# Kandinsky 3: Text-to-Image Synthesis for Multifunctional Generative Framework

arXiv: https://arxiv.org/abs/2410.21061 · HTML: https://mlsanity.com/paper/2410.21061/

## Key facts

- Cited by 25 papers in the map (data through 14 Oct 2026).
- Placed in Image generation, text-to-image and editing, one of 14 directions in Diffusion models.
- Builds on 31 of its 47 references that are in the map.
- First posted on arXiv 28 Oct 2024.

## Placed in

- Diffusion models / [Image generation, text-to-image and editing](https://mlsanity.com/diffusion/image-generation-text-to-image-and-editing/)

## Builds on (most cited first, 30 of 31)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding](https://mlsanity.com/paper/2205.11487/) (2022)
- [SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis](https://mlsanity.com/paper/2307.01952/) (2023)
- [Zero-Shot Text-to-Image Generation](https://mlsanity.com/paper/2102.12092/) (2021)
- [LAION-5B: An open large-scale dataset for training next generation image-text models](https://mlsanity.com/paper/2210.08402/) (2022)
- [GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models](https://mlsanity.com/paper/2112.10741/) (2021)
- [DreamFusion: Text-to-3D using 2D Diffusion](https://mlsanity.com/paper/2209.14988/) (2022)
- [Large Scale GAN Training for High Fidelity Natural Image Synthesis](https://mlsanity.com/paper/1809.11096/) (2018)
- [Make-A-Video: Text-to-Video Generation without Text-Video Data](https://mlsanity.com/paper/2209.14792/) (2022)
- [Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2304.08818/) (2023)
- [Magic3D: High-Resolution Text-to-3D Content Creation](https://mlsanity.com/paper/2211.10440/) (2022)
- [Sigmoid-Weighted Linear Units for Neural Network Function Approximation in Reinforcement Learning](https://mlsanity.com/paper/1702.03118/) (2017)
- [On Distillation of Guided Diffusion Models](https://mlsanity.com/paper/2210.03142/) (2022)
- [AdaBins: Depth Estimation using Adaptive Bins](https://mlsanity.com/paper/2011.14141/) (2020)
- [Holistically-Nested Edge Detection](https://mlsanity.com/paper/1504.06375/) (2015)
- [Towards Real-World Blind Face Restoration with Generative Facial Prior](https://mlsanity.com/paper/2101.04061/) (2021)
- [Photorealistic Video Generation with Diffusion Models](https://mlsanity.com/paper/2312.06662/) (2023)
- [Inversion-Based Style Transfer with Diffusion Models](https://mlsanity.com/paper/2211.13203/) (2022)
- [SmartBrush: Text and Shape Guided Object Inpainting with Diffusion Model](https://mlsanity.com/paper/2212.05034/) (2022)
- [DreamBooth3D: Subject-Driven Text-to-3D Generation](https://mlsanity.com/paper/2303.13508/) (2023)
- [DragonDiffusion: Enabling Drag-style Manipulation on Diffusion Models](https://mlsanity.com/paper/2307.02421/) (2023)
- [TF-ICON: Diffusion-Based Training-Free Cross-Domain Image Composition](https://mlsanity.com/paper/2307.12493/) (2023)
- [DreamPose: Fashion Image-to-Video Synthesis via Stable Diffusion](https://mlsanity.com/paper/2304.06025/) (2023)
- [Kandinsky: an Improved Text-to-Image Synthesis with Image Prior and Latent Diffusion](https://mlsanity.com/paper/2310.03502/) (2023)

## Built on by (most cited first, 25 of 25)

- [SnapGen: Taming High-Resolution Text-to-Image Models for Mobile Devices with Efficient Architectures and Training](https://mlsanity.com/paper/2412.09619/) (2024)
- [LMM4LMM: Benchmarking and Evaluating Large-multimodal Image Generation with LMMs](https://mlsanity.com/paper/2504.08358/) (2025)
- [Be More Diverse than the Most Diverse: Optimal Mixtures of Generative Models via Mixture-UCB Bandit Algorithms](https://mlsanity.com/paper/2412.17622/) (2024)
- [GigaChat Family: Efficient Russian Language Modeling Through Mixture of Experts Architecture](https://mlsanity.com/paper/2506.09440/) (2025)
- [DFBench: Benchmarking Deepfake Image Detection Capability of Large Multimodal Models](https://mlsanity.com/paper/2506.03007/) (2025)
- [DREAM: Scalable Red Teaming for Text-to-Image Generative Systems via Distribution Modeling](https://mlsanity.com/paper/2507.16329/) (2025)
- [SYNTHIA: Novel Concept Design with Affordance Composition](https://mlsanity.com/paper/2502.17793/) (2025)
- [Towards Reliable Identification of Diffusion-based Image Manipulations](https://mlsanity.com/paper/2506.05466/) (2025)
- [Reusing Computation in Text-to-Image Diffusion for Efficient Generation of Image Sets](https://mlsanity.com/paper/2508.21032/) (2025)
- [VIVAT: Virtuous Improving VAE Training through Artifact Mitigation](https://mlsanity.com/paper/2506.07863/) (2025)
- [Time-Correlated Video Bridge Matching](https://mlsanity.com/paper/2510.12453/) (2025)
- [T2IBias: Uncovering Societal Bias Encoded in the Latent Space of Text-to-Image Generative Models](https://mlsanity.com/paper/2511.10089/) (2025)
- [Efficient Adversarial Attacks on High-dimensional Offline Bandits](https://mlsanity.com/paper/2602.01658/) (2026)
- [DAK-UCB: Diversity-Aware Prompt Routing for LLMs and Generative Models](https://mlsanity.com/paper/2603.23140/) (2026)
- [RusCode: Russian Cultural Code Benchmark for Text-to-Image Generation](https://mlsanity.com/paper/2502.07455/) (2025)
- [NABLA: Neighborhood Adaptive Block-Level Attention](https://mlsanity.com/paper/2507.13546/) (2025)
- [Un-Doubling Diffusion: LLM-guided Disambiguation of Homonym Duplication](https://mlsanity.com/paper/2509.21262/) (2025)
- [ControlVP: Interactive Geometric Refinement of AI-Generated Images with Consistent Vanishing Points](https://mlsanity.com/paper/2512.07504/) (2025)
- [ImageAttributionBench: How Far Are We from Generalizable Attribution?](https://mlsanity.com/paper/2605.12967/) (2026)
- [CRAFT: Cultural Russian-Oriented Dataset Adaptation for Focused Text-to-Image Generation](https://mlsanity.com/paper/2505.04851/) (2025)
- [Redefining Generalization in Visual Domains: A Two-Axis Framework for Fake Image Detection with FusionDetect](https://mlsanity.com/paper/2510.05740/) (2025)
- [CREward: A Type-Specific Creativity Reward Model](https://mlsanity.com/paper/2511.19995/) (2025)
- [SoS: Analysis of Surface over Semantics in Multilingual Text-To-Image Generation](https://mlsanity.com/paper/2601.16803/) (2026)
- [Evidence Packing for Cross-Domain Image Deepfake Detection with LVLMs](https://mlsanity.com/paper/2603.17761/) (2026)
- [Unified Backbone Refinement for Diffusion Models via Internal-Latent Analysis](https://mlsanity.com/paper/2607.09753/) (2026)

## Abstract (arXiv)

Text-to-image (T2I) diffusion models are popular for introducing image manipulation methods, such as editing, image fusion, inpainting, etc. At the same time, image-to-video (I2V) and text-to-video (T2V) models are also built on top of T2I models. We present Kandinsky 3, a novel T2I model based on latent diffusion, achieving a high level of quality and photorealism. The key feature of the new architecture is the simplicity and efficiency of its adaptation for many types of generation tasks. We extend the base T2I model for various applications and create a multifunctional generation system that includes text-guided inpainting/outpainting, image fusion, text-image fusion, image variations generation, I2V and T2V generation. We also present a distilled version of the T2I model, evaluating inference in 4 steps of the reverse process without reducing image quality and 3 times faster than the base model. We deployed a user-friendly demo system in which all the features can be tested in the public domain. Additionally, we released the source code and checkpoints for the Kandinsky 3 and extended models. Human evaluations show that Kandinsky 3 demonstrates one of the highest quality scores among open source generation systems.