Text-to-Vision Nexus

I have created a pretty good website, so I would like to update my blog and introduce it to you after a long time.

https://www.ikachi.org/transformer/

This site can extract text from images and generate images from text.

This site has the following four functions

<<Image To Text>>

Extracts text from an image.

<<Text To Image>>

Generates an image with the content specified in the text.

<<Image To Image>>

Retrieves tags from an image and recreates the image from the tags.

<<Text To Text>>

Converts a text into another text with the same meaning.

The artificial intelligence services used are,

• Microsoft Azure Recognition Service
• ChatGPT 3.5 Turbo
• DALL-E2

ChatGPT 3.5 Turbo, and DALL-E2.

Microsoft Azure Recognition Service is used to extract text from images and to obtain tags from images.

ChatGPT 3.5 Turbo is used for Text To Text.

DALL-E2 is used to create images from text and tags.

This blog is in English because the site is in English.

I just used DeepL translation to make Japanese into English.