Skip to main content
Rase AI Intelligence Newsletter

Creative AI Model or AI service

Tencent published HunyuanVideo research for text-guided video generation

HunyuanVideo is Tencent’s research model for generating video from text prompts. [3]

What the model does

The authors describe a system that combines a video representation with text conditioning to generate a sequence of frames. [3]

Why it matters

Research teams can use the published work to examine how a model follows a prompt while keeping a scene coherent over time. [3]

Key dates

  1. HunyuanVideo preprint is submitted [3]

Sources and verification

Catalog evidence checked How we verify records

  1. Primary source Tencent HunyuanVideo release date and community license
  2. Primary source tencent/HunyuanVideo
  3. Primary source HunyuanVideo: A Systematic Framework For Large Video Generative Models

Related profiles

Creative AI

Seedance 2.5 (4K API and Flash)

ByteDance (Volcano Engine / BytePlus)

These tools generate video through developer services. The cited sources describe different variants and routes of access.

Medium confidenceEvidence checked

Creative AI

LongCat-Video-Avatar 1.6

Meituan (LongCat team)

It generates video of an avatar from supported inputs in the documented project.

High confidenceEvidence checked

Creative AI

MiniMax H3-Image

MiniMax

It generates images from prompts through the model architecture described by MiniMax.

High confidenceEvidence checked