're excited to introduce our latest project, presented by Tsinghua University and Shengshu Technology - Vidu, a text and image-to-video MultiModal LLM. Professor Jun Zhu and his colleagues published a research paper on Vidu and its capabilities during Vidu's early stages: https://arxiv.org/abs/2405.04233 To set Vidu apart from the mass generative video AI that has already been released, our team chose to focus on augmenting specific properties during the early-stages of Vidu's developments, such as consistency. Inconsistencies has to be the most expressed concern…

1 point; 1 discussion reply on HN. Paper and source history. A submission is not an endorsement.

Vidu: a Highly Consistent, Dynamic and Skilled Text-to-Video Generator with Diffusion Models · HackerPapers discussions

Vidu: a Highly Consistent, Dynamic and Skilled Text-to-Video Generator with Diffusion Models — HN submission