arXiv:2511.14993v3 Announce Type: replace-cross 
Abstract: 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.

يمثل تقديم كاندينسكي 5.0 تقدمًا كبيرًا في مجال الذكاء الاصطناعي، حيث يقدم مجموعة من النماذج الأساسية المصممة لتوليد الصور والفيديوهات عالية الدقة. يتضمن هذا الإطار ثلاثة نماذج رئيسية: كاندينسكي 5.0 Image Lite، كاندينسكي 5.0 Video Lite، وكاندينسكي 5.0 Video Pro، كل منها مُحسّن لتطبيقات مختلفة في توليد الصور والفيديو.

La introducción de Kandinsky 5.0 marca un avance significativo en el campo de la inteligencia artificial, presentando una familia de modelos fundamentales diseñados para la generación de imágenes y videos de alta resolución. Este marco incluye tres modelos distintos: Kandinsky 5.0 Image Lite, Kandinsky 5.0 Video Lite y Kandinsky 5.0 Video Pro, cada uno optimizado para diferentes aplicaciones en la síntesis de imágenes y videos.

L'introduction de Kandinsky 5.0 représente une avancée significative dans le domaine de l'intelligence artificielle, présentant une famille de modèles fondamentaux conçus pour la génération d'images et de vidéos haute résolution. Ce cadre comprend trois modèles distincts : Kandinsky 5.0 Image Lite, Kandinsky 5.0 Video Lite et Kandinsky 5.0 Video Pro, chacun optimisé pour différentes applications dans la synthèse d'images et de vidéos.

The introduction of Kandinsky 5.0 marks a significant advancement in the field of artificial intelligence, presenting a family of foundation models designed for high-resolution image and video generation. This framework includes three distinct models: Kandinsky 5.0 Image Lite, Kandinsky 5.0 Video Lite, and Kandinsky 5.0 Video Pro, each optimized for different applications in image and video synthesis.