# V-Stylist: Video Stylization via Collaboration and Reflection of MLLM Agents

arXiv: https://arxiv.org/abs/2503.12077 · HTML: https://mlsanity.com/paper/2503.12077/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 16 references that are in the map.
- First posted on arXiv 15 Mar 2025.

## Builds on (most cited first, 15 of 15)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding](https://mlsanity.com/paper/2205.11487/) (2022)
- [InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks](https://mlsanity.com/paper/2312.14238/) (2023)
- [Universal Style Transfer via Feature Transforms](https://mlsanity.com/paper/1705.08086/) (2017)
- [Rerender A Video: Zero-Shot Text-Guided Video-to-Video Translation](https://mlsanity.com/paper/2306.07954/) (2023)
- [Theory of Mind for Multi-Agent Collaboration via Large Language Models](https://mlsanity.com/paper/2310.10701/) (2023)
- [MindAgent: Emergent Gaming Interaction](https://mlsanity.com/paper/2309.09971/) (2023)
- [Arbitrary Video Style Transfer via Multi-Channel Correlation](https://mlsanity.com/paper/2009.08003/) (2020)
- [VELMA: Verbalization Embodiment of LLM Agents for Vision and Language Navigation in Street View](https://mlsanity.com/paper/2307.06082/) (2023)
- [Interactive Video Stylization Using Few-Shot Patch-Based Training](https://mlsanity.com/paper/2004.14489/) (2020)
- [AIGCBench: Comprehensive Evaluation of Image-to-Video Content Generated by AI](https://mlsanity.com/paper/2401.01651/) (2024)
- [VE-Bench: Subjective-Aligned Benchmark Suite for Text-Driven Video Editing Quality Assessment](https://mlsanity.com/paper/2408.11481/) (2024)
- [MUSES: 3D-Controllable Image Generation via Multi-Modal Agent Collaboration](https://mlsanity.com/paper/2408.10605/) (2024)
- [Diffutoon: High-Resolution Editable Toon Shading via Diffusion Models](https://mlsanity.com/paper/2401.16224/) (2024)

## Built on by (most cited first, 9 of 9)

- [UniFlow: A Unified Pixel Flow Tokenizer for Visual Understanding and Generation](https://mlsanity.com/paper/2510.10575/) (2025)
- [CVBench: Benchmarking Cross-Video Synergies for Complex Multimodal Reasoning](https://mlsanity.com/paper/2508.19542/) (2025)
- [UniVA: Universal Video Agent towards Open-Source Next-Generation Video Generalist](https://mlsanity.com/paper/2511.08521/) (2025)
- [Video-GPT via Next Clip Diffusion](https://mlsanity.com/paper/2505.12489/) (2025)
- [DIRECT: Video Mashup Creation via Hierarchical Multi-Agent Planning and Intent-Guided Editing](https://mlsanity.com/paper/2604.04875/) (2026)
- [PickStyle: Video-to-Video Style Transfer with Context-Style Adapters](https://mlsanity.com/paper/2510.07546/) (2025)
- [BrandFusion: A Multi-Agent Framework for Seamless Brand Integration in Text-to-Video Generation](https://mlsanity.com/paper/2603.02816/) (2026)
- [Audio-Visual Intelligence in Large Foundation Models](https://mlsanity.com/paper/2605.04045/) (2026)
- [SkillPE: Creativity-Oriented Cinematic Skill Evolution for Text-to-Video Prompt Engineering](https://mlsanity.com/paper/2609.34335/) (2026)

## Abstract (arXiv)

Despite the recent advancement in video stylization, most existing methods struggle to render any video with complex transitions, based on an open style description of user query. To fill this gap, we introduce a generic multi-agent system for video stylization, V-Stylist, by a novel collaboration and reflection paradigm of multi-modal large language models. Specifically, our V-Stylist is a systematical workflow with three key roles: (1) Video Parser decomposes the input video into a number of shots and generates their text prompts of key shot content. Via a concise video-to-shot prompting paradigm, it allows our V-Stylist to effectively handle videos with complex transitions. (2) Style Parser identifies the style in the user query and progressively search the matched style model from a style tree. Via a robust tree-of-thought searching paradigm, it allows our V-Stylist to precisely specify vague style preference in the open user query. (3) Style Artist leverages the matched model to render all the video shots into the required style. Via a novel multi-round self-reflection paradigm, it allows our V-Stylist to adaptively adjust detail control, according to the style requirement. With such a distinct design of mimicking human professionals, our V-Stylist achieves a major breakthrough over the primary challenges for effective and automatic video stylization. Moreover,we further construct a new benchmark Text-driven Video Stylization Benchmark (TVSBench), which fills the gap to assess stylization of complex videos on open user queries. Extensive experiments show that, V-Stylist achieves the state-of-the-art, e.g.,V-Stylist surpasses FRESCO and ControlVideo by 6.05% and 4.51% respectively in overall average metrics, marking a significant advance in video stylization.