Open Source Project

Tencent AI Lab and other joint research and development of open source song generation model, 10 seconds of audio + lyrics into 2 minutes 30 seconds of high-quality music, comparable to commercial standards.

Tencent's open source Chinese text-to-image prompt word enhancement framework that optimizes user-input prompts and improves the image quality and semantic accuracy of the generated model.

Tencent launched the open source raw image model, which natively supports 2K HD raw images, accurately parses complex semantics, and can efficiently generate high-quality images with Chinese and English fusion.

Tencent introduced the industry's first open source world model that supports native 3D reconstruction and ultra-long roaming, allowing for rapid generation of interactive and immersive 3D scenes based on a single image or text.

Waver 1.0 is an open source full-featured video generation model that makes it easy to create text/images to HD video with efficiency, convenience and outstanding quality.

ByteDance's open-source 36 billion parameter-long contextual big language model supports 512K tokens, a controlled mind budget, excels in inference, code and agent tasks, and is freely commercially available under the Apache-2.0 license.

An open source lightweight text-to-speech model that is less than 25 MB and can run in real time on ordinary CPUs, supports a variety of natural tones and can be used offline.

Ali Tongyi Thousand Questions open source 20 billion parameter image generation model , specializing in Chinese and English high fidelity text rendering and complex scene detail processing , support for multi-style image generation .

Ali open source code big model, support full-flow programming and complex task planning, performance over GPT-4.1, lower cost.

A multimodal model that supports text generation and image editing with powerful contextual understanding and authoring capabilities.

Google introduced a lightweight open source large language model , both high performance and easy to deploy , suitable for local development and multi-scenario applications .

Tencent hybrid open source voice digital human model, upload pictures and audio that generate multi-style, highly dynamic personalized dynamic video.

Xiaomi's open-sourced 7 billion parameter inference macromodel, which outperforms models such as OpenAI o1-mini in mathematical reasoning and code competitions by a small margin.

The unlimited duration movie generation model introduced by KunlunWanwei team breaks through the bottleneck of the existing video generation technology and realizes high-quality, high-consistency and high-fidelity video creation.

AI video subtitle translation and dubbing tool, supporting multi-language input and translation, providing one-stop solution from video acquisition to subtitle translation and dubbing.

Open source AI translation tool, supporting bilingual control, multi-engine translation, format preservation and batch processing, helping researchers read foreign literature efficiently.

The real-time portrait video generation tool developed by Alibaba's Dharma Institute realizes highly realistic, style-controlled and real-time efficient portrait video generation through a hierarchical motion diffusion model, which is suitable for video chatting, virtual anchoring and digital entertainment scenarios.

Open source AI-assisted drawing tool that intelligently converts hand-drawn sketches and text descriptions into 3D models, supporting real-time collaboration and creative expression.

Tencent's self-developed deep thinking models with fast response, ultra-long text processing and strong reasoning capabilities have been widely used in intelligent Q&A, document processing and other fields.

Combining visual language modeling and reinforcement learning, the autopilot technology framework is equipped with powerful planning inference and multimodal planning capabilities to deal with complex and rare traffic scenarios.

The Tsinghua University team and Qingcheng Jizhi jointly launched an open source large model inference engine, aiming to realize efficient model inference across chip architectures through underlying technological innovations and promote the widespread application of AI technology.

AI 3D scene generation tool that can efficiently generate complete 3D environments containing multiple objects from a single image, widely used in VR/AR, game development, film and television production and other fields.

Lucent Technologies has launched a new open source video generation model with high performance and low cost, leading the open source video generation technology into a new stage.

Alibaba's open-source multimodal large language model uses RLVR technology to achieve emotion recognition and provide an interpretable reasoning process for multiple scenarios.

An open source AI Agent framework that supports localized deployment and multi-intelligence collaboration to efficiently complete complex tasks.

Alibaba released a high-performance inference model with 32 billion parameters that excels in mathematics and programming for a wide range of application scenarios.

Google open-sourced a model that uses artificial intelligence technology to analyze camera trap photos to automatically identify animal species.

Alibaba launched an efficient video generation model that can accurately simulate complex scenes and actions, support Chinese and English special effects, and lead a new era of AI video creation.

The open-source text-to-graphics model released by Wisdom Spectrum AI supports bilingual input, generates high-quality images and is the first to generate Chinese characters in the screen, which is widely used in advertising, short videos, art creation and other fields.

Open source real-time facial expression editing tool that allows users to adjust facial expressions and head orientation in static images in real time with simple operations.