mlsanityData to 7 Oct 2026

Kandinsky 3.0 Technical Report

arXiv 2312.03511 ↗First posted 6 Dec 2023cs.CV cs.LG cs.MMcited by 18

On the map: Diffusion models → Image generation, text-to-image and editing

Abstract (arXiv)

We present Kandinsky 3.0, a large-scale text-to-image generation model based on latent diffusion, continuing the series of text-to-image Kandinsky models and reflecting our progress to achieve higher quality and realism of image generation. In this report we describe the architecture of the model, the data collection procedure, the training technique, and the production system for user interaction. We focus on the key components that, as we have identified as a result of a large number of experiments, had the most significant impact on improving the quality of our model compared to the others. We also describe extensions and applications of our model, including super resolution, inpainting, image editing, image-to-video generation, and a distilled version of Kandinsky 3.0 - Kandinsky 3.1, which does inference in 4 steps of the reverse process and 20 times faster without visual quality decrease. By side-by-side human preferences comparison, Kandinsky becomes better in text understanding and works better on specific domains. The code is available at https://github.com/ai-forever/Kandinsky-3

Key facts. Cited by 18 papers in the map (data through 7 Oct 2026). Placed in Image generation, text-to-image and editing, one of 14 directions in Diffusion models. Builds on 35 of its 50 references that are in the map. First posted on arXiv 6 Dec 2023.

Builds on

35 of 50 references.

Closest ancestors · 7

Same direction, newest first

  1. 2023IP-Adapter: Text Compatible Image Prompt Adapter for Text-to-Image Diffusion Models13 Aug
  2. 2023MultiDiffusion: Fusing Diffusion Paths for Controlled Image Generation16 Feb
  3. 2023Adding Conditional Control to Text-to-Image Diffusion Models10 Feb
  4. 2022eDiff-I: Text-to-Image Diffusion Models with an Ensemble of Expert Denoisers2 Nov
  5. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding23 May
  6. 2022Hierarchical Text-Conditional Image Generation with CLIP Latents13 Apr
  7. 2021GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models20 Dec

Other references · 28

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  4. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  5. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  6. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  7. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  8. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,005
  9. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 6,979
  10. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
  11. 2023SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesiscited by 4,290
  12. 2021Zero-Shot Text-to-Image Generationcited by 4,276
16 more
  1. 2022LAION-5B: An open large-scale dataset for training next generation image-text modelscited by 4,131
  2. 2020Taming Transformers for High-Resolution Image Synthesiscited by 3,229
  3. 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,609
  4. 2018Group Normalizationcited by 1,514
  5. 2019Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfercited by 1,484
  6. 2021Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Datacited by 961
  7. 2017Sigmoid-Weighted Linear Units for Neural Network Function Approximation in Reinforcement Learningcited by 935
  8. 2022Autoregressive Image Generation using Residual Quantizationcited by 706
  9. 2020AdaBins: Depth Estimation using Adaptive Binscited by 596
  10. 2015Holistically-Nested Edge Detectioncited by 590
  11. 2022MaxViT: Multi-Axis Vision Transformercited by 476
  12. 2023Symbolic Discovery of Optimization Algorithmscited by 423
  13. 2019Toward Real-World Single Image Super-Resolution: A New Benchmark and A New Modelcited by 400
  14. 2022UL2: Unifying Language Learning Paradigmscited by 292
  15. 2022MoVQ: Modulating Quantized Vectors for High-Fidelity Image Generationcited by 125
  16. 2023FusionFrames: Efficient Architectural Aspects for Text-to-Video Generation Pipelinecited by 7

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 6; 2025: 8; 2026: 4.

18 papers.

Sort:

By area:

  1. 2024SIDA: Social Media Image Deepfake Detection, Localization and Explanation with Large Multimodal Modelcited by 107
  2. 2025T2ISafety: Benchmark for Assessing Fairness, Toxicity, and Privacy in Image Generationcited by 47
  3. 2024FIRE: Robust Detection of Diffusion-Generated Images via Frequency-Guided Reconstruction Errorcited by 46
  4. 2024EvalMuse-40K: A Reliable and Fine-Grained Benchmark with Comprehensive Human Annotations for Text-to-Image Generation Model Evaluationcited by 37
  5. 2024UMBRAE: Unified Multimodal Brain Decodingcited by 31
  6. 2024YaART: Yet Another ART Rendering Technologycited by 5
  7. 2025DRAGON: A Large-Scale Dataset of Realistic Images Generated by Diffusion Modelscited by 4
  8. 2025So-Fake: Benchmarking and Explaining Social Media Image Forgery Detectioncited by 4
  9. 2024MuLan: Adapting Multilingual Diffusion Models for Hundreds of Languages with Negligible Costcited by 3
  10. 2025Instruction-augmented Multimodal Alignment for Image-Text and Element Matchingcited by 2
  11. 2026A Difference-in-Difference Approach to Detecting AI-Generated Imagescited by 2
  12. 2025Origin Identification for Text-Guided Image-to-Image Diffusion Modelscited by 1
6 more
  1. 2025SynthDrive: Scalable Real2Sim2Real Sensor Simulation Pipeline for High-Fidelity Asset Generation and Driving Data Synthesiscited by 1
  2. 2025Adversarial Concept Distillation for One-Step Diffusion Personalizationcited by 1
  3. 2025ControlVP: Interactive Geometric Refinement of AI-Generated Images with Consistent Vanishing Pointscited by 1
  4. 2026Exploiting the Final Component of Generator Architectures for AI-Generated Image Detectioncited by 1
  5. 2026DynEval: Holistic Evaluations of T2I Generative Models in the Wildcited by 0
  6. 2026REALIS: A Curated Dataset for Studying the Challenges of AI Image Detectioncited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Kandinsky 3: Text-to-Image Synthesis for Multifunctional Generative Framework
  2. 2023Kandinsky: an Improved Text-to-Image Synthesis with Image Prior and Latent Diffusion
  3. 2022Implementing and Experimenting with Diffusion Models for Text-to-Image Generation
  4. 2023Text-to-image Diffusion Models in Generative AI: A Survey
  5. 2022Plug-and-Play Diffusion Features for Text-Driven Image-to-Image Translation
  6. 2026i1: A Simple and Fully Open Recipe for Strong Text-to-Image Models
  7. 2023RenAIssance: A Survey into AI Text-to-Image Generation in the Era of Large Model
  8. 2023Rich Human Feedback for Text-to-Image Generation