TV2TV: A Unified Framework for Interleaved Language and Video Generation
By: Xiaochuang Han , Youssef Emad , Melissa Hall and more
Potential Business Impact:
Makes videos that follow stories better.
Video generation models are rapidly advancing, but can still struggle with complex video outputs that require significant semantic branching or repeated high-level reasoning about what should happen next. In this paper, we introduce a new class of omni video-text models that integrate ideas from recent LM reasoning advances to address this challenge. More specifically, we present TV2TV, a unified generative modeling framework which decomposes video generation into an interleaved text and video generation process. TV2TV jointly learns language modeling (next-token prediction) and video flow matching (next-frame prediction) using a Mixture-of-Transformers (MoT) architecture. At inference time, TV2TV decides when to alternate between generating text and video frames, allowing the model to "think in words" about subsequent content before ``acting in pixels'' to produce frames. This design offloads much of the responsibility for deciding what should happen next to the language modeling tower, enabling improved visual quality and prompt alignment of generated videos. It also enables fine-grained controllability, allowing users to modify the video generation trajectory through text interventions at any point in the process. In controlled experiments on video game data, TV2TV demonstrates substantial improvements in both visual quality and controllability. TV2TV also scales to natural videos, as we show by augmenting sports videos with interleaved natural language action descriptions using vision-language models (VLMs). Training TV2TV on this corpus yields strong visual quality and prompt alignment, showcasing the model's ability to reason about and generate complex real-world action sequences. Together, these results highlight TV2TV as a promising step toward video generation with open-ended textual reasoning and control.
Similar Papers
Bridging Text and Video Generation: A Survey
Graphics
Makes videos from written words.
OmniV2V: Versatile Video Generation and Editing via Dynamic Content Manipulation
CV and Pattern Recognition
Edits and makes videos from text and pictures.
3MDiT: Unified Tri-Modal Diffusion Transformer for Text-Driven Synchronized Audio-Video Generation
Multimedia
Makes videos and sounds match perfectly.