# DOLLAR: Few-Step Video Generation via Distillation and Latent Reward Optimization

arXiv: https://arxiv.org/abs/2412.15689 · HTML: https://mlsanity.com/paper/2412.15689/

## Key facts

- Cited by 26 papers in the map (data through 14 Oct 2026).
- Placed in Video generation, one of 14 directions in Diffusion models.
- Builds on 66 of its 77 references that are in the map.
- First posted on arXiv 20 Dec 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 66)

- [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)
- [Deep Unsupervised Learning using Nonequilibrium Thermodynamics](https://mlsanity.com/paper/1503.03585/) (2015)
- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [Classifier-Free Diffusion Guidance](https://mlsanity.com/paper/2207.12598/) (2022)
- [Flow Matching for Generative Modeling](https://mlsanity.com/paper/2210.02747/) (2022)
- [Scaling Rectified Flow Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2403.03206/) (2024)
- [LAION-5B: An open large-scale dataset for training next generation image-text models](https://mlsanity.com/paper/2210.08402/) (2022)
- [Generative Modeling by Estimating Gradients of the Data Distribution](https://mlsanity.com/paper/1907.05600/) (2019)
- [Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow](https://mlsanity.com/paper/2209.03003/) (2022)
- [DreamFusion: Text-to-3D using 2D Diffusion](https://mlsanity.com/paper/2209.14988/) (2022)
- [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)
- [DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Steps](https://mlsanity.com/paper/2206.00927/) (2022)
- [Consistency Models](https://mlsanity.com/paper/2303.01469/) (2023)
- [VBench: Comprehensive Benchmark Suite for Video Generative Models](https://mlsanity.com/paper/2311.17982/) (2023)
- [Make-A-Video: Text-to-Video Generation without Text-Video Data](https://mlsanity.com/paper/2209.14792/) (2022)
- [HunyuanVideo: A Systematic Framework For Large Video Generative Models](https://mlsanity.com/paper/2412.03603/) (2024)
- [Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2304.08818/) (2023)
- [Diffusion Posterior Sampling for General Noisy Inverse Problems](https://mlsanity.com/paper/2209.14687/) (2022)
- [ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillation](https://mlsanity.com/paper/2305.16213/) (2023)
- [ImageReward: Learning and Evaluating Human Preferences for Text-to-Image Generation](https://mlsanity.com/paper/2304.05977/) (2023)
- [One-step Diffusion with Distribution Matching Distillation](https://mlsanity.com/paper/2311.18828/) (2023)
- [CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformers](https://mlsanity.com/paper/2205.15868/) (2022)
- [Training Diffusion Models with Reinforcement Learning](https://mlsanity.com/paper/2305.13301/) (2023)
- [Pick-a-Pic: An Open Dataset of User Preferences for Text-to-Image Generation](https://mlsanity.com/paper/2305.01569/) (2023)

## Built on by (most cited first, 26 of 26)

- [Flow Q-Learning](https://mlsanity.com/paper/2502.02538/) (2025)
- [VRAG: Learning World Models for Interactive Video Generation](https://mlsanity.com/paper/2505.21996/) (2025)
- [FlashVideo: Flowing Fidelity to Detail for Efficient High-Resolution Video Generation](https://mlsanity.com/paper/2502.05179/) (2025)
- [Transition Matching Distillation for Fast Video Generation](https://mlsanity.com/paper/2601.09881/) (2026)
- [FPSAttention: Training-Aware FP8 and Sparsity Co-Design for Fast Video Diffusion](https://mlsanity.com/paper/2506.04648/) (2025)
- [Flash-WAM: Modality-Aware Distillation for World Action Models](https://mlsanity.com/paper/2606.05254/) (2026)
- [Video Generation Models Are Good Latent Reward Models](https://mlsanity.com/paper/2511.21541/) (2025)
- [LatSearch: Latent Reward-Guided Search for Faster Inference-Time Scaling in Video Diffusion](https://mlsanity.com/paper/2603.14526/) (2026)
- [StreamingEffect: Real-Time Human-Centric Video Effect Generation](https://mlsanity.com/paper/2605.17019/) (2026)
- [Towards Reason-Informed Video Editing in Unified Models with Self-Reflective Learning](https://mlsanity.com/paper/2512.09924/) (2025)
- [Efficient Video Diffusion Models: Advancements and Challenges](https://mlsanity.com/paper/2604.15911/) (2026)
- [Flex-Forcing: Towards a Unified Autoregressive and Bidirectional Video Diffusion Model](https://mlsanity.com/paper/2607.03509/) (2026)
- [Learning from Noisy Preferences: A Semi-Supervised Learning Approach to Direct Preference Optimization](https://mlsanity.com/paper/2604.24952/) (2026)
- [Exploring Data-Free LoRA Transferability for Video Diffusion Models](https://mlsanity.com/paper/2605.01929/) (2026)
- [World Models: A Comprehensive Survey of Architectures, Methodologies, Reasoning Paradigms, and Applications](https://mlsanity.com/paper/2606.00133/) (2026)
- [VC-Attention: Value Smoothing and Softmax Casting for Low-bit Attention](https://mlsanity.com/paper/2609.15810/) (2026)
- [FIS-DiT: Breaking the Few-Step Video Inference Barrier via Training-Free Frame Interleaved Sparsity](https://mlsanity.com/paper/2605.11869/) (2026)
- [StressDream: Steering Video World Models for Robust Policy Evaluation and Improvement](https://mlsanity.com/paper/2606.00267/) (2026)
- [Mitigating Compounding Error via Video Representation Regularization](https://mlsanity.com/paper/2607.27036/) (2026)
- [DuoMatching: Joint-Marginal Distribution Matching for Few-Step Video Generation](https://mlsanity.com/paper/2610.03543/) (2026)
- [Forecasting in Offline Reinforcement Learning for Non-stationary Environments](https://mlsanity.com/paper/2512.01987/) (2025)
- [Reward Lightning: Fast Video Generation via Homologous Preference Distillation](https://mlsanity.com/paper/2607.03960/) (2026)
- [Reinforcement Learning: From Algorithms To Foundation Models](https://mlsanity.com/paper/2607.17560/) (2026)
- [OSVE: One Step Video Editing with One Step Diffusion Models](https://mlsanity.com/paper/2607.19895/) (2026)
- [LongLive-Plug: Once-for-All Distillation for Video Generation](https://mlsanity.com/paper/2609.38154/) (2026)
- [Uncertainty-Aware Consistency Distillation for Few-Step Video Generation](https://mlsanity.com/paper/2609.39132/) (2026)

## Abstract (arXiv)

Diffusion probabilistic models have shown significant progress in video generation; however, their computational efficiency is limited by the large number of sampling steps required. Reducing sampling steps often compromises video quality or generation diversity. In this work, we introduce a distillation method that combines variational score distillation and consistency distillation to achieve few-step video generation, maintaining both high quality and diversity. We also propose a latent reward model fine-tuning approach to further enhance video generation performance according to any specified reward metric. This approach reduces memory usage and does not require the reward to be differentiable. Our method demonstrates state-of-the-art performance in few-step generation for 10-second videos (128 frames at 12 FPS). The distilled student model achieves a score of 82.57 on VBench, surpassing the teacher model as well as baseline models Gen-3, T2V-Turbo, and Kling. One-step distillation accelerates the teacher model's diffusion sampling by up to 278.6 times, enabling near real-time generation. Human evaluations further validate the superior performance of our 4-step student models compared to teacher model using 50-step DDIM sampling.