Based on the Disco Diffusion, we have developed a Chinese & English version of the AI art creation software "AI Atelier". We offer both Text-To-Image models (Disco Diffusion and VQGAN+CLIP) and Text-To-Text (GPT-J-6B and GPT-NEOX-20B) as options.

在Disco Diffusion模型的基础上，我们开发了一款汉化版AI艺术创作软件“AI聊天画室”。我们同时提供了文本生成图像模型（Disco Diffusion与VQGAN+CLIP）及文本生成文本（GPT-J-6B及GPT-NEOX-20B）可供选择。

🌈✨ Welcome the participation of more developers to help making AI Art more accessible ✨🌈

🌈✨ 欢迎更多开发者参与并助力ai艺术的普及与发展 ✨🌈

Making available complete source code of licensed works and modifications, which include larger works using a licensed work, under the same license. Copyright and license notices must be preserved. When a modified version is used to provide a service over a network, the complete source code of the modified version must be made available.

如果您将本程序二次开发或者提供给他人使用（即使是仅作为在线工具提供服务），您必须延用AGPL许可证且在网上开源共享你修改的版本。相应的版权和许可声明必须保留。

More info ｜ 相关信息 [1] [2]

V0.0.4
· Add Chinese translation 新增汉化翻译
· Add chatbot(text-to-text) generation 新增聊天机器人（文本生成文本）
· Optimise files saving structure 优化文件保存结构
· Update GUI and colour scheme to improve readability 优化界面及色彩主题以提升可读性
· Host api for authorization 新增用于授权的API接口

V0.0.3
· Save your own settings to google drive 可保存你的参数设置至谷歌云盘
· Save generated process video to google drive 可将生成过程的视频保存至谷歌云盘
· More prompt enhancers 新增风格类形容词
· Improve GUI of colab notebook 优化界面排版
· Default image size set to 16:9 默认图像尺寸设置为16:9
· Fix 'seed' value error 修复 "种子"值不同步的错误

☑️ Buildin GPT-J-6B chatbot 搭建GPT-J-6B聊天机器人
· Create 2D and 3D animations and not only still frames (from Disco Diffusion v5 and VQGAN Animations) 创建2D和3D动画，而非静态图像（来自Disco Diffusion v5和VQGAN Animations）
· Restore your own settings 导入并恢复你的图像设置
· Input audio and images for generation instead of just text 输入音频和图片进行生成，而不仅仅是文字。
· Simplify tool setup process on colab, and enable ‘one-click’ sharing of the generated link to other users. Experiment with the possibilities for multi-user access to the same link. 简化colab端工具加载流程，优化链接分享流程。实验允许多个用户接入同个链接使用的可能性。

This would not be possible without the brilliant work of MindsEye beta develop by @multimodalart and gpt-j-api by Víctor Gallego.
Disco Diffusion v5 model by @somnai_dreams and @gandamu, based on the foundational work of @RiversHaveWings, with modifications by @danielrussruss, Dango233, Chigozie Nri, @softologyComAu and others.
Hypertron v2 VQGAN model by Philipuss adapted from @RiversHaveWings with modifications by @jbusted1, @softologyComAu and others. Original GAN+CLIP by @advadnoun. CLIP and Guided Diffusion were originally released by OpenAI. VQGAN was released by CompVis Heidelberg.
API access to large language models by TextSynth. Translation powered by Google.

感谢@multimodalart的MindsEye beta 与 Víctor Gallego的gpt-j-api的开创性作品，本软件才能得以实现。
Disco Diffusion v5模型由@somnai_dreams与@gandamu所开发。基于@RiversHaveWings开创性的基础工作，以及@danielrussruss，Dango233，Chigozie Nri，@softologyComAu等其他人对其进一步的优化。参数的中文翻译基于Vultur。
Hypertron v2VQGAN 模型由Philipuss改编自@RiversHaveWings， 并由@jbusted1和@softologyComAu等其他人进一步修改。 原始GAN+CLIP由@advadnoun所提供。CLIP和Guided Diffusion最初由OpenAI发布。VQGAN则是由CompVis Heidelberg发布的。
对大型语言模型的API访问由TextSynth提供。翻译技术来自谷歌