LLMPopcorn: Exploring LLMs as Assistants for Popular Micro-video Generation

Junchen Fu, Xuri Ge, Kaiwen Zheng, Alexandros Karatzoglou, Ioannis Arapakis, Xin Xin, Yongxin Ni, Joemon M. Jose

TL;DR

LLMPopcorn is a novel pipeline that leverages Large Language Models (LLMs) to act as "creative directors" for generating viral micro-videos. By combining Retrieval-Augmented Generation (RAG) and Chain-of-Thought (CoT) prompting, the system produces AI-generated content that rivals or even surpasses human-created videos in predicted popularity.

What Problem Does This Paper Address?

Micro-videos (like those on TikTok and YouTube Shorts) are a multi-billion-dollar industry, but creating "viral" content is traditionally labor-intensive, requiring professional scripting, filming, and editing. While AI video generation models (like Sora or LTX-Video) have made massive strides in visual quality, they lack the "creative spark" to know what content will actually engage an audience.

Current research typically focuses on technical metrics like resolution or duration. This paper addresses the "popularity gap": Can LLMs be used to autonomously plan and prompt videos specifically designed to be popular?

Methods

The authors introduce the LLMPopcorn pipeline, which treats the LLM as a video generation assistant. The process follows these steps:

  1. Input: A user provides a query (either "Concrete," like a specific product description, or "Abstract," like a general theme).
  2. Prompt Enhancement (PE): This is the core innovation. Instead of just passing the user query to a video generator, the system uses:
  3. Retrieval-Augmented Generation (RAG): It searches a database of existing micro-videos to find examples of what has succeeded (positive examples) and what has failed (negative examples) in that specific genre.
  4. Chain-of-Thought (CoT): The LLM follows a structured reasoning process—examining the retrieved data, brainstorming unique topics, and developing a logical script—before generating the final video prompt and title.
  5. Video Generation: The enhanced prompt is fed into a pre-trained video model (e.g., LTX-Video, HunyuanVideo).
  6. Popularity Prediction: An offline evaluator (the MMRA model) predicts the video's engagement potential based on the generated video and its title.
Fig. 1. Overview of the LLMPopcorn pipeline. An LLM processes a user query, generating a video title and prompt for a video generator to create a micro-video. The video and title are then evaluated for predicted popularity.

Datasets

  • Microlens: The largest available micro-video dataset, used as the source for the RAG component and as a human-created baseline for comparison.
  • Custom Prompt Datasets: The authors used ChatGPT-4o to generate 200 unique user prompts (100 concrete, 100 abstract) across five categories: Anime, Delicacy, Daily Sharing, Film & Television, and Gaming.

Key Insights and Ideas

  • LLMs as Strategic Planners: The study finds that LLMs are highly effective at structuring descriptions. By analyzing past successes and failures via RAG, they can steer video generators away from "static" or boring content toward more dynamic, narrative-driven scenes.
  • DeepSeek Dominance: In the benchmarking phase, DeepSeek-V3 and DeepSeek-R1 consistently outperformed other models like Llama-3.3 and GPT-4o in generating high-popularity prompts.
  • Abstract vs. Concrete: LLMs showed a particular strength in handling "Abstract" prompts. While humans often struggle to visualize a vague concept, the LLM could transform a general idea into a diverse range of imaginative, high-engagement scenes.
  • The "Human-Level" Threshold: The most striking finding is that DeepSeek-V3-generated videos achieved median popularity scores (0.73 for abstract prompts) that slightly exceeded the human-crafted videos in the Microlens dataset (0.71).
Fig. 3. Predicted popularity distributions for different LLMs. Y-axis: frequency. X-axis: predicted popularity.

Key Results

  • Popularity Scores: DeepSeek-V3 achieved median popularity scores of 0.56 (concrete) and 0.73 (abstract), compared to human-crafted scores of 0.44 and 0.71, respectively.
  • Prompt Enhancement (PE) Impact: PE significantly boosted results. In a user study, participants preferred videos generated with PE over the basic pipeline 66.67% of the time for concrete prompts and 62.50% for abstract prompts.
  • Video Model Benchmarking: LTX-Video and HunyuanVideo were found to be more reliable and higher-performing than CogVideoX-5b for this specific task.
Fig. 5. Video examples from LLMPopcorn with Prompt Enhance- ment, shown from left to right: abstract user queries (1–3) and con- crete user queries (4–6).

Limitations and Future Work

  • Video Model Constraints: While the LLM "scripts" are excellent, the actual visual output is still limited by the current state of open-source video generation models, which can sometimes produce low-resolution or short-duration clips.
  • Evaluation Proxy: The study relies on an offline popularity predictor (MMRA). While robust, it is a proxy for real-world viral dynamics which are notoriously fickle.
  • Future Directions: The authors suggest exploring Reinforcement Learning from Human Feedback (RLHF) to further align LLM prompts with real-world engagement metrics and contextual cues.

Summary updated

Abstract

In an era where micro-videos dominate platforms like TikTok and YouTube, AI-generated content is nearing cinematic quality. The next frontier is using large language models (LLMs) to autonomously create viral micro-videos, a largely untapped potential that could shape the future of AI-driven content creation. To address this gap, this paper presents the first exploration of LLM-assisted popular micro-video generation (LLMPopcorn). We selected popcorn as the icon for this paper because it symbolizes leisure and entertainment, aligning with this study on leveraging LLMs as assistants for generating popular micro-videos that are often consumed during leisure time. Specifically, we empirically study the following research questions: (i) How can LLMs be effectively utilized to assist popular micro-video generation? (ii) To what extent can prompt-based enhancements optimize the LLM-generated content for higher popularity? (iii) How well do various LLMs and video generators perform in the popular micro-video generation task? Exploring these questions, we show that advanced LLMs like DeepSeek-V3 can generate micro-videos with popularity rivaling human content. Prompt enhancement further boosts results, while benchmarking highlights DeepSeek-V3 and R1 for LLMs, and LTX-Video and HunyuanVideo for video generation. This work advances AI-assisted micro-video creation and opens new research directions. The code is publicly available at https://github.com/GAIR-Lab/LLMPopcorn.
BibTeX
@inproceedings{fu2026llmpopcorn,
  author = {Junchen Fu and Xuri Ge and Kaiwen Zheng and Alexandros Karatzoglou and Ioannis Arapakis and Xin Xin and Yongxin Ni and Joemon M. Jose},
  title = {{LLMPopcorn: Exploring LLMs as Assistants for Popular Micro-video Generation}},
  booktitle = {ENLIGHTEN},
  year = {2026},
}
Figure