Multimodality

Multimodality

Time

Duration 3:12

icon
You know ChatGPT for its text prompt: you give it text, it answers back text. Be just like human, it can cover much more: → audio → video → PDFs → excels This is called multimodality.

Here are the several models I mentioned

✔️ Midjourney

✔️ Sora

✔️ Dall-E

→ You have access to my entire Midjourney resource here

You also have access to my GPT agents helping your prompting here:

Click here 👆
Click here 👆
icon
Multimodal is the future. LLMs like ChatGPT will be closer & closer to humans, sharing the same senses as us.