mlsanityData to 7 Oct 2026

SANA 1.5: Efficient Scaling of Training-Time and Inference-Time Compute in Linear Diffusion Transformer

arXiv 2501.18427 ↗First posted 30 Jan 2025cs.CVcited by 165

On the map: LLM reasoning → Diffusion reasoning and test-time scaling

also in 1 more
Abstract (arXiv)

This paper presents SANA-1.5, a linear Diffusion Transformer for efficient scaling in text-to-image generation. Building upon SANA-1.0, we introduce three key innovations: (1) Efficient Training Scaling: A depth-growth paradigm that enables scaling from 1.6B to 4.8B parameters with significantly reduced computational resources, combined with a memory-efficient 8-bit optimizer. (2) Model Depth Pruning: A block importance analysis technique for efficient model compression to arbitrary sizes with minimal quality loss. (3) Inference-time Scaling: A repeated sampling strategy that trades computation for model capacity, enabling smaller models to match larger model quality at inference time. Through these strategies, SANA-1.5 achieves a text-image alignment score of 0.81 on GenEval, which can be further improved to 0.96 through inference scaling with VILA-Judge, establishing a new SoTA on GenEval benchmark. These innovations enable efficient model scaling across different compute budgets while maintaining high quality, making high-quality image generation more accessible. Our code and pre-trained models are released.

Key facts. Cited by 165 papers in the map (data through 7 Oct 2026). Placed in Diffusion reasoning and test-time scaling, one of 17 directions in LLM reasoning. Builds on 47 of its 56 references that are in the map. First posted on arXiv 30 Jan 2025.

Builds on

47 of 56 references.

Closest ancestors · 2

Same direction, newest first

  1. 2025Inference-Time Scaling for Diffusion Models beyond Scaling Denoising Steps16 Jan
  2. 2025A General Framework for Inference-time Scaling and Steering of Diffusion Models12 Jan

Other references · 45

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  3. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  4. 2023GPT-4 Technical Reportcited by 18,132
  5. 2024The Llama 3 Herd of Modelscited by 14,192
  6. 2020Scaling Laws for Neural Language Modelscited by 6,411
  7. 2022Scalable Diffusion Models with Transformerscited by 5,931
  8. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,601
  9. 2023SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesiscited by 4,290
  10. 2024Scaling Rectified Flow Transformers for High-Resolution Image Synthesiscited by 4,094
  11. 2024Gemini 1.5: Unlocking multimodal understanding across millions of tokens of contextcited by 3,175
  12. 2015Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Codingcited by 2,291
33 more
  1. 2019Root Mean Square Layer Normalizationcited by 1,425
  2. 2023ImageReward: Learning and Evaluating Human Preferences for Text-to-Image Generationcited by 1,010
  3. 2024Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Predictioncited by 1,005
  4. 2021Scaling Vision Transformerscited by 993
  5. 2023GenEval: An Object-Focused Framework for Evaluating Text-to-Image Alignmentcited by 946
  6. 2024Large Language Monkeys: Scaling Inference Compute with Repeated Samplingcited by 946
  7. 2023PixArt-α: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesiscited by 854
  8. 2019Once-for-All: Train One Network and Specialize it for Efficient Deploymentcited by 778
  9. 2024Emu3: Next-Token Prediction is All You Needcited by 761
  10. 2024Autoregressive Model Beats Diffusion: Llama for Scalable Image Generationcited by 760
  11. 2023LLM-Pruner: On the Structural Pruning of Large Language Modelscited by 643
  12. 2024ELLA: Equip Diffusion Models with LLM for Enhanced Semantic Alignmentcited by 455
  13. 20218-bit Optimizers via Block-wise Quantizationcited by 395
  14. 2024SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformerscited by 331
  15. 2024PixArt-Sigma: Weak-to-Strong Training of Diffusion Transformer for 4K Text-to-Image Generationcited by 326
  16. 2024Infinity: Scaling Bitwise AutoRegressive Modeling for High-Resolution Image Synthesiscited by 297
  17. 2024Hunyuan-DiT: A Powerful Multi-Resolution Diffusion Transformer with Fine-Grained Chinese Understandingcited by 294
  18. 2024Playground v2.5: Three Insights towards Enhancing Aesthetic Quality in Text-to-Image Generationcited by 249
  19. 2015Net2Net: Accelerating Learning via Knowledge Transfercited by 245
  20. 2023SnapFusion: Text-to-Image Diffusion Model on Mobile Devices within Two Secondscited by 227
  21. 2024ShieldGemma: Generative AI Content Moderation Based on Gemmacited by 224
  22. 2024Deep Compression Autoencoder for Efficient High-Resolution Diffusion Modelscited by 209
  23. 2024NVILA: Efficient Frontier Visual Language Modelscited by 206
  24. 2023Progressive-Hint Prompting Improves Reasoning in Large Language Modelscited by 147
  25. 2024Lumina-Next: Making Lumina-T2X Stronger and Faster with Next-DiTcited by 130
  26. 2022Revisiting Neural Scaling Laws in Language and Visioncited by 129
  27. 2024HART: Efficient Visual Generation with Hybrid Autoregressive Transformercited by 128
  28. 2024Playground v3: Improving Text-to-Image Alignment with Deep-Fusion Large Language Modelscited by 113
  29. 2024LLM Pruning and Distillation in Practice: The Minitron Approachcited by 82
  30. 2024Scaling Laws For Diffusion Transformerscited by 41
  31. 2024On the Scalability of Diffusion-based Text-to-Image Generationcited by 36
  32. 2023CAME: Confidence-guided Adaptive Memory Efficient Optimizationcited by 34
  33. 2024SnapGen: Taming High-Resolution Text-to-Image Models for Mobile Devices with Efficient Architectures and Trainingcited by 27

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 99; 2026: 66.

165 papers.

Sort:

By area:

  1. 2025Qwen-Image Technical Reportcited by 973
  2. 2025Flow-GRPO: Training Flow Matching Models via Online RLcited by 605
  3. 2025Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Modelscited by 381
  4. 2025YOLOv12: Attention-Centric Real-Time Object Detectorscited by 300
  5. 2025In-Context Edit: Enabling Instructional Image Editing with In-Context Generation in Large Scale Diffusion Transformercited by 199
  6. 2025Sparse VideoGen2: Accelerate Video Generation with Sparse Attention via Semantic-Aware Permutationcited by 100
  7. 2025Lumina-Image 2.0: A Unified and Efficient Image Generative Frameworkcited by 93
  8. 2025TempFlow-GRPO: When Timing Matters for GRPO in Flow Modelscited by 93
  9. 2025SANA-Video: Efficient Video Generation with Block Linear Diffusion Transformercited by 91
  10. 2025SANA-Sprint: One-Step Diffusion with Continuous-Time Consistency Distillationcited by 85
  11. 2025Lumina-DiMOO: An Omni Diffusion Large Language Model for Multi-Modal Generation and Understandingcited by 83
  12. 2025Large Scale Diffusion Distillation via Score-Regularized Continuous-Time Consistencycited by 81
38 more
  1. 2025TIIF-Bench: How Does Your T2I Model Follow Your Instructions?cited by 64
  2. 2025NextStep-1: Toward Autoregressive Image Generation with Continuous Tokens at Scalecited by 55
  3. 2025From Reflection to Perfection: Scaling Inference-Time Optimization for Text-to-Image Diffusion Models via Reflection Tuningcited by 53
  4. 2026Scaling Text-to-Image Diffusion Transformers with Representation Autoencoderscited by 49
  5. 2025Inference-time Scaling of Diffusion Models through Classical Searchcited by 48
  6. 2025Reconstruction Alignment Improves Unified Multimodal Modelscited by 48
  7. 2025FUDOKI: Discrete Flow-based Unified Understanding and Generation via Kinetic-Optimal Velocitiescited by 46
  8. 2025OpenUni: A Simple Baseline for Unified Multimodal Understanding and Generationcited by 45
  9. 2025DC-AE 1.5: Accelerating Diffusion Model Convergence with Structured Latent Spacecited by 44
  10. 2025Reflect-DiT: Inference-Time Scaling for Text-to-Image Diffusion Transformers via In-Context Reflectioncited by 42
  11. 2025Interleaving Reasoning for Better Text-to-Image Generationcited by 40
  12. 2025Scaling Image and Video Generation via Test-Time Evolutionary Searchcited by 38
  13. 2025Skywork UniPic 2.0: Building Kontext Model with Online RL for Unified Multimodal Modelcited by 38
  14. 2025Inference-Time Scaling for Flow Models via Stochastic Generation and Rollover Budget Forcingcited by 37
  15. 2025FLUX-Reason-6M & PRISM-Bench: A Million-Scale Text-to-Image Reasoning Dataset and Comprehensive Benchmarkcited by 37
  16. 2025Lumina-mGPT 2.0: Stand-Alone AutoRegressive Image Modelingcited by 35
  17. 2025REPA Works Until It Doesn't: Early-Stopped, Holistic Alignment Supercharges Diffusion Trainingcited by 33
  18. 2025UniGen: Enhanced Training & Test-Time Strategies for Unified Multimodal Understanding and Generationcited by 32
  19. 2025Transition Models: Rethinking the Generative Learning Objectivecited by 32
  20. 2026Beyond Language Modeling: An Exploration of Multimodal Pretrainingcited by 32
  21. 2025R2I-Bench: Benchmarking Reasoning-Driven Text-to-Image Generationcited by 31
  22. 2025MindOmni: Unleashing Reasoning Generation in Vision Language Models with RGPOcited by 30
  23. 2025textttComplex-Edit: CoT-Like Instruction Generation for Complexity-Controllable Image Editing Benchmarkcited by 25
  24. 2025VeriThinker: Learning to Verify Makes Reasoning Model Efficientcited by 24
  25. 2025RePrompt: Reasoning-Augmented Reprompting for Text-to-Image Generation via Reinforcement Learningcited by 22
  26. 2025Lumos-1: On Autoregressive Video Generation with Discrete Diffusion from a Unified Model Perspectivecited by 22
  27. 2025NExT-OMNI: Towards Any-to-Any Omnimodal Foundation Models with Discrete Flow Matchingcited by 19
  28. 2025UniPercept: Towards Unified Perceptual-Level Image Understanding across Aesthetics, Quality, Structure, and Texturecited by 19
  29. 2025A Survey of Slow Thinking-based Reasoning LLMs using Reinforced Learning and Inference-time Scaling Lawcited by 18
  30. 2025TwinFlow: Realizing One-step Generation on Large Models with Self-adversarial Flowscited by 17
  31. 2025GARDO: Reinforcing Diffusion Models without Reward Hackingcited by 17
  32. 2025Factuality Matters: When Image Generation and Editing Meet Structured Visualscited by 16
  33. 2025Exploring the Deep Fusion of Large Language Models and Diffusion Transformers for Text-to-Image Synthesiscited by 15
  34. 2025TTS-VAR: A Test-Time Scaling Framework for Visual Auto-Regressive Generationcited by 15
  35. 2025STAGE: Stable and Generalizable GRPO for Autoregressive Image Generationcited by 15
  36. 2025Lavida-O: Elastic Large Masked Diffusion Models for Unified Multimodal Understanding and Generationcited by 14
  37. 2025ImAgent: A Unified Multimodal Agent Framework for Test-Time Scalable Image Generationcited by 14
  38. 2026Everything in Its Place: Benchmarking Spatial Intelligence of Text-to-Image Modelscited by 14

50 most cited of 165 All 165 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2026Abra: Scaling Diffusion Image Training
  2. 2024Efficient Scaling of Diffusion Transformers for Text-to-Image Generation
  3. 2026Flash-BoN: Instant Drafts for Inference-Time Scaling in Diffusion Models
  4. 2024Towards Precise Scaling Laws for Video Diffusion Transformers
  5. 2024EC-DIT: Scaling Diffusion Transformers with Adaptive Expert-Choice Routing
  6. 2025Performance Plateaus in Inference-Time Scaling for Text-to-Image Diffusion Without External Models
  7. 2024Diffusion-RWKV: Scaling RWKV-Like Architectures for Diffusion Models
  8. 2025Glance: Accelerating Diffusion Models with 1 Sample