---
title: "Kuaishou models: release history and timeline"
description: "Chinese short-video platform company that develops the Kling video generation models, Kolors image models, Keye-VL multimodal models, and Kwaipilot coding models."
type: "release-archive"
canonical_url: "https://theaiengineering.com/releases/kuaishou"
markdown_url: "https://theaiengineering.com/releases/kuaishou.md"
author: "The AI Engineering Editors"
publisher: "The AI Engineering"
updated: "2026-10-15"
citation: "The AI Engineering Editors. \"Kuaishou models: release history and timeline.\" The AI Engineering, updated Oct 15, 2026. https://theaiengineering.com/releases/kuaishou"
license: "CC BY 4.0"
license_url: "https://creativecommons.org/licenses/by/4.0/"
data_csv: "https://theaiengineering.com/releases.csv"
data_json: "https://theaiengineering.com/releases.json"
---

# Kuaishou models: release history and timeline

Chinese short-video platform company that develops the Kling video generation models, Kolors image models, Keye-VL multimodal models, and Kwaipilot coding models.

- Headquarters: Beijing, China
- Founded: 2011
- Website: https://www.kuaishou.com

16 releases from 1 lab, 6 with open weights. Dates are the labs' official announcement dates.

## October 2026

### Kling 4.0

Kling 4.0 is Kuaishou's next-generation video generation model, focused on steadier large-scale motion and complex camera work, native single-pass generation of up to 30 seconds, and expanded reference-based control.

- Date: 2026-10-15
- Lab: Kuaishou
- Type: Video
- Weights: Proprietary
- Modalities: text, image, video, audio → video, audio
- Available at launch: Consumer app
- Permalink: https://theaiengineering.com/releases/2026/10#kling-4-0

Highlights:

- Native single-pass video generation of up to 30 seconds
- Omni Reference supports up to 15 reference assets and up to 10 keyframes
- Supports up to 10-bit HDR output
- Kuaishou said API access for enterprises and developers would follow

Source: [Kling AI Officially Launches Next-Generation Kling 4.0, Raising the Bar for Professional-Grade Video Models](https://ir.kuaishou.com/news-releases/news-release-details/kling-ai-officially-launches-next-generation-kling-40-raising)

## June 2026

### Kling 3.0 Turbo

Kling 3.0 Turbo is a new model in Kuaishou's Kling 3.0 video series, launched as part of a series upgrade that also improved video editing in Kling 3.0 Omni.

- Date: 2026-06-17
- Lab: Kuaishou
- Type: Video
- Weights: Proprietary
- Modalities: text, image → video
- Available at launch: Consumer app
- Permalink: https://theaiengineering.com/releases/2026/06#kling-3-0-turbo

Highlights:

- Listed as a Kling 3.0 model series upgrade in Kling's release notes
- Launched alongside upgraded video editing in Kling 3.0 Omni

Source: [Kling AI Release Notes & Version History | Kling AI](https://kling.ai/release-note/release-history)

## May 2026

### Keye-VL-2.0-30B-A3B

Keye-VL-2.0-30B-A3B is the 30B-class flagship of Kuaishou's Keye multimodal series, using a DSA sparse-attention architecture to support long-video understanding over a 256K context.

- Date: 2026-05-25
- Lab: Kuaishou
- Type: Multimodal
- Weights: Open weights
- Modalities: text, image, video → text
- Context window: 256,000 tokens
- Parameters: MoE: 30B total, 3B active
- License: Apache-2.0
- Available at launch: Open weights
- Permalink: https://theaiengineering.com/releases/2026/05#keye-vl-2-0

Highlights:

- Sparse attention architecture for hour-long video understanding
- Nearly lossless reasoning over 256K context, per the model card
- Weights released under Apache-2.0

Source: [GitHub - Kwai-Keye/Keye](https://github.com/Kwai-Keye/Keye)

## January 2026

### Kling 3.0

Kling 3.0 is Kuaishou's model series comprising Video 3.0, Video 3.0 Omni, Image 3.0, and Image 3.0 Omni, unifying generation and editing with native audio, longer clips, and stronger character consistency.

- Date: 2026-01-31
- Lab: Kuaishou
- Type: Video
- Weights: Proprietary
- Modalities: text, image, video, audio → video, image, audio
- Available at launch: Consumer app
- Permalink: https://theaiengineering.com/releases/2026/01#kling-3-0

Highlights:

- Video generation up to 15 seconds with native multilingual audio
- Video 3.0 Omni adds reference-video based character and voice consistency
- Image 3.0 supports direct 2K and 4K output
- Kuaishou's press release announcing the series followed on February 5, 2026

Source: [Kling AI Release Notes & Version History | Kling AI](https://kling.ai/release-note/release-history)

## December 2025

### Kling Video 2.6

Kling Video 2.6 is Kling's first model with simultaneous audio-visual generation, producing visuals together with voiceovers, sound effects, and ambient sound in a single pass from text or image prompts.

- Date: 2025-12-03
- Lab: Kuaishou
- Type: Video
- Weights: Proprietary
- Modalities: text, image → video, audio
- Available at launch: Consumer app
- Permalink: https://theaiengineering.com/releases/2025/12#kling-video-2-6

Highlights:

- Generates speech, sound effects, and ambient audio with the video
- Supports Chinese and English voice generation
- Generates clips up to 10 seconds long

Source: [Kling AI Launches Video 2.6 Model with "Simultaneous Audio-Visual Generation" Capability, Redefining AI Video Creation Workflow](https://ir.kuaishou.com/news-releases/news-release-details/kling-ai-launches-video-26-model-simultaneous-audio-visual)

### Kling O1

Kling O1 is a unified multimodal video model that combines reference-based generation, text-to-video, start and end frames, in-painting, restyling, and shot extension in one engine built on a Multimodal Visual Language framework.

- Date: 2025-12-01
- Lab: Kuaishou
- Type: Video
- Weights: Proprietary
- Modalities: text, image, video → video, image
- Available at launch: Consumer app
- Permalink: https://theaiengineering.com/releases/2025/12#kling-o1

Highlights:

- Accepts text, image, video, and subject references as prompts
- Supports conversational video editing without manual masking
- Kling Image O1 image model followed on December 2, 2025

Source: [Kling O1 Launches as the World's First Unified Multimodal Video Model](https://ir.kuaishou.com/news-releases/news-release-details/kling-o1-launches-worlds-first-unified-multimodal-video-model-0)

## November 2025

### Keye-VL-671B-A37B

Keye-VL-671B-A37B is the largest model in Kuaishou's Keye multimodal series, combining the Keye-VL-1.5 vision encoder with upgraded pre-training and post-training for text, image, and video understanding.

- Date: 2025-11-20
- Lab: Kuaishou
- Type: Multimodal
- Weights: Open weights
- Modalities: text, image, video → text
- Parameters: MoE: 671B total, 37B active
- License: Apache-2.0
- Available at launch: Open weights
- Permalink: https://theaiengineering.com/releases/2025/11#keye-vl-671b-a37b

Highlights:

- Reuses the Keye-VL-1.5 vision encoder
- Synthetic chain-of-thought data used during continual pre-training
- Weights released under Apache-2.0

Source: [GitHub - Kwai-Keye/Keye](https://github.com/Kwai-Keye/Keye)

## September 2025

### Kling 2.5 Turbo

Kling 2.5 Turbo is an upgraded Kling video model with improved text-to-video and image-to-video quality, including better prompt adherence, motion, style consistency, and aesthetics.

- Date: 2025-09-19
- Lab: Kuaishou
- Type: Video
- Weights: Proprietary
- Modalities: text, image → video
- Available at launch: Consumer app
- Permalink: https://theaiengineering.com/releases/2025/09#kling-2-5-turbo

Highlights:

- Improved handling of multi-step instructions and causal relationships in prompts
- Larger-amplitude motion and camera movement with more realistic physics
- Kuaishou's press release dates the launch to September 23, 2025

Source: [Kling AI Release Notes & Version History | Kling AI](https://kling.ai/release-note/release-history)

## August 2025

### Keye-VL-1.5-8B

Keye-VL-1.5 is an upgraded 8B multimodal model from Kuaishou's Keye team that improves short-video comprehension with a Slow-Fast video encoding strategy and new long chain-of-thought and reinforcement learning stages.

- Date: 2025-08-28
- Lab: Kuaishou
- Type: Multimodal
- Weights: Open weights
- Modalities: text, image, video → text
- Parameters: 8B
- License: Apache-2.0
- Available at launch: Open weights
- Permalink: https://theaiengineering.com/releases/2025/08#keye-vl-1-5

Highlights:

- Slow-Fast video encoding strategy for video understanding
- Progressive four-stage pre-training
- Weights released under Apache-2.0

Source: [GitHub - Kwai-Keye/Keye](https://github.com/Kwai-Keye/Keye)

## June 2025

### Keye-VL-8B-Preview

Keye-VL is Kuaishou's first open multimodal large language model, built to understand short-form video as well as images, with a switchable thinking mode for reasoning.

- Date: 2025-06-26
- Lab: Kuaishou
- Type: Multimodal
- Weights: Open weights
- Modalities: text, image, video → text
- Parameters: 8B
- License: Apache-2.0
- Available at launch: Open weights
- Permalink: https://theaiengineering.com/releases/2025/06#keye-vl-8b-preview

Highlights:

- Focused on dynamic, information-dense short-form video
- Soft switch between thinking and non-thinking modes
- Technical report followed on July 1, 2025

Source: [GitHub - Kwai-Keye/Keye](https://github.com/Kwai-Keye/Keye)

## May 2025

### Kling 2.1

Kling 2.1 is a model series that adds Standard and High Quality video generation modes alongside a premium Kling 2.1 Master edition with stronger motion and prompt responsiveness.

- Date: 2025-05-26
- Lab: Kuaishou
- Type: Video
- Weights: Proprietary
- Modalities: text, image → video
- Available at launch: Consumer app
- Permalink: https://theaiengineering.com/releases/2025/05#kling-2-1

Highlights:

- Standard (720p) and High Quality (1080p) modes
- Kling 2.1 Master offers improved motion and semantic responsiveness
- Start and end frame control for Kling 2.1 arrived on August 21, 2025

Source: [Kling AI Release Notes & Version History | Kling AI](https://kling.ai/release-note/release-history)

## April 2025

### Kling 2.0

Kling 2.0 Master is the second-generation Kling video generation model, launched globally with improvements in motion quality, semantic responsiveness, and visual aesthetics, alongside the Kolors 2.0 image model.

- Date: 2025-04-15
- Lab: Kuaishou
- Type: Video
- Weights: Proprietary
- Modalities: text, image → video
- Available at launch: Consumer app
- Permalink: https://theaiengineering.com/releases/2025/04#kling-2-0

Highlights:

- Launched at Kling's From Vision to Screen event in Beijing
- Released together with Kolors 2.0 and new multimodal editing features
- Kuaishou reported more than 20 Kling iterations since June 2024

Source: [Kling AI Advances to the 2.0 Era, Empowering Everyone to Tell Great Stories with AI](https://ir.kuaishou.com/news-releases/news-release-details/kling-ai-advances-20-era-empowering-everyone-tell-great-stories)

### Kolors 2.0

Kolors 2.0 is Kuaishou's second-generation image generation model, launched on Kling AI with the Kling 2.0 video model and improved prompt adherence, cinematic quality, and artistic style expression.

- Date: 2025-04-15
- Lab: Kuaishou
- Type: Image
- Weights: Proprietary
- Modalities: text, image → image
- Available at launch: Consumer app
- Permalink: https://theaiengineering.com/releases/2025/04#kolors-2-0

Highlights:

- Launched on Kling AI alongside Kling 2.0 Master
- Improves prompt adherence, cinematic quality, and artistic styles

Source: [Kling AI Advances to the 2.0 Era, Empowering Everyone to Tell Great Stories with AI](https://ir.kuaishou.com/news-releases/news-release-details/kling-ai-advances-20-era-empowering-everyone-tell-great-stories)

## March 2025

### OASIS-code-embedding-1.5B

OASIS-code-embedding-1.5B is a code embedding model from Kuaishou's Kwaipilot team, designed to improve semantic code retrieval and search across programming contexts.

- Date: 2025-03-12
- Lab: Kuaishou
- Type: Embedding
- Weights: Open weights
- Modalities: text → text
- Parameters: 1.5B
- License: MIT
- Available at launch: Open weights
- Permalink: https://theaiengineering.com/releases/2025/03#kwaipilot-oasis-code-embedding-1-5b

Highlights:

- Built for code retrieval and code search systems
- Released with a preprint on the same day
- Weights on Hugging Face under MIT

Source: [Kwaipilot/OASIS-code-embedding-1.5B · Hugging Face](https://huggingface.co/Kwaipilot/OASIS-code-embedding-1.5B)

## July 2024

### Kolors

Kolors is Kuaishou's large text-to-image model trained on billions of text-image pairs, bilingual in Chinese and English, open-sourced at the 2024 World Artificial Intelligence Conference.

- Date: 2024-07-06
- Lab: Kuaishou
- Type: Image
- Weights: Open weights
- Modalities: text → image
- License: Kolors Model License Agreement
- Available at launch: Open weights
- Permalink: https://theaiengineering.com/releases/2024/07#kolors

Highlights:

- Bilingual Chinese and English prompts with a 256-token text context
- ControlNet, inpainting, and IP-Adapter variants released in July 2024
- Weights free for academic research; commercial use requires registration

Source: [GitHub - Kwai-Kolors/Kolors](https://github.com/Kwai-Kolors/Kolors)

## June 2024

### Kling

Kling is Kuaishou's first video generation model, a diffusion transformer with a self-developed 3D VAE that generates videos of up to two minutes at 30fps and up to 1080p from text prompts.

- Date: 2024-06-06
- Lab: Kuaishou
- Type: Video
- Weights: Proprietary
- Modalities: text → video
- Available at launch: Consumer app
- Permalink: https://theaiengineering.com/releases/2024/06#kling-1-0

Highlights:

- Kuaishou's July 25, 2024 release dates the opening of trial applications to June 6, 2024
- Diffusion transformer with a self-developed 3D VAE for spatiotemporal compression
- Initial beta testing ran inside the KuaiYing app; web access and a global beta followed in July 2024

Source: [Kuaishou Unveils Proprietary Video Generation Model 'Kling;' Testing Now Available](https://ir.kuaishou.com/news-releases/news-release-details/kuaishou-unveils-proprietary-video-generation-model-kling)

## Cite and reuse this data

These release records are free to reuse under CC BY 4.0, including commercially. Credit The AI Engineering and link to this page's URL. Dates are the labs' official announcement dates, and every record links to its source. List fields in the CSV are separated by " | ".

The AI Engineering Editors. "Kuaishou models: release history and timeline." The AI Engineering, updated Oct 15, 2026. https://theaiengineering.com/releases/kuaishou

HTML link:

```html
<a href="https://theaiengineering.com/releases/kuaishou">Kuaishou models: release history and timeline</a> (The AI Engineering)
```

- Title: Kuaishou models: release history and timeline
- Author: The AI Engineering Editors
- Publisher: The AI Engineering
- Updated: 2026-10-15
- URL: https://theaiengineering.com/releases/kuaishou
- Markdown: https://theaiengineering.com/releases/kuaishou.md
- License: CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/)
- Full dataset as CSV: https://theaiengineering.com/releases.csv
- Full dataset as JSON: https://theaiengineering.com/releases.json
