# Free2Guide: Training-Free Text-to-Video Alignment using Image LVLM

arXiv: https://arxiv.org/abs/2411.17041 · HTML: https://mlsanity.com/paper/2411.17041/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Placed in Video generation, one of 14 directions in Diffusion models.
- Builds on 43 of its 51 references that are in the map.
- First posted on arXiv 26 Nov 2024.

## Placed in

- Diffusion models / [Video generation](https://mlsanity.com/diffusion/video-generation/)
- LLM alignment / RLHF / preference optimisation / [Diffusion and multimodal model alignment](https://mlsanity.com/alignment/diffusion-and-multimodal-model-alignment/)

## Builds on (most cited first, 30 of 43)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Score-Based Generative Modeling through Stochastic Differential Equations](https://mlsanity.com/paper/2011.13456/) (2020)
- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021)
- [Deep Unsupervised Learning using Nonequilibrium Thermodynamics](https://mlsanity.com/paper/1503.03585/) (2015)
- [Scaling Laws for Neural Language Models](https://mlsanity.com/paper/2001.08361/) (2020)
- [Classifier-Free Diffusion Guidance](https://mlsanity.com/paper/2207.12598/) (2022)
- [Large Language Models are Zero-Shot Reasoners](https://mlsanity.com/paper/2205.11916/) (2022)
- [Elucidating the Design Space of Diffusion-Based Generative Models](https://mlsanity.com/paper/2206.00364/) (2022)
- [Video Diffusion Models](https://mlsanity.com/paper/2204.03458/) (2022)
- [VBench: Comprehensive Benchmark Suite for Video Generative Models](https://mlsanity.com/paper/2311.17982/) (2023)
- [Diffusion Posterior Sampling for General Noisy Inverse Problems](https://mlsanity.com/paper/2209.14687/) (2022)
- [MVBench: A Comprehensive Multi-modal Video Understanding Benchmark](https://mlsanity.com/paper/2311.17005/) (2023)
- [ImageReward: Learning and Evaluating Human Preferences for Text-to-Image Generation](https://mlsanity.com/paper/2304.05977/) (2023)
- [Training Diffusion Models with Reinforcement Learning](https://mlsanity.com/paper/2305.13301/) (2023)
- [Human Preference Score v2: A Solid Benchmark for Evaluating Human Preferences of Text-to-Image Synthesis](https://mlsanity.com/paper/2306.09341/) (2023)
- [Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inference](https://mlsanity.com/paper/2310.04378/) (2023)
- [VideoCrafter2: Overcoming Data Limitations for High-Quality Video Diffusion Models](https://mlsanity.com/paper/2401.09047/) (2024)
- [InternVid: A Large-scale Video-Text Dataset for Multimodal Understanding and Generation](https://mlsanity.com/paper/2307.06942/) (2023)
- [Diffusion Models for Adversarial Purification](https://mlsanity.com/paper/2205.07460/) (2022)
- [Directly Fine-Tuning Diffusion Models on Differentiable Rewards](https://mlsanity.com/paper/2309.17400/) (2023)
- [Latent Video Diffusion Models for High-Fidelity Long Video Generation](https://mlsanity.com/paper/2211.13221/) (2022)
- [LayoutGPT: Compositional Visual Planning and Generation with Large Language Models](https://mlsanity.com/paper/2305.15393/) (2023)
- [Aligning Text-to-Image Diffusion Models with Reward Backpropagation](https://mlsanity.com/paper/2310.03739/) (2023)
- [Mastering Text-to-Image Diffusion: Recaptioning, Planning, and Generating with Multimodal LLMs](https://mlsanity.com/paper/2401.11708/) (2024)
- [T2V-CompBench: A Comprehensive Benchmark for Compositional Text-to-video Generation](https://mlsanity.com/paper/2407.14505/) (2024)
- [A Primer on Zeroth-Order Optimization in Signal Processing and Machine Learning](https://mlsanity.com/paper/2006.06224/) (2020)

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

- [Inference-Time Text-to-Video Alignment with Diffusion Latent Beam Search](https://mlsanity.com/paper/2501.19252/) (2025)
- [Reangle-A-Video: 4D Video Generation as Video-to-Video Translation](https://mlsanity.com/paper/2503.09151/) (2025)
- [Diffusion-Sharpening: Fine-tuning Diffusion Models with Denoising Trajectory Sharpening](https://mlsanity.com/paper/2502.12146/) (2025)
- [Training-Free Reward-Guided Image Editing via Trajectory Optimal Control](https://mlsanity.com/paper/2509.25845/) (2025)
- [Gradient-Free Noise Optimization for Reward Alignment in Generative Models](https://mlsanity.com/paper/2605.11347/) (2026)
- [PromptLoop: Plug-and-Play Prompt Refinement via Latent Feedback for Diffusion Model Alignment](https://mlsanity.com/paper/2510.00430/) (2025)
- [When Numbers Speak: Aligning Textual Numerals and Visual Instances in Text-to-Video Diffusion Models](https://mlsanity.com/paper/2604.08546/) (2026)
- [Training-free Controllable Human Motion Generation under Heterogeneous Constraints](https://mlsanity.com/paper/2607.01990/) (2026)
- [Manifold-Constrained Initial Noise Optimization for Efficient Generative Model Alignment](https://mlsanity.com/paper/2610.00365/) (2026)

## Abstract (arXiv)

Diffusion models have achieved impressive results in generative tasks for text-to-video (T2V) synthesis. However, achieving accurate text alignment in T2V generation remains challenging due to the complex temporal dependencies across frames. Existing reinforcement learning (RL)-based approaches to enhance text alignment often require differentiable reward functions trained for videos, hindering their scalability and applicability. In this paper, we propose Free2Guide, a novel gradient-free and training-free framework for aligning generated videos with text prompts. Specifically, leveraging principles from path integral control, Free2Guide approximates guidance for diffusion models using non-differentiable reward functions, thereby enabling the integration of powerful black-box Large Vision-Language Models (LVLMs) as reward models. To enable image-trained LVLMs to assess text-to-video alignment, we leverage textitstitching between video frames and use system prompts to capture sequential attributions. Our framework supports the flexible ensembling of multiple reward models to synergistically enhance alignment without significant computational overhead. Experimental results confirm that Free2Guide using image-trained LVLMs significantly improves text-to-video alignment, thereby enhancing the overall video quality. Our results and code are available at https://kjm981995.github.io/free2guide/