Update 1.8: GPT-4o, image analysis support
Update items
Here are the details of the update on May 17, 2024. The following items will be added this time:
- AI Chat
- Supports GPT-4o
- Supports image analysis
Supports GPT-4o
overview
The model available for AI chat has been changed from GPT-4turbo to GPT-4o.
This change is expected to provide the following benefits:
- Response speed has improved (more than doubled).
- It allows for more logical and human conversations.
How to use
- From [Account Settings], select [Model to use] > [GPT-4o] and press [Change].
- After that, you can talk as usual via AI chat or AI agent.
Supports image analysis
overview
Image analysis on the chat screen is now supported. This allows AI to analyze the characteristics of uploaded images.
Specific uses will be introduced as "use cases" later in this article.
How to use
- To perform image analysis, you must set it to GPT4. From [Account Settings], select [Model to Use] > [GPT-4o].
- On the chat screen, select the image from the paperclip icon.
- After selecting the image, the analysis is performed along with the text that instructs it. Note that multiple images can be analyzed at the same time.
Notes
- Image analysis supports the following file extensions: PNG, JPG, JPEG, WebP.
- Image file size is limited to 20MB.
Use Cases
We will propose some use cases that may be useful for image analysis.
① Analyze images and create product descriptions
The AI writes the introduction by analyzing the characteristics of the image and specifying the length of the text etc. in the instructions.
② Analyze the image and create a prompt for image generation
From image analysis, you can also use text descriptions of images to generate similar images. Below, we instruct the AI to analyze by category, such as [structure], [shape], etc.
3) Analyze handwritten notes and diagrams
You can also photograph and analyze handwritten notes and diagrams, and use AI to transcribe them and analyze the diagrams.
