Gemini GeminiAI Text-to-Image Usage Tutorial

Gemini is the first AI model ever launched by Google with native multimodal capabilities, and it has been used in Google Pixel 8 Pro smartphones and the chatbot Bard.

Currently, text-to-image is not yet supported, but it won't be long; the technology has already been mastered, and it is only a matter of release timing.



As of February 20, 2024, we tested it again, and it could actually do it—but for text-to-image you need to use English.



Just when I thought it was working, I then asked it what its image generation function was, and it told me it doesn't have one~



When I asked it again why it uses other platforms' APIs to draw, it told me its capabilities are not yet complete. I think I now know why it must use English for image generation: because it connects to other platforms' APIs, and some platforms do not support Chinese. It seems we'll have to wait a bit longer; it's worth looking forward to.