# Kandinsky 5.0: A Family of Foundation Models for Image and Video Generation

arXiv: https://arxiv.org/abs/2511.14993 · HTML: https://mlsanity.com/paper/2511.14993/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Nov 2025.

## Built on by (most cited first, 12 of 12)

- [Cosmos 3: Omnimodal World Models for Physical AI](https://mlsanity.com/paper/2606.02800/) (2026)
- [Helios: Real Real-Time Long Video Generation Model](https://mlsanity.com/paper/2603.04379/) (2026)
- [OP-GRPO: Efficient Off-Policy GRPO for Flow-Matching Models](https://mlsanity.com/paper/2604.04142/) (2026)
- [RAVEN: Real-time Autoregressive Video Extrapolation with Consistency-model GRPO](https://mlsanity.com/paper/2605.15190/) (2026)
- [HumanScore: Benchmarking Human Motions in Generated Videos](https://mlsanity.com/paper/2604.20157/) (2026)
- [HyperVAttention: Efficient Sparse Attention with Spatio-Temporal Clustering for Video Diffusion](https://mlsanity.com/paper/2607.03012/) (2026)
- [Adding Voice Cloning to Text-to-Audio-Video Models with a Single Zero-Initialised Layer](https://mlsanity.com/paper/2608.15690/) (2026)
- [AtlasVid: Efficient Ultra-High-Resolution Long Video Generation via Decoupled Global-Local Modeling](https://mlsanity.com/paper/2605.16649/) (2026)
- [DiTailed: Ensuring Visual Object Consistency in Text-Image-to-Image Flow Matching Models](https://mlsanity.com/paper/2607.12539/) (2026)
- [REALIS: A Curated Dataset for Studying the Challenges of AI Image Detection](https://mlsanity.com/paper/2609.32734/) (2026)
- [Video Generation Models: A Survey of Post-Training and Alignment](https://mlsanity.com/paper/2610.00812/) (2026)
- [Kandinsky 6.0 Video: Foundation Models for Synchronized Video and Audio Generation](https://mlsanity.com/paper/2610.05608/) (2026)

## Abstract (arXiv)

This report introduces Kandinsky 5.0, a family of state-of-the-art foundation models for high-resolution image and 10-second video synthesis. The framework comprises three core line-up of models: Kandinsky 5.0 Image Lite - a line-up of 6B parameter image generation models, Kandinsky 5.0 Video Lite - a fast and lightweight 2B parameter text-to-video and image-to-video models, and Kandinsky 5.0 Video Pro - 19B parameter models that achieves superior video generation quality. We provide a comprehensive review of the data curation lifecycle - including collection, processing, filtering and clustering - for the multi-stage training pipeline that involves extensive pre-training and incorporates quality-enhancement techniques such as self-supervised fine-tuning (SFT) and reinforcement learning (RL)-based post-training. We also present novel architectural, training, and inference optimizations that enable Kandinsky 5.0 to achieve high generation speeds and state-of-the-art performance across various tasks, as demonstrated by human evaluation. As a large-scale, publicly available generative framework, Kandinsky 5.0 leverages the full potential of its pre-training and subsequent stages to be adapted for a wide range of generative applications. We hope that this report, together with the release of our open-source code and training checkpoints, will substantially advance the development and accessibility of high-quality generative models for the research community.