Zhipu AI has just presented AI enthusiasts with a great gift – they've open-sourced their latest image generation model, CogView4!
This isn't just an ordinary model; it's the industry's first open-source text-to-image model that supports both Chinese and English prompts. It excels at understanding Chinese prompts and can even generate Chinese characters in images. Simply put, you can tell it what you want in Chinese or English, and it will generate an image that matches the description. Whether you're looking to create advertising designs, short video content, or just have fun with creative ideas, this model can come in handy.
What is CogView4?
CogView4 is an AI image generation model developed by Zhipu AI, belonging to the "text-to-image" technology category, which generates images based on text descriptions. It has 6 billion parameters (equivalent to the model's "brain capacity"), making it very powerful in performance. What makes it special is that it not only supports Chinese and English input but also accurately understands complex Chinese prompts, and can even generate clear Chinese characters within images. For example, if you enter "a swordsman in ancient costume standing in a bamboo forest, with the words '侠义' (chivalry) written next to him," CogView4 can generate such a scene. This ability is a first in open-source models and is very suitable for Chinese users.
In addition, CogView4 can generate images of arbitrary resolution (within a certain range) and supports ultra-long prompt descriptions. This means you can write a detailed creative idea, and it will try to recreate your idea as much as possible. Whether it's a simple "a cat" or a complex "a cityscape at night with skyscrapers," it can handle it.
How to Use CogView4?
The good news is that CogView4 has been open-sourced, meaning anyone can download and use it for free! Its code and model files can be found on GitHub: https://github.com/THUDM/CogView4
If you are a novice user, don't worry about complex technical details. Zhipu also plans to launch the latest version CogView4-6B-0304 on their "Zhipu Qingyan" platform on March 13th. At that time, you only need to open the webpage or App, enter the image description you want to generate, and click to see the results. It's as simple as taking a photo with your phone.
Official Website Online Usehttps://open.bigmodel.cn/trialcenter/modeltrial?modelCode=glm-4-voice
What are Some Similar Domestic Services?
The domestic AI text-to-image field is developing rapidly. In addition to CogView4, there are some similar tools. For example:
- Wenxin Yige (Baidu): A text-to-image service launched by Baidu, supports Chinese input, can generate artistic-style images, and is suitable for design and creative work.
- Tongyi Wanxiang (Alibaba): Alibaba's image generation tool, also supports Chinese prompts, has good results, and is more inclined towards commercial applications.
- Doubao (ByteDance): ByteDance's AI tool, supports text-to-image and multimodal creation, has a simple interface, and is suitable for beginners.
Most of these services have web versions or Apps, which are easy to operate, but some functions may require payment. The advantage of CogView4 is that it is open-source and free, with greater flexibility, and is especially suitable for those who want to do it themselves.