Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Feature: 使用bot发送消息来切换模型 #140

Open
Tracked by #143
yi03 opened this issue Dec 2, 2022 · 8 comments
Open
Tracked by #143

Feature: 使用bot发送消息来切换模型 #140

yi03 opened this issue Dec 2, 2022 · 8 comments
Assignees
Labels
enhancement New feature or request

Comments

@yi03
Copy link

yi03 commented Dec 2, 2022

Scope

Stable Diffusion WebUI (AUTOMATIC1111)

Describe the problem related to the feature request

本地有很多不同的模型,只能bot管理者手动切换,有些时候很不方便。

Describe the solution you'd like

在群里向bot发送切换模型的指令后,bot切换模型。

Describe alternatives you've considered

No response

Additional context

No response

@MaikoTan MaikoTan self-assigned this Dec 3, 2022
@MaikoTan MaikoTan added the enhancement New feature or request label Dec 3, 2022
@MaikoTan
Copy link
Member

Since many sd-webui provider are individuals that they don't have higher spec computer. Switching models frequently causes downtime of the webui extremely long.
So I think if there were a command doing the such thing, it would be better to require an authority of level 2 or 3.
As always you could change that with commands plugin. Anyone thoughts?

自从很多 sd-webui 提供者是个人,没有高配置电脑。频繁地切换模型会造成 webui 极其长的停机时间。
所以我想如果有一个指令做了这件事情,要求一个 2 或 3 的权威会更好。和往常一样你可以通过指令插件改变。有人想法?

@yi03
Copy link
Author

yi03 commented Feb 1, 2023

Since many sd-webui provider are individuals that they don't have higher spec computer. Switching models frequently causes downtime of the webui extremely long. So I think if there were a command doing the such thing, it would be better to require an authority of level 2 or 3. As always you could change that with commands plugin. Anyone thoughts?

自从很多 sd-webui 提供者是个人,没有高配置电脑。频繁地切换模型会造成 webui 极其长的停机时间。 所以我想如果有一个指令做了这件事情,要求一个 2 或 3 的权威会更好。和往常一样你可以通过指令插件改变。有人想法?

其实现在sd-switch插件已经基本满足了我的需求了。我切换2GB大小的DreamBooth模型大概需要五六秒,由于现在我的群玩ai的群友已经很少了,多个群友同时玩的次数不多,所以我没设置什么权限限制。当然我这种情况应该比较少,还是应该有一个权限限制。通过commads插件来改变我觉得挺好的。
另外除了DreamBooth模型之外还有Textual Inversion, Hypernetwork, Lora这些小模型,这几个小模型在最新版的sd-webui里都可以在prompt里来选择,比如在prompt里输入<lora:amberGenshinImpact_flexibleV1:1>就表示选择了一个名叫amberGenshinImpact_flexibleV1Lora模型,权重是1。所以需要一个列出当前所有可用Textual Inversion, Hypernetwork, Lora模型的功能。这三种模型里我个人的话Lora模型用的最多,有时会用Textual Inversion模型,几乎不用Hypernetwork模型。

@MaikoTan
Copy link
Member

MaikoTan commented Feb 1, 2023

其实现在sd-switch插件已经基本满足了我的需求了。

In fact, our implementations would be different with sd-switch. I would add documents for it soon after we succesfully distrbute this feature.

通过commads插件来改变我觉得挺好的。

OK, I would walk this way.

另外除了DreamBooth模型之外还有Textual Inversion, Hypernetwork, Lora这些小模型,这几个小模型在最新版的sd-webui里都可以在prompt里来选择,比如在prompt里输入<lora:amberGenshinImpact_flexibleV1:1>就表示选择了一个名叫amberGenshinImpact_flexibleV1Lora模型,权重是1。

Currently the < and > wouldn't be convert into &lt and &gt? I thought it would be the issue that should be fixed before!

所以需要一个列出当前所有可用Textual Inversion, Hypernetwork, Lora模型的功能。

That is another feature request I think.

@yi03
Copy link
Author

yi03 commented Feb 1, 2023

Yes. Currently the < and > would be convert into &lt and &gt. #161

That is another feature request I think.

OK. I will open an another issue.

@MaikoTan
Copy link
Member

MaikoTan commented Feb 1, 2023

Yes. Currently the < and > would be convert into &lt and &gt. #161

Oh, okay.
Too many works in these days that I even forgot this issue that I commented.

@s567901
Copy link

s567901 commented Jun 7, 2023

附议,希望能通过向bot发送切换模型😀

@Ninzore
Copy link
Collaborator

Ninzore commented Sep 1, 2023

在做了

@MirrorCY
Copy link
Member

MirrorCY commented Feb 4, 2024

感觉现在这个项目已经很重了,这个需求我建议放到 sd-switch 实现,你觉得如何 @MaikoTan

顺便,有任何与这个功能相关的需求可以到这里提出 https://github.com/MirrorCY/sd-switch/issues

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
enhancement New feature or request
Projects
None yet
Development

No branches or pull requests

5 participants