ChatGPTNextWeb / ChatGPT-Next-Web

A cross-platform ChatGPT/Gemini UI (Web / PWA / Linux / Win / MacOS). 一键拥有你自己的跨平台 ChatGPT/Gemini 应用。
https://app.nextchat.dev/
MIT License
72.62k stars 57.71k forks source link

[Feature] 准备引入 DALL-E 3 #2904

Open devyujie opened 9 months ago

devyujie commented 9 months ago

为了提高交流效率,我们设立了官方 QQ 群和 QQ 频道,如果你在使用或者搭建过程中遇到了任何问题,请先第一时间加群或者频道咨询解决,除非是可以稳定复现的 Bug 或者较为有创意的功能建议,否则请不要随意往 Issue 区发送低质无意义帖子。

点击加入官方群聊

这个功能与现有的问题有关吗?

你想要什么功能或者有什么建议? 能否先引入 DALL-E 2 以提供专门的文生图能力,类似马上要发布官网 DALL-E 3 显示页面(虽然不知道什么时候开放 API)。

用一个专门的页面显示,而不是面具的形式,并且用户可以设置一次生成几张图片。

image

有没有可以参考的同类竞品?

其他信息

Issues-translate-bot commented 9 months ago

Bot detected the issue body's language is not English, translate it automatically.


Title: [Feature] Prepare to introduce DALL-E 3

In order to improve communication efficiency, we have set up an official QQ group and QQ channel. If you encounter any problems during use or construction, please join the group or channel for consultation as soon as possible, unless it is a bug that can be stably reproduced or More creative feature suggestions, otherwise please do not send low-quality and meaningless posts to the Issue area.

Click to join the official group chat

Is this feature related to an existing issue? ,

What features do you want or have any suggestions? Can DALL-E 2 be introduced first to provide specialized Vincentian graphics capabilities, similar to the DALL-E 3 display page on the official website that will be released soon (although I don’t know when the API will be opened)

image

Are there any similar competing products that we can refer to? ,

other information ,

H0llyW00dzZ commented 9 months ago

I had previously added this, but the problem is that I can't quickly bypass the CORS (Cross-Origin Resource Sharing) issue for the image URLs generated from OpenAI. Essentially, any image generated as a prompt using the DALL-E models cannot be exported as an image or in text/JSON format.

EDITED Here's what was previously added:

Drawing Indonesia flag

The problem is that when you try to export the messages as an image, text, or JSON, the images generated by OpenAI using the DALL-E models won't be displayed.

H0llyW00dzZ commented 8 months ago

[still beta] https://github.com/H0llyW00dzZ/ChatGPT-Next-Web/pull/52/commits/6948667589ccd53f43c2167ef5f8ed51604aa60c

H0llyW00dzZ commented 8 months ago

which is better than DALL-E 3 lmao Exploring the Milky Way galaxy (1)

Captivating Image_ Andromeda Galaxy Captivating Picture_ Milky Way

Exploring Andromeda Galaxy

Exploring the Milky Way Galaxy

muaxb commented 2 months ago

Have you resolved the issue with exporting the generated images?