Alibaba Qwen 2.5 announced: How to access it, get started, and generate videos and images

Alibaba Qwen 2.5

Alibaba has announced its latest AI language model – Qwen 2.5. The new language model comes bearing tons of features, advanced processing, natural language understanding, text generation, vision and audio processing, AI tool use, and chatbot role-play.

To make it easier for users to try the new Qwen 2.5 features, the company has integrated this into its own Qwen Chat. If you are unaware, Qwen Chat is an AI chatbot like DeepSeek, ChatGPT, Google Gemini and Microsoft Copilot.

In addition to this, the Qwen Chat supports all the versions of Qwen 2.5 including the Plus, Max, Qwen2.5-VL-72B-Instruct, Qwen2.5-14B-Instruct-1M and QVQ-72B-Preview.

If you are wondering how to access the new Chinese AI chatbot, here’s our step-by-step guide:

Internet access and a system with a web browser as there’s no native app available for now

An active email account (or Google account) for login

Multilingual Support – Supports over 29 languages, including English, Chinese, French, Spanish, Portuguese, German, Italian, Russian, Japanese, Korean, Vietnamese, Thai, and Arabic.

Large-Scale Training – pre-trained on a dataset of up to 18 trillion tokens for improved language understanding and generation.

Long-Context Processing – Can handle up to 128K tokens in context, enabling better long-form content generation and complex reasoning.

Structured Data Understanding – Enhanced capability to process tables, JSON formats, and structured outputs for better data interpretation.

Advanced Instruction Following – Improved alignment with human instructions, making responses more precise and contextually relevant.

Multimodal Capabilities – Can understand and generate text, process visual and audio inputs, and interact with various tools.

AI Agent Functions – Supports role-playing, chatbot condition-setting, and interactive agent-like behaviours for diverse applications.

System Prompt Resilience – More robust handling of diverse prompts, improving adaptability to different chatbot scenarios.

Optimized Energy Efficiency – Improved model efficiency ensures faster response times and lower computational costs for deployments.

Open a web browser and head to “https://chat.qwenlm.ai/”

Then, enter your email address or use Google login option to login into the Qwen Chat

At the top, you’ll find a drop-down menu with Qwen 2.5 Plus. Click on it to select your desired AI language.

That’s it, you can now enter the prompt to get the response.

Enter the command for the image that you want it to generate. Then, click on the ‘Image Generation’ option from the chatbox. Hit enter for it to start generating the image.

The process is more or less, all you need to do is enter the prompt and then select the ‘Video Generation’ option.