[Feature Request]: Using Images

acheong08 / EdgeGPT

Reverse engineered API of Microsoft's Bing Chat AI

The Unlicense

8.07k stars 909 forks source link

[Feature Request]: Using Images #573

Open Eikosa opened 1 year ago

Eikosa commented 1 year ago

Is there an existing issue for this?

[X] I have searched the existing issues and checked the recent builds/commits

What would your feature do ?

As it is known, image interpretation feature was recently added to bing chat. It would be great to be able to use this in edgegpt

Proposed workflow

Additional information

No response

Nu11Const commented 1 year ago

How to image interpretation

renqabs commented 1 year ago

How to image interpretation

Log in with a new account, clean cookies, clean up established links in the proxy, switch to a node in Japan or the United States, refresh the new bing page, this function can appear with a high probability

TanukiAI commented 1 year ago

Microsoft added this feature and it works fine. Hope this will be adapted in the near future! Seems really simple. Also 18+ images are blocked and will return {"blobId":null,"processedBlobId":null}

renqabs commented 1 year ago

I've implemented this feature based on someone's modified version of EdgeGPT, but it may have a bad impact on other features of the current version of EdgeGPT

TanukiAI commented 1 year ago

Any updates?

wh-yu commented 1 year ago

I've implemented this feature based on someone's modified version of EdgeGPT, but it may have a bad impact on other features of the current version of EdgeGPT

Hi @renqabs , could you please share the code? Thank you so much.