mlsanityData to 7 Oct 2026

Trajectory Consistency Distillation: Improved Latent Consistency Distillation by Semi-Linear Consistency Function with Trajectory Mapping

arXiv 2402.19159 ↗First posted 29 Feb 2024cs.CVcited by 44

On the map: Diffusion models → Diffusion foundations and sampling

Abstract (arXiv)

Latent Consistency Model (LCM) extends the Consistency Model to the latent space and leverages the guided consistency distillation technique to achieve impressive performance in accelerating text-to-image synthesis. However, we observed that LCM struggles to generate images with both clarity and detailed intricacy. Consequently, we introduce Trajectory Consistency Distillation (TCD), which encompasses trajectory consistency function and strategic stochastic sampling. The trajectory consistency function diminishes the parameterisation and distillation errors by broadening the scope of the self-consistency boundary condition with trajectory mapping and endowing the TCD with the ability to accurately trace the entire trajectory of the Probability Flow ODE in semi-linear form with an Exponential Integrator. Additionally, strategic stochastic sampling provides explicit control of stochastic and circumvents the accumulated errors inherent in multi-step consistency sampling. Experiments demonstrate that TCD not only significantly enhances image quality at low NFEs but also yields more detailed results compared to the teacher model at high NFEs.

Key facts. Cited by 44 papers in the map (data through 7 Oct 2026). Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models. Builds on 44 of its 56 references that are in the map. First posted on arXiv 29 Feb 2024.

Builds on

44 of 56 references.

Closest ancestors · 28

Same direction, newest first

  1. 2023Adversarial Diffusion Distillation28 Nov
  2. 2023LCM-LoRA: A Universal Stable-Diffusion Acceleration Module9 Nov
  3. 2023Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inference6 Oct
  4. 2023Consistency Trajectory Models: Learning Probability Flow ODE Trajectory of Diffusion1 Oct
  5. 2023Convergence guarantee for consistency models22 Aug
  6. 2023SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis4 Jul
  7. 2023Restart Sampling for Improving Generative Processes26 Jun
  8. 2023BOOT: Data-free Distillation of Denoising Diffusion Models with Bootstrapping8 Jun
  9. 2023Consistency Models2 Mar
  10. 2022Why Are Conditional Generative Models Better Than Unconditional Ones?1 Dec
  11. 2022DPM-Solver++: Fast Solver for Guided Sampling of Diffusion Probabilistic Models2 Nov
  12. 2022On Distillation of Guided Diffusion Models6 Oct
16 more
  1. 2022Convergence of score-based generative modeling for general data distributions26 Sep
  2. 2022Sampling is as easy as learning the score: theory for diffusion models with minimal data assumptions22 Sep
  3. 2022Classifier-Free Diffusion Guidance26 Jul
  4. 2022DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Steps2 Jun
  5. 2022Elucidating the Design Space of Diffusion-Based Generative Models1 Jun
  6. 2022Fast Sampling of Diffusion Models with Exponential Integrator29 Apr
  7. 2021High-Resolution Image Synthesis with Latent Diffusion Models20 Dec
  8. 2021Variational Diffusion Models1 Jul
  9. 2021Diffusion Schr"odinger Bridge with Applications to Score-Based Generative Modeling1 Jun
  10. 2021On Fast Sampling of Diffusion Probabilistic Models31 May
  11. 2021Gotta Go Fast When Generating Data with Score-Based Models28 May
  12. 2021Diffusion Models Beat GANs on Image Synthesis11 May
  13. 2021Knowledge Distillation in Iterative Generative Models for Improved Sampling Speed7 Jan
  14. 2020Score-Based Generative Modeling through Stochastic Differential Equations26 Nov
  15. 2020Denoising Diffusion Implicit Models6 Oct
  16. 2020Denoising Diffusion Probabilistic Models19 Jun

Other references · 16

  1. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,005
  2. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,539
  3. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,322
  4. 2019Parameter-Efficient Transfer Learning for NLPcited by 4,195
  5. 2022LAION-5B: An open large-scale dataset for training next generation image-text modelscited by 4,131
  6. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,067
  7. 2021GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Modelscited by 3,595
  8. 2023AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuningcited by 1,418
  9. 2020DiffWave: A Versatile Diffusion Model for Audio Synthesiscited by 1,339
  10. 2023ImageReward: Learning and Evaluating Human Preferences for Text-to-Image Generationcited by 1,010
  11. 2022Tune-A-Video: One-Shot Tuning of Image Diffusion Models for Text-to-Video Generationcited by 958
  12. 2023Pick-a-Pic: An Open Dataset of User Preferences for Text-to-Image Generationcited by 950
4 more
  1. 2022eDiff-I: Text-to-Image Diffusion Models with an Ensemble of Expert Denoiserscited by 921
  2. 2020Intrinsic Dimensionality Explains the Effectiveness of Language Model Fine-Tuningcited by 658
  3. 2020WaveGrad: Estimating Gradients for Waveform Generationcited by 620
  4. 2021Grad-TTS: A Diffusion Probabilistic Model for Text-to-Speechcited by 445

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 22; 2025: 19; 2026: 3.

44 papers.

Sort:

By area:

  1. 2024Improved Distribution Matching Distillation for Fast Image Synthesiscited by 648
  2. 2024Fast High-Resolution Image Synthesis with Latent Adversarial Diffusion Distillationcited by 276
  3. 2024Hyper-SD: Trajectory Segmented Consistency Model for Efficient Image Synthesiscited by 153
  4. 2024Phased Consistency Modelscited by 83
  5. 2024One-Step Diffusion Distillation through Score Implicit Matchingcited by 68
  6. 2024A Survey on Diffusion Models for Time Series and Spatio-Temporal Datacited by 66
  7. 2024EM Distillation for One-step Diffusion Modelscited by 60
  8. 2024Adversarial Diffusion Compression for Real-World Image Super-Resolutioncited by 49
  9. 2024SF-V: Single Forward Video Generation Modelcited by 40
  10. 2024OSV: One Step is Enough for High-Quality Image to Video Generationcited by 36
  11. 2024Autoregressive Diffusion Transformer for Text-to-Speech Synthesiscited by 34
  12. 2024Diff-Instruct++: Training One-step Text-to-image Generator Model to Align with Human Preferencescited by 30
32 more
  1. 2024DITTO-2: Distilled Diffusion Inference-Time T-Optimization for Music Generationcited by 26
  2. 2024Unraveling the Smoothness Properties of Diffusion Models: A Gaussian Mixture Perspectivecited by 24
  3. 2025Dual-Expert Consistency Model for Efficient and High-Quality Video Generationcited by 21
  4. 2024Connecting Consistency Distillation to Score Distillation for Text-to-3D Generationcited by 18
  5. 2025Flash-DMD: Towards High-Fidelity Few-Step Image Generation with Efficient Distillation and Joint Reinforcement Learningcited by 17
  6. 2024NitroFusion: High-Fidelity Single-Step Diffusion through Dynamic Adversarial Trainingcited by 16
  7. 2024Instant Adversarial Purification with Adversarial Consistency Distillationcited by 14
  8. 2025Improved Training Technique for Latent Consistency Modelscited by 13
  9. 2025RayFlow: Instance-Aware Diffusion Acceleration via Adaptive Flow Trajectoriescited by 12
  10. 2025Normalized Attention Guidance: Universal Negative Guidance for Diffusion Modelscited by 12
  11. 2025UniLumos: Fast and Unified Image and Video Relighting with Physics-Plausible Feedbackcited by 12
  12. 2024David and Goliath: Small One-step Model Beats Large Diffusion with Score Post-trainingcited by 8
  13. 2024AutoLoRA: AutoGuidance Meets Low-Rank Adaptation for Diffusion Modelscited by 7
  14. 2025PLADIS: Pushing the Limits of Attention in Diffusion Models at Inference Time by Leveraging Sparsitycited by 7
  15. 2026LiveLight: Real-time Streaming Video Relighting with Interactive Controlcited by 6
  16. 2025Differentiable Solver Search for Fast Diffusion Samplingcited by 5
  17. 2025One-Way Ticket:Time-Independent Unified Encoder for Distilling Text-to-Image Diffusion Modelscited by 5
  18. 2024FADA: Fast Diffusion Avatar Synthesis with Mixed-Supervised Multi-CFG Distillationcited by 4
  19. 2025Q-Sched: Pushing the Boundaries of Few-Step Diffusion Models with Quantization-Aware Schedulingcited by 3
  20. 2025Self-Evaluation Unlocks Any-Step Text-to-Image Generationcited by 3
  21. 2025Taming Consistency Distillation for Accelerated Human Image Animationcited by 2
  22. 2024Single Trajectory Distillation for Accelerating Image and Video Style Transfercited by 1
  23. 2025UniCMs: A Unified Consistency Model For Efficient Multimodal Generation and Understandingcited by 1
  24. 2025Sampling-Aware Quantization for Diffusion Modelscited by 1
  25. 2025LawDIS: Language-Window-based Controllable Dichotomous Image Segmentationcited by 1
  26. 2025Adversarial Concept Distillation for One-Step Diffusion Personalizationcited by 1
  27. 2026Fast, faithful and photorealistic diffusion-based image super-resolution with enhanced Flow Map modelscited by 1
  28. 2024Inconsistencies In Consistency Models: Better ODE Solving Does Not Imply Better Samplescited by 0
  29. 2025Designing Parameter and Compute Efficient Diffusion Transformers using Distillationcited by 0
  30. 2025A multi-temporal multi-spectral attention-augmented deep convolution neural network with contrastive learning for crop yield predictioncited by 0
  31. 2025Masked Auto-Regressive Variational Acceleration: Fast Inference Makes Practical Reinforcement Learningcited by 0
  32. 2026D2PO: Optimizing Diffusion Samplers via Dynamic Preferencecited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025SegmentDreamer: Towards High-fidelity Text-to-3D Synthesis with Segmented Consistency Trajectory Distillation
  2. 2024Invertible Consistency Distillation for Text-Guided Image Editing in Around 7 Steps
  3. 2024Reward Guided Latent Consistency Distillation
  4. 2024Consistent3D: Towards Consistent High-Fidelity Text-to-3D Generation with Deterministic Sampling Prior
  5. 2025Image-Free Timestep Distillation via Continuous-Time Consistency with Trajectory-Sampled Pairs
  6. 2024SCott: Accelerating Diffusion Models with Stochastic Consistency Distillation
  7. 2024TLCM: Training-efficient Latent Consistency Model for Image Generation with 2-8 Steps
  8. 2024Target-Driven Distillation: Consistency Distillation with Target Timestep Selection and Decoupled Guidance