English

Plan-X: Instruct Video Generation via Semantic Planning

Computer Vision and Pattern Recognition 2025-11-25 v1 Artificial Intelligence

Abstract

Diffusion Transformers have demonstrated remarkable capabilities in visual synthesis, yet they often struggle with high-level semantic reasoning and long-horizon planning. This limitation frequently leads to visual hallucinations and mis-alignments with user instructions, especially in scenarios involving complex scene understanding, human-object interactions, multi-stage actions, and in-context motion reasoning. To address these challenges, we propose Plan-X, a framework that explicitly enforces high-level semantic planning to instruct video generation process. At its core lies a Semantic Planner, a learnable multimodal language model that reasons over the user's intent from both text prompts and visual context, and autoregressively generates a sequence of text-grounded spatio-temporal semantic tokens. These semantic tokens, complementary to high-level text prompt guidance, serve as structured "semantic sketches" over time for the video diffusion model, which has its strength at synthesizing high-fidelity visual details. Plan-X effectively integrates the strength of language models in multimodal in-context reasoning and planning, together with the strength of diffusion models in photorealistic video synthesis. Extensive experiments demonstrate that our framework substantially reduces visual hallucinations and enables fine-grained, instruction-aligned video generation consistent with multimodal context.

Keywords

Cite

@article{arxiv.2511.17986,
  title  = {Plan-X: Instruct Video Generation via Semantic Planning},
  author = {Lun Huang and You Xie and Hongyi Xu and Tianpei Gu and Chenxu Zhang and Guoxian Song and Zenan Li and Xiaochen Zhao and Linjie Luo and Guillermo Sapiro},
  journal= {arXiv preprint arXiv:2511.17986},
  year   = {2025}
}

Comments

The project page is at https://byteaigc.github.io/Plan-X

R2 v1 2026-07-01T07:50:07.253Z