LatentCRF: Continuous CRF for Efficient Latent Diffusion
On the map: Diffusion models → Diffusion foundations and sampling
Abstract (arXiv)
Latent Diffusion Models (LDMs) produce high-quality, photo-realistic images, however, the latency incurred by multiple costly inference iterations can restrict their applicability. We introduce LatentCRF, a continuous Conditional Random Field (CRF) model, implemented as a neural network layer, that models the spatial and semantic relationships among the latent vectors in the LDM. By replacing some of the computationally-intensive LDM inference iterations with our lightweight LatentCRF, we achieve a superior balance between quality, speed and diversity. We increase inference efficiency by 33% with no loss in image quality or diversity compared to the full LDM. LatentCRF is an easy add-on, which does not require modifying the LDM.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models. Builds on 20 of its 67 references that are in the map. First posted on arXiv 24 Dec 2024.
Builds on
20 of 67 references.
Closest ancestors · 12
Same direction, newest first
- 2024Improved Distribution Matching Distillation for Fast Image Synthesis23 May
- 2024SDXL-Lightning: Progressive Adversarial Diffusion Distillation21 Feb
- 2023Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inference6 Oct
- 2023FreeU: Free Lunch in Diffusion U-Net20 Sep
- 2023SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis4 Jul
- 2023Squeezing Large-Scale Diffusion Models for Mobile3 Jul
- 2023BK-SDM: A Lightweight, Fast, and Cheap Version of Stable Diffusion25 May
- 2023UniPC: A Unified Predictor-Corrector Framework for Fast Sampling of Diffusion Models9 Feb
- 2022DPM-Solver++: Fast Solver for Guided Sampling of Diffusion Probabilistic Models2 Nov
- 2021Tackling the Generative Learning Trilemma with Denoising Diffusion GANs15 Dec
- 2021Gotta Go Fast When Generating Data with Score-Based Models28 May
- 2020Denoising Diffusion Implicit Models6 Oct
Other references · 8
- 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,539
- 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,322
- 2017Neural Discrete Representation Learningcited by 4,650
- 2023InstaFlow: One Step is Enough for High-Quality Diffusion-Based Text-to-Image Generationcited by 387
- 2023SnapFusion: Text-to-Image Diffusion Model on Mobile Devices within Two Secondscited by 227
- 2023Diffusion Illusions: Hiding Images in Plain Sightcited by 26
- 2023Cousins Of The Vendi Score: A Family Of Similarity-Based Diversity Metrics For Science And Machine Learningcited by 24
- 2024StructLDM: Structured Latent Diffusion for 3D Human Generationcited by 17
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2024Pixel-Space Post-Training of Latent Diffusion Models
- 2025Alias-Free Latent Diffusion Models: Improving Fractional Shift Equivariance of Diffusion Latent Space
- 2024On Improved Conditioning Mechanisms and Pre-training Strategies for Diffusion Models
- 2026LDM-is-AE: Latent Diffusion Model is an Auto-Encoder for End-to-End Image Generation
- 2024Bigger is not Always Better: Scaling Properties of Latent Diffusion Models
- 2024Boosting Latent Diffusion with Perceptual Objectives
- 2025REGLUE Your Latents with Global and Local Semantics for Entangled Diffusion
- 2024Nested Diffusion Models Using Hierarchical Latent Priors