mlsanityData to 14 Oct 2026

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

arXiv 2410.21061 ↗First posted 28 Oct 2024cs.CV cs.AI cs.MMcited by 25

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

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.

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.

Builds on

31 of 47 references.

Closest ancestors · 7

Same direction, newest first

  1. 2023Kandinsky: an Improved Text-to-Image Synthesis with Image Prior and Latent Diffusion5 Oct
  2. 2023TF-ICON: Diffusion-Based Training-Free Cross-Domain Image Composition24 Jul
  3. 2023DragonDiffusion: Enabling Drag-style Manipulation on Diffusion Models5 Jul
  4. 2022Inversion-Based Style Transfer with Diffusion Models23 Nov
  5. 2022MagicMix: Semantic Mixing with Diffusion Models28 Oct
  6. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding23 May
  7. 2021GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models20 Dec

Other references · 24

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  4. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  5. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  6. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
  7. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 7,005
  8. 2023SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesiscited by 4,356
  9. 2021Zero-Shot Text-to-Image Generationcited by 4,288
  10. 2022LAION-5B: An open large-scale dataset for training next generation image-text modelscited by 4,152
  11. 2022DreamFusion: Text-to-3D using 2D Diffusioncited by 3,025
  12. 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,626
12 more
  1. 2022Make-A-Video: Text-to-Video Generation without Text-Video Datacited by 1,742
  2. 2023Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Modelscited by 1,476
  3. 2022Magic3D: High-Resolution Text-to-3D Content Creationcited by 1,290
  4. 2017Sigmoid-Weighted Linear Units for Neural Network Function Approximation in Reinforcement Learningcited by 950
  5. 2022On Distillation of Guided Diffusion Modelscited by 725
  6. 2020AdaBins: Depth Estimation using Adaptive Binscited by 601
  7. 2015Holistically-Nested Edge Detectioncited by 592
  8. 2021Towards Real-World Blind Face Restoration with Generative Facial Priorcited by 349
  9. 2023Photorealistic Video Generation with Diffusion Modelscited by 306
  10. 2022SmartBrush: Text and Shape Guided Object Inpainting with Diffusion Modelcited by 278
  11. 2023DreamBooth3D: Subject-Driven Text-to-3D Generationcited by 235
  12. 2023DreamPose: Fashion Image-to-Video Synthesis via Stable Diffusioncited by 167

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 2; 2025: 17; 2026: 6.

25 papers.

Sort:

By area:

  1. 2024SnapGen: Taming High-Resolution Text-to-Image Models for Mobile Devices with Efficient Architectures and Trainingcited by 27
  2. 2025LMM4LMM: Benchmarking and Evaluating Large-multimodal Image Generation with LMMscited by 24
  3. 2024Be More Diverse than the Most Diverse: Optimal Mixtures of Generative Models via Mixture-UCB Bandit Algorithmscited by 14
  4. 2025GigaChat Family: Efficient Russian Language Modeling Through Mixture of Experts Architecturecited by 8
  5. 2025DFBench: Benchmarking Deepfake Image Detection Capability of Large Multimodal Modelscited by 7
  6. 2025DREAM: Scalable Red Teaming for Text-to-Image Generative Systems via Distribution Modelingcited by 5
  7. 2025SYNTHIA: Novel Concept Design with Affordance Compositioncited by 4
  8. 2025Towards Reliable Identification of Diffusion-based Image Manipulationscited by 4
  9. 2025Reusing Computation in Text-to-Image Diffusion for Efficient Generation of Image Setscited by 4
  10. 2025VIVAT: Virtuous Improving VAE Training through Artifact Mitigationcited by 3
  11. 2025Time-Correlated Video Bridge Matchingcited by 2
  12. 2025T2IBias: Uncovering Societal Bias Encoded in the Latent Space of Text-to-Image Generative Modelscited by 2
13 more
  1. 2026Efficient Adversarial Attacks on High-dimensional Offline Banditscited by 2
  2. 2026DAK-UCB: Diversity-Aware Prompt Routing for LLMs and Generative Modelscited by 2
  3. 2025RusCode: Russian Cultural Code Benchmark for Text-to-Image Generationcited by 1
  4. 2025NABLA: Neighborhood Adaptive Block-Level Attentioncited by 1
  5. 2025Un-Doubling Diffusion: LLM-guided Disambiguation of Homonym Duplicationcited by 1
  6. 2025ControlVP: Interactive Geometric Refinement of AI-Generated Images with Consistent Vanishing Pointscited by 1
  7. 2026ImageAttributionBench: How Far Are We from Generalizable Attribution?cited by 1
  8. 2025CRAFT: Cultural Russian-Oriented Dataset Adaptation for Focused Text-to-Image Generationcited by 0
  9. 2025Redefining Generalization in Visual Domains: A Two-Axis Framework for Fake Image Detection with FusionDetectcited by 0
  10. 2025CREward: A Type-Specific Creativity Reward Modelcited by 0
  11. 2026SoS: Analysis of Surface over Semantics in Multilingual Text-To-Image Generationcited by 0
  12. 2026Evidence Packing for Cross-Domain Image Deepfake Detection with LVLMscited by 0
  13. 2026Unified Backbone Refinement for Diffusion Models via Internal-Latent Analysiscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2023Kandinsky 3.0 Technical Report
  2. 2023Text-to-image Diffusion Models in Generative AI: A Survey
  3. 2024MaxFusion: Plug&Play Multi-Modal Generation in Text-to-Image Diffusion Models
  4. 2022Plug-and-Play Diffusion Features for Text-Driven Image-to-Image Translation
  5. 2024Image Regeneration: Evaluating Text-to-Image Model via Generating Identical Image with Multimodal Large Language Models
  6. 2022Implementing and Experimenting with Diffusion Models for Text-to-Image Generation
  7. 2023KOALA: Empirical Lessons Toward Memory-Efficient and Fast Diffusion Models for Text-to-Image Synthesis
  8. 2023Text-driven Visual Synthesis with Latent Diffusion Prior