{"url":"/method/latent-diffusion-model","slug":"latent-diffusion-model","name":"Latent Diffusion Model","full_name":"Latent Diffusion Model","full_name_withheld":false,"description_markdown":"Diffusion models applied to latent spaces, which are normally built with (Variational) Autoencoders.","description_state":"present","introduced_year":null,"introduced_by":{"title":"High-Resolution Image Synthesis with Latent Diffusion Models","paper":"/paper/high-resolution-image-synthesis-with-latent","first_author":"Robin Rombach","n_authors":5,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/high-resolution-image-synthesis-with-latent"},"source":{"url":"https://arxiv.org/abs/2112.10752v2","title":"High-Resolution Image Synthesis with Latent Diffusion Models","url_on_a_paper_host":true},"code_snippet_url":null,"code_snippet_url_on_a_code_host":false,"categories":[{"area":"General","area_id":"general","collection":"Dimensionality Reduction","url":"/methods/category/dimensionality-reduction","pwc_aliases":[]}],"n_papers_tagged":366,"archive_num_papers":366,"papers_newest_first":[{"paper":null,"title":"Latent Space Consistency for Sparse-View CT Reconstruction","date":"2025-07-15","arxiv_id":"2507.11152","n_code_links":0,"syntology":null},{"paper":null,"title":"MultiViT2: A Data-augmented Multimodal Neuroimaging Prediction Framework via Latent Diffusion Model","date":"2025-06-16","arxiv_id":"2506.13667","n_code_links":0,"syntology":null},{"paper":null,"title":"GM-LDM: Latent Diffusion Model for Brain Biomarker Identification through Functional Data-Driven Gray Matter Synthesis","date":"2025-06-15","arxiv_id":"2506.12719","n_code_links":0,"syntology":null},{"paper":null,"title":"Anatomy-Grounded Weakly Supervised Prompt Tuning for Chest X-ray Latent Diffusion Models","date":"2025-06-12","arxiv_id":"2506.10633","n_code_links":0,"syntology":null},{"paper":null,"title":"High-resolution efficient image generation from WiFi CSI using a pretrained latent diffusion model","date":"2025-06-12","arxiv_id":"2506.10605","n_code_links":0,"syntology":null},{"paper":null,"title":"Latent Diffusion Model Based Denoising Receiver for 6G Semantic Communication: From Stochastic Differential Theory to Application","date":"2025-06-06","arxiv_id":"2506.05710","n_code_links":0,"syntology":null},{"paper":"/paper/latent-wavelet-diffusion-enabling-4k-image","title":"Latent Wavelet Diffusion: Enabling 4K Image Synthesis for Free","date":"2025-05-31","arxiv_id":"2506.00433","n_code_links":0,"syntology":{"ran":2,"of":10,"unverified":8,"pointer_only":0}},{"paper":"/paper/cora-correspondence-aware-image-editing-using","title":"Cora: Correspondence-aware image editing using few step diffusion","date":"2025-05-29","arxiv_id":"2505.23907","n_code_links":1,"syntology":null},{"paper":null,"title":"SAIL: Self-supervised Albedo Estimation from Real Images with a Latent Diffusion Model","date":"2025-05-26","arxiv_id":"2505.19751","n_code_links":0,"syntology":null},{"paper":null,"title":"Masked Conditioning for Deep Generative Models","date":"2025-05-22","arxiv_id":"2505.16725","n_code_links":0,"syntology":null},{"paper":"/paper/sculpting-features-from-noise-reward-guided","title":"Sculpting Features from Noise: Reward-Guided Hierarchical Diffusion for Task-Optimal Feature Transformation","date":"2025-05-21","arxiv_id":"2505.15152","n_code_links":1,"syntology":null},{"paper":null,"title":"ORL-LDM: Offline Reinforcement Learning Guided Latent Diffusion Model Super-Resolution Reconstruction","date":"2025-05-15","arxiv_id":"2505.10027","n_code_links":0,"syntology":null},{"paper":null,"title":"Score-based diffusion nowcasting of GOES imagery","date":"2025-05-15","arxiv_id":"2505.10432","n_code_links":0,"syntology":null},{"paper":"/paper/mission-balance-generating-under-represented","title":"Mission Balance: Generating Under-represented Class Samples using Video Diffusion Models","date":"2025-05-14","arxiv_id":"2505.09858","n_code_links":1,"syntology":null},{"paper":null,"title":"HistDiST: Histopathological Diffusion-based Stain Transfer","date":"2025-05-11","arxiv_id":"2505.06793","n_code_links":0,"syntology":null},{"paper":null,"title":"Computationally Efficient Diffusion Models in Medical Imaging: A Comprehensive Review","date":"2025-05-09","arxiv_id":"2505.07866","n_code_links":0,"syntology":null},{"paper":null,"title":"GlyphMastero: A Glyph Encoder for High-Fidelity Scene Text Editing","date":"2025-05-08","arxiv_id":"2505.04915","n_code_links":0,"syntology":null},{"paper":null,"title":"From Spaceborne to Airborne: SAR Image Synthesis Using Foundation Models for Multi-Scale Adaptation","date":"2025-05-05","arxiv_id":"2505.03844","n_code_links":0,"syntology":null},{"paper":null,"title":"Model See Model Do: Speech-Driven Facial Animation with Style Control","date":"2025-05-02","arxiv_id":"2505.01319","n_code_links":0,"syntology":null},{"paper":null,"title":"GuideSR: Rethinking Guidance for One-Step High-Fidelity Diffusion-Based Super-Resolution","date":"2025-05-01","arxiv_id":"2505.00687","n_code_links":0,"syntology":null},{"paper":null,"title":"Safety-Critical Traffic Simulation with Guided Latent Diffusion Model","date":"2025-05-01","arxiv_id":"2505.00515","n_code_links":0,"syntology":null},{"paper":"/paper/magicportrait-temporally-consistent-face","title":"MagicPortrait: Temporally Consistent Face Reenactment with 3D Geometric Guidance","date":"2025-04-30","arxiv_id":"2504.21497","n_code_links":1,"syntology":null},{"paper":null,"title":"Appa: Bending Weather Dynamics with Latent Diffusion Models for Global Data Assimilation","date":"2025-04-25","arxiv_id":"2504.18720","n_code_links":0,"syntology":null},{"paper":null,"title":"polyGen: A Learning Framework for Atomic-level Polymer Structure Generation","date":"2025-04-24","arxiv_id":"2504.17656","n_code_links":0,"syntology":null},{"paper":null,"title":"Causal Disentanglement for Robust Long-tail Medical Image Generation","date":"2025-04-20","arxiv_id":"2504.14450","n_code_links":0,"syntology":null},{"paper":"/paper/enhancing-person-to-person-virtual-try-on","title":"Enhancing Person-to-Person Virtual Try-On with Multi-Garment Virtual Try-Off","date":"2025-04-17","arxiv_id":"2504.13078","n_code_links":1,"syntology":null},{"paper":"/paper/deep-generative-model-based-generation-of","title":"Deep Generative Model-Based Generation of Synthetic Individual-Specific Brain MRI Segmentations","date":"2025-04-15","arxiv_id":"2504.12352","n_code_links":1,"syntology":null},{"paper":null,"title":"WaterFlow: Learning Fast & Robust Watermarks using Stable Diffusion","date":"2025-04-15","arxiv_id":"2504.12354","n_code_links":0,"syntology":null},{"paper":null,"title":"Controllable Expressive 3D Facial Animation via Diffusion in a Unified Multimodal Space","date":"2025-04-14","arxiv_id":"2506.10007","n_code_links":0,"syntology":null},{"paper":"/paper/id-booth-identity-consistent-face-generation","title":"ID-Booth: Identity-consistent Face Generation with Diffusion Models","date":"2025-04-10","arxiv_id":"2504.07392","n_code_links":1,"syntology":null}],"papers_shown":30,"tasks":[{"task":"/task/image-generation","name":"Image Generation","papers":89},{"task":"/task/denoising","name":"Denoising","papers":51},{"task":"/task/decoder","name":"Decoder","papers":21},{"task":"/task/diversity","name":"Diversity","papers":17},{"task":"/task/data-augmentation","name":"Data Augmentation","papers":14},{"task":"/task/video-generation","name":"Video Generation","papers":14},{"task":"/task/model","name":"model","papers":14},{"task":"/task/image-reconstruction","name":"Image Reconstruction","papers":13},{"task":"/task/text-to-image-generation","name":"Text-to-Image Generation","papers":13},{"task":"/task/computational-efficiency","name":"Computational Efficiency","papers":12},{"task":"/task/super-resolution","name":"Super-Resolution","papers":12},{"task":"/task/3d-generation","name":"3D Generation","papers":11},{"task":"/task/translation","name":"Translation","papers":11},{"task":"/task/virtual-try-on","name":"Virtual Try-on","papers":11},{"task":"/task/segmentation","name":"Segmentation","papers":10},{"task":"/task/semantic-segmentation","name":"Semantic Segmentation","papers":10},{"task":"/task/contrastive-learning","name":"Contrastive Learning","papers":9},{"task":"/task/image-to-image-translation","name":"Image-to-Image Translation","papers":9},{"task":"/task/text-to-image-generation-1","name":"Text to Image Generation","papers":9},{"task":"/task/attribute","name":"Attribute","papers":8}],"tasks_shown":20,"n_tasks":290,"usage_by_year":[{"year":"2021","papers":1},{"year":"2022","papers":13},{"year":"2023","papers":109},{"year":"2024","papers":171},{"year":"2025","papers":72}],"row_source":"methods_table","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/latent-diffusion-model"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}