# Mimir: Improving Video Diffusion Models for Precise Text Understanding

arXiv: https://arxiv.org/abs/2412.03085 · HTML: https://mlsanity.com/paper/2412.03085/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- Placed in Video generation, one of 14 directions in Diffusion models.
- Builds on 54 of its 69 references that are in the map.
- First posted on arXiv 4 Dec 2024.

## Placed in

- Diffusion models / [Video generation](https://mlsanity.com/diffusion/video-generation/)

## Builds on (most cited first, 30 of 54)

- [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)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Deep Unsupervised Learning using Nonequilibrium Thermodynamics](https://mlsanity.com/paper/1503.03585/) (2015)
- [Hierarchical Text-Conditional Image Generation with CLIP Latents](https://mlsanity.com/paper/2204.06125/) (2022)
- [Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding](https://mlsanity.com/paper/2205.11487/) (2022)
- [SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis](https://mlsanity.com/paper/2307.01952/) (2023)
- [Scaling Rectified Flow Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2403.03206/) (2024)
- [Qwen Technical Report](https://mlsanity.com/paper/2309.16609/) (2023)
- [Taming Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2012.09841/) (2020)
- [Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets](https://mlsanity.com/paper/2311.15127/) (2023)
- [Video Diffusion Models](https://mlsanity.com/paper/2204.03458/) (2022)
- [CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer](https://mlsanity.com/paper/2408.06072/) (2024)
- [Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone](https://mlsanity.com/paper/2404.14219/) (2024)
- [VBench: Comprehensive Benchmark Suite for Video Generative Models](https://mlsanity.com/paper/2311.17982/) (2023)
- [AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning](https://mlsanity.com/paper/2307.04725/) (2023)
- [MUSIQ: Multi-scale Image Quality Transformer](https://mlsanity.com/paper/2108.05997/) (2021)
- [CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformers](https://mlsanity.com/paper/2205.15868/) (2022)
- [eDiff-I: Text-to-Image Diffusion Models with an Ensemble of Expert Denoisers](https://mlsanity.com/paper/2211.01324/) (2022)
- [PixArt-α: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis](https://mlsanity.com/paper/2310.00426/) (2023)
- [Yi: Open Foundation Models by 01.AI](https://mlsanity.com/paper/2403.04652/) (2024)
- [Baichuan 2: Open Large-scale Language Models](https://mlsanity.com/paper/2309.10305/) (2023)
- [Language Model Beats Diffusion -- Tokenizer is Key to Visual Generation](https://mlsanity.com/paper/2310.05737/) (2023)
- [InternVid: A Large-scale Video-Text Dataset for Multimodal Understanding and Generation](https://mlsanity.com/paper/2307.06942/) (2023)
- [VideoPoet: A Large Language Model for Zero-Shot Video Generation](https://mlsanity.com/paper/2312.14125/) (2023)
- [ELLA: Equip Diffusion Models with LLM for Enhanced Semantic Alignment](https://mlsanity.com/paper/2403.05135/) (2024)
- [LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders](https://mlsanity.com/paper/2404.05961/) (2024)
- [MAGVIT: Masked Generative Video Transformer](https://mlsanity.com/paper/2212.05199/) (2022)

## Built on by (most cited first, 16 of 16)

- [DreamRelation: Relation-Centric Video Customization](https://mlsanity.com/paper/2503.07602/) (2025)
- [PhysRVG: Physics-Aware Unified Reinforcement Learning for Video Generative Models](https://mlsanity.com/paper/2601.11087/) (2026)
- [FixTalk: Taming Identity Leakage for High-Quality Talking Head Generation in Extreme Cases](https://mlsanity.com/paper/2507.01390/) (2025)
- [Ming-Lite-Uni: Advancements in Unified Architecture for Natural Multimodal Interaction](https://mlsanity.com/paper/2505.02471/) (2025)
- [MOS: Modeling Object-Scene Associations in Generalized Category Discovery](https://mlsanity.com/paper/2503.12035/) (2025)
- [Animate-X++: Universal Character Image Animation with Dynamic Backgrounds](https://mlsanity.com/paper/2508.09454/) (2025)
- [SynMotion: Semantic-Visual Adaptation for Motion Customized Video Generation](https://mlsanity.com/paper/2506.23690/) (2025)
- [Dynamic-I2V: Exploring Image-to-Video Generation Models via Multimodal LLM](https://mlsanity.com/paper/2505.19901/) (2025)
- [EDTalk++: Full Disentanglement for Controllable Talking Head Synthesis](https://mlsanity.com/paper/2508.13442/) (2025)
- [GenTune: Toward Traceable Prompts to Improve Controllability of Image Refinement in Environment Design](https://mlsanity.com/paper/2508.15227/) (2025)
- [RISE-T2V: Rephrasing and Injecting Semantics with LLM for Expansive Text-to-Video Generation](https://mlsanity.com/paper/2511.04317/) (2025)
- [CoDance: An Unbind-Rebind Paradigm for Robust Multi-Subject Animation](https://mlsanity.com/paper/2601.11096/) (2026)
- [Surprise Forcing: What to Remember, When to Skip in Long Video Generation](https://mlsanity.com/paper/2607.18436/) (2026)
- [ESGaussianFace: Emotional and Stylized Audio-Driven Facial Animation via 3D Gaussian Splatting](https://mlsanity.com/paper/2601.01847/) (2026)
- [Bridging Brain and Semantics: A Hierarchical Framework for Semantically Enhanced fMRI-to-Video Reconstruction](https://mlsanity.com/paper/2605.14569/) (2026)
- [Sharpness-aware Model Merging with Salience Recovery for LLM-based Cross-Domain Sequential Recommendation](https://mlsanity.com/paper/2607.25366/) (2026)

## Abstract (arXiv)

Text serves as the key control signal in video generation due to its narrative nature. To render text descriptions into video clips, current video diffusion models borrow features from text encoders yet struggle with limited text comprehension. The recent success of large language models (LLMs) showcases the power of decoder-only transformers, which offers three clear benefits for text-to-video (T2V) generation, namely, precise text understanding resulting from the superior scalability, imagination beyond the input text enabled by next token prediction, and flexibility to prioritize user interests through instruction tuning. Nevertheless, the feature distribution gap emerging from the two different text modeling paradigms hinders the direct use of LLMs in established T2V models. This work addresses this challenge with Mimir, an end-to-end training framework featuring a carefully tailored token fuser to harmonize the outputs from text encoders and LLMs. Such a design allows the T2V model to fully leverage learned video priors while capitalizing on the text-related capability of LLMs. Extensive quantitative and qualitative results demonstrate the effectiveness of Mimir in generating high-quality videos with excellent text comprehension, especially when processing short captions and managing shifting motions. Project page: https://lucaria-academy.github.io/Mimir/