mlsanityData to 7 Oct 2026

Lossy Compression with Pretrained Diffusion Models

arXiv 2501.09815 ↗First posted 16 Jan 2025cs.CV eess.IVcited by 23

On the map: Diffusion models → Diffusion for compression and wireless

Abstract (arXiv)

We apply the DiffC algorithm (Theis et al. 2022) to Stable Diffusion 1.5, 2.1, XL, and Flux-dev, and demonstrate that these pretrained models are remarkably capable lossy image compressors. A principled algorithm for lossy compression using pretrained diffusion models has been understood since at least Ho et al. 2020, but challenges in reverse-channel coding have prevented such algorithms from ever being fully implemented. We introduce simple workarounds that lead to the first complete implementation of DiffC, which is capable of compressing and decompressing images using Stable Diffusion in under 10 seconds. Despite requiring no additional training, our method is competitive with other state-of-the-art generative compression methods at low ultra-low bitrates.

Key facts. Cited by 23 papers in the map (data through 7 Oct 2026). Placed in Diffusion for compression and wireless, one of 14 directions in Diffusion models. Builds on 31 of its 39 references that are in the map. First posted on arXiv 16 Jan 2025.

Builds on

31 of 39 references.

Closest ancestors · 3

Same direction, newest first

  1. 2024Towards Extreme Image Compression with Latent Feature Guidance and Diffusion Prior29 Apr
  2. 2022Lossy Image Compression with Conditional Diffusion Models14 Sep
  3. 2022Lossy Compression with Gaussian Diffusion17 Jun

Other references · 28

  1. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  2. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  3. 2020Denoising Diffusion Implicit Modelscited by 9,655
  4. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,005
  5. 2023Adding Conditional Control to Text-to-Image Diffusion Modelscited by 5,466
  6. 2022Flow Matching for Generative Modelingcited by 5,426
  7. 2023SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesiscited by 4,290
  8. 2024Scaling Rectified Flow Transformers for High-Resolution Image Synthesiscited by 4,094
  9. 2022Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flowcited by 3,550
  10. 2022DreamFusion: Text-to-3D using 2D Diffusioncited by 3,006
  11. 2021CLIPScore: A Reference-free Evaluation Metric for Image Captioningcited by 2,388
  12. 2022Diffusion Posterior Sampling for General Noisy Inverse Problemscited by 1,375
16 more
  1. 2021Variational Diffusion Modelscited by 1,145
  2. 2018Joint Autoregressive and Hierarchical Priors for Learned Image Compressioncited by 642
  3. 2023Q-Align: Teaching LMMs for Visual Scoring via Discrete Text-Defined Levelscited by 489
  4. 2023DeepCache: Accelerating Diffusion Models for Freecited by 346
  5. 2020High-Fidelity Generative Image Compressioncited by 331
  6. 2023Hard Prompts Made Easy: Gradient-Based Discrete Optimization for Prompt Tuning and Discoverycited by 329
  7. 2020PIPAL: a Large-Scale Image Quality Assessment Dataset for Perceptual Image Restorationcited by 177
  8. 2023Towards image compression with perfect realism at ultra-low bitratescited by 99
  9. 2023Improving Statistical Fidelity for Neural Image Compression with Implicit Local Likelihood Modelscited by 90
  10. 2023Text + Sketch: Image Compression at Ultra Low Ratescited by 63
  11. 2018Minimal Random Code Learning: Getting Bits Back from Compressed Model Parameterscited by 56
  12. 2023Visual Anagrams: Generating Multi-View Optical Illusions with Diffusion Modelscited by 46
  13. 2023ElasticDiffusion: Training-free Arbitrary Size Image Generation through Global-Local Content Separationcited by 37
  14. 2021Algorithms for the Communication of Samplescited by 31
  15. 2024Idempotence and Perceptual Image Compressioncited by 27
  16. 2024Factorized Diffusion: Perceptual Illusions by Noise Decompositioncited by 23

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 9; 2026: 14.

23 papers.

Sort:

By area:

  1. 2025One-Step Diffusion-Based Image Compression with Semantic Distillationcited by 23
  2. 2025CoD: A Diffusion Foundation Model for Image Compressioncited by 9
  3. 2025Turbo-DDCM: Fast and Flexible Zero-Shot Diffusion-Based Image Compressioncited by 4
  4. 2025Ultra-Low Bitrate Perceptual Image Compression with Shallow Encodercited by 4
  5. 2026Dual-Representation Image Compression at Ultra-Low Bitrates via Explicit Semantics and Implicit Texturescited by 4
  6. 2025Steering One-Step Diffusion Model with Fidelity-Rich Decoder for Fast Image Compressioncited by 3
  7. 2026Scalable Differentially Private Data Compression via Diffusion and Stochastic Codescited by 3
  8. 2026Compression as Adaptation: Implicit Visual Representation with Diffusion Foundation Modelscited by 2
  9. 2026Next-Frame Decoding for Ultra-Low-Bitrate Image Compression with Video Diffusion Priorscited by 2
  10. 2026GVCC: Zero-Shot Video Compression via Codebook-Driven Stochastic Rectified Flowcited by 2
  11. 2025Training-Free Vector Quantization via Gaussian VAEscited by 1
  12. 2026ZeroGVC: Zero-Shot Generative Video Compression with Autoregressive Diffusion Priorscited by 1
11 more
  1. 2025PerCoV2: Ultra-Low Bit-Rate Perceptual Image Compression via Query-Based 1D Multimodal Image Tokenscited by 0
  2. 2025FaSDiff: Balancing Perception and Semantics in Face Compression via Stable Diffusion Priorscited by 0
  3. 2025Generative Semantic Coding for Ultra-Low Bitrate Visual Communication and Analysiscited by 0
  4. 2026Advances in Diffusion-Based Generative Compressioncited by 0
  5. 2026Training-Free Rate-Distortion-Perception Traversal With Diffusioncited by 0
  6. 2026Region-Adaptive Generative Compression with Spatially Varying Diffusion Modelscited by 0
  7. 2026On the Robustness of Diffusion-Based Image Compression to Bit-Flip Errorscited by 0
  8. 2026Few-step Generative Models as Lossy Compressioncited by 0
  9. 2026Scalable Discrete-to-Continuous Channel Simulation for Compression and Privacycited by 0
  10. 2026Rethinking Generative Image Compression at Extremely Low Bitratescited by 0
  11. 2026ResARC: Residual-Aware AutoRegressive Coding for Ultra-Low Bitrate Image Compressioncited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025StableCodec: Taming One-Step Diffusion for Extreme Image Compression
  2. 2024Lossy Image Compression with Foundation Diffusion Models
  3. 2026CoD-Lite: Real-Time Diffusion-Based Generative Image Compression
  4. 2025OSCAR: One-Step Diffusion Codec Across Multiple Bit-rates
  5. 2025Single-step Diffusion for Image Compression at Ultra-Low Bitrates
  6. 2026Towards Efficient Low-rate Image Compression with Frequency-aware Diffusion Prior Refinement
  7. 2026DiT-IC: Aligned Diffusion Transformer for Efficient Image Compression
  8. 2025HDCompression: Hybrid-Diffusion Image Compression for Ultra-Low Bitrates