Alibaba Composer: Revolutionizing AI Content Creation

On April 12th, at the 2023 Web3 Carnival in Hong Kong, Zhao Deli, Director of the Basic Visual Team at Alibaba Dharma Institute, delivered a keynote speech titled “Alibaba Composer, Unleashing the Creativity of AIGC” during the “New Trends in Web3 Technology: Artificial Intelligence Generated Content (AIGC) and Privacy Computing Technology” event. She stated that the future trends of the AI industry, including the development of AI algorithms in vertical industries, will continue to be deeply cultivated, The emergence of open source platforms (such as the ModelScope model launched by the Dharma Academy), and the unification of underlying algorithms. Our roadmap has gone through three stages in Text to Image: Foundation Models (Composer 1.0), Customized Generation, and Controllable Generation (Composer 2.0). This year, we have released ControlNet, Composer 2.0, and T2I Adapter. We have built a “Tongyi Wanxiang” product based on Alibaba Cloud, which will be open to everyone at the end of this month.

Director of the Basic Visual Team at Alibaba Dharma Academy: The text generated image product “Tongyi Wanxiang” will gradually be launched by the end of this month

At the 2023 Web3 Carnival in Hong Kong, Zhao Deli, Director of the Basic Visual Team at Alibaba Dharma Institute, gave a keynote speech titled “Alibaba Composer, Unleashing the Creativity of AIGC” during the “New Trends in Web3 Technology: Artificial Intelligence Generated Content (AIGC) and Privacy Computing Technology” event. Deli spoke about the future trends of the AI industry, mentioning the deep cultivation of AI algorithms in vertical industries, the emergence of open source platforms like Dharma Academy’s ModelScope model, and the unification of underlying algorithms.

The Three Stages of Text to Image

Deli discussed Alibaba’s roadmap through Text to Image, its development process towards perfecting AI-generated images. The process included three stages: Foundation Models (Composer 1.0), Customized Generation, and Controllable Generation (Composer 2.0).

Composer 1.0: Foundation Models

In the first stage of development, Alibaba focused on building Foundation Models (Composer 1.0) with the ability to generate diverse visual elements like landscapes, characters, and objects.

Customized Generation

In the second stage, Alibaba developed Customized Generation models, which allowed for personalization in generated images. This included the user’s ability to adjust lighting, texture, and color.

Composer 2.0: Controllable Generation

The final stage in their roadmap was the release of Composer 2.0: Controllable Generation. This modeled a new world of AI-generated images, providing full control of image creation for users. The introduction of ControlNet, Composer 2.0, and T2I Adapter signaled Alibaba’s commitment to the industry and their belief that AI-generated visual content will revolutionize the future of content creation.

The Unveiling of Tongyi Wanxiang

Deli announced the completion and unveiling of “Tongyi Wanxiang” product, developed using Alibaba Cloud technology. This product was to be open to the public by the end of the month, providing AI-generated images accessible to everyone with access to the Alibaba Cloud.

Advancements in AI Image Generation

Many view AI-generated images as a natural evolution of the industry. With the improvement in AI technology and deep learning methods, the possibility of generating high-quality images is now easier and more efficient than ever before.

Conclusion

In conclusion, the future innovation of AI-generated visual content is rapidly growing, with advancements being a core development strategy in modern machine learning. Alibaba’s Composer Roadmap is a strong indicator of the industry’s potential and the desire for everyone to have access to high-quality AI-generated images.

FAQs:

Q: What is Tongyi Wanxiang?

A: Tongyi Wanxiang is a product developed using Alibaba Cloud technology that provides accessibility to AI-generated images.

Q: How many stages are there in Alibaba’s roadmap for Text to Image?

A: There are three stages: Foundation Models (Composer 1.0), Customized Generation, and Controllable Generation (Composer 2.0).

Q: What did Zhao Deli speak about at the 2023 Web3 Carnival?

A: Zhao Deli, Director of the Basic Visual Team at Alibaba Dharma Institute, spoke about Alibaba Composer and the potential for AI-generated visual content at the “New Trends in Web3 Technology: Artificial Intelligence Generated Content (AIGC) and Privacy Computing Technology” event.