# LightGen: Efficient Image Generation through Knowledge Distillation and Direct Preference Optimization

arXiv: https://arxiv.org/abs/2503.08619 · HTML: https://mlsanity.com/paper/2503.08619/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- Placed in Diffusion and multimodal model alignment, one of 10 directions in LLM alignment / RLHF / preference optimisation.
- Builds on 45 of its 51 references that are in the map.
- First posted on arXiv 11 Mar 2025.

## Placed in

- LLM alignment / RLHF / preference optimisation / [Diffusion and multimodal model alignment](https://mlsanity.com/alignment/diffusion-and-multimodal-model-alignment/)
- Knowledge distillation / [Multimodal distillation](https://mlsanity.com/distill/multimodal-distillation/)

## Builds on (most cited first, 30 of 45)

- [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)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [Adding Conditional Control to Text-to-Image Diffusion Models](https://mlsanity.com/paper/2302.05543/) (2023)
- [Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution](https://mlsanity.com/paper/2409.12191/) (2024)
- [Scaling Rectified Flow Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2403.03206/) (2024)
- [Scaling Instruction-Finetuned Language Models](https://mlsanity.com/paper/2210.11416/) (2022)
- [Variational Inference with Normalizing Flows](https://mlsanity.com/paper/1505.05770/) (2015)
- [MaskGIT: Masked Generative Image Transformer](https://mlsanity.com/paper/2202.04200/) (2022)
- [Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction](https://mlsanity.com/paper/2404.02905/) (2024)
- [GenEval: An Object-Focused Framework for Evaluating Text-to-Image Alignment](https://mlsanity.com/paper/2310.11513/) (2023)
- [Diffusion Model Alignment Using Direct Preference Optimization](https://mlsanity.com/paper/2311.12908/) (2023)
- [Autoregressive Model Beats Diffusion: Llama for Scalable Image Generation](https://mlsanity.com/paper/2406.06525/) (2024)
- [Show-o: One Single Transformer to Unify Multimodal Understanding and Generation](https://mlsanity.com/paper/2408.12528/) (2024)
- [SiT: Exploring Flow and Diffusion-based Generative Models with Scalable Interpolant Transformers](https://mlsanity.com/paper/2401.08740/) (2024)
- [Autoregressive Image Generation using Residual Quantization](https://mlsanity.com/paper/2203.01941/) (2022)
- [Autoregressive Image Generation without Vector Quantization](https://mlsanity.com/paper/2406.11838/) (2024)
- [Sentence-T5: Scalable Sentence Encoders from Pre-trained Text-to-Text Models](https://mlsanity.com/paper/2108.08877/) (2021)
- [Simple diffusion: End-to-end diffusion for high resolution images](https://mlsanity.com/paper/2301.11093/) (2023)
- [OmniGen: Unified Image Generation](https://mlsanity.com/paper/2409.11340/) (2024)
- [SEED-X: Multimodal Models with Unified Multi-granularity Comprehension and Generation](https://mlsanity.com/paper/2404.14396/) (2024)
- [MDTv2: Masked Diffusion Transformer is a Strong Image Synthesizer](https://mlsanity.com/paper/2303.14389/) (2023)
- [Open-MAGVIT2: An Open-Source Project Toward Democratizing Auto-regressive Visual Generation](https://mlsanity.com/paper/2409.04410/) (2024)

## Built on by (most cited first, 20 of 20)

- [Qwen-Image Technical Report](https://mlsanity.com/paper/2508.02324/) (2025)
- [Z-Image: An Efficient Image Generation Foundation Model with Single-Stream Diffusion Transformer](https://mlsanity.com/paper/2511.22699/) (2025)
- [T2I-R1: Reinforcing Image Generation with Collaborative Semantic-level and Token-level CoT](https://mlsanity.com/paper/2505.00703/) (2025)
- [TIIF-Bench: How Does Your T2I Model Follow Your Instructions?](https://mlsanity.com/paper/2506.02161/) (2025)
- [Interleaving Reasoning for Better Text-to-Image Generation](https://mlsanity.com/paper/2509.06945/) (2025)
- [Hierarchical Fine-grained Preference Optimization for Physically Plausible Video Generation](https://mlsanity.com/paper/2508.10858/) (2025)
- [TiViBench: Benchmarking Think-in-Video Reasoning for Video Generative Models](https://mlsanity.com/paper/2511.13704/) (2025)
- [VistaDPO: Video Hierarchical Spatial-Temporal Direct Preference Optimization for Large Video Models](https://mlsanity.com/paper/2504.13122/) (2025)
- [Model Reveals What to Cache: Profiling-Based Feature Reuse for Video Diffusion Models](https://mlsanity.com/paper/2504.03140/) (2025)
- [Integrating Reinforcement Learning with Visual Generative Models: Foundations and Advances](https://mlsanity.com/paper/2508.10316/) (2025)
- [Understanding-in-Generation: Reinforcing Generative Capability of Unified Model via Infusing Understanding into Generation](https://mlsanity.com/paper/2509.18639/) (2025)
- [Temporal Regularization Makes Your Video Generator Stronger](https://mlsanity.com/paper/2503.15417/) (2025)
- [TBAC-UniImage: Unified Understanding and Generation by Ladder-Side Diffusion Tuning](https://mlsanity.com/paper/2508.08098/) (2025)
- [Show, Don't Tell: Morphing Latent Reasoning into Image Generation](https://mlsanity.com/paper/2602.02227/) (2026)
- [GenRouter: Unified Workflow Routing for Agentic Image Generation](https://mlsanity.com/paper/2608.16721/) (2026)
- [BitDance: Scaling Autoregressive Generative Models with Binary Tokens](https://mlsanity.com/paper/2602.14041/) (2026)
- [ScalingAR: Scaling Confidence for Autoregressive Image Generation](https://mlsanity.com/paper/2509.26376/) (2025)
- [Generation then Reconstruction: Accelerating Masked Autoregressive Models via Two-Stage Sampling](https://mlsanity.com/paper/2510.17171/) (2025)
- [ArtifactLens: Hundreds of Labels Are Enough for Artifact Detection with VLMs](https://mlsanity.com/paper/2602.09475/) (2026)
- [FR-TTS: Test-Time Scaling for NTP-based Image Generation with Effective Filling-based Reward Signal](https://mlsanity.com/paper/2512.00438/) (2025)

## Abstract (arXiv)

Recent advances in text-to-image generation have primarily relied on extensive datasets and parameter-heavy architectures. These requirements severely limit accessibility for researchers and practitioners who lack substantial computational resources. In this paper, we introduce model, an efficient training paradigm for image generation models that uses knowledge distillation (KD) and Direct Preference Optimization (DPO). Drawing inspiration from the success of data KD techniques widely adopted in Multi-Modal Large Language Models (MLLMs), LightGen distills knowledge from state-of-the-art (SOTA) text-to-image models into a compact Masked Autoregressive (MAR) architecture with only 0.7B parameters. Using a compact synthetic dataset of just 2M high-quality images generated from varied captions, we demonstrate that data diversity significantly outweighs data volume in determining model performance. This strategy dramatically reduces computational demands and reduces pre-training time from potentially thousands of GPU-days to merely 88 GPU-days. Furthermore, to address the inherent shortcomings of synthetic data, particularly poor high-frequency details and spatial inaccuracies, we integrate the DPO technique that refines image fidelity and positional accuracy. Comprehensive experiments confirm that LightGen achieves image generation quality comparable to SOTA models while significantly reducing computational resources and expanding accessibility for resource-constrained environments. Code is available at https://github.com/XianfengWu01/LightGen