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

Does ComfyUI-Prompt-MZ have to install some Python dependency related? See the screenshot #16

Open
KennyChan3389 opened this issue Jun 2, 2024 · 15 comments

Comments

@KennyChan3389
Copy link

dbf84c483289f94df89b646df93b6551
@wailovet
Copy link
Contributor

wailovet commented Jun 2, 2024

You may need to manually go to https://github.com/abetlen/llama-cpp-python/releases to install the appropriate version

@KennyChan3389
Copy link
Author

You may need to manually go to https://github.com/abetlen/llama-cpp-python/releases to install the appropriate version

image
pip list:
lightning-utilities 0.10.1
llama_cpp_python 0.2.76

I can't find where I'm going wrong, I can run it but no results are returned, please help!

@wailovet
Copy link
Contributor

wailovet commented Jun 3, 2024

Try using CLIPTextEncode (ImageInterrogator) instead
image

@KennyChan3389
Copy link
Author

Try using CLIPTextEncode (ImageInterrogator) instead image

您推荐的节点是可以用但是其他的节点又出问题,寻求帮助。

109521251ac53d911d8f8e1ecbb2b068

@wailovet
Copy link
Contributor

wailovet commented Jun 6, 2024

Try using CLIPTextEncode (ImageInterrogator) instead image

您推荐的节点是可以用但是其他的节点又出问题,寻求帮助。

109521251ac53d911d8f8e1ecbb2b068

刷新后重试

@KennyChan3389
Copy link
Author

真不行啊,而且我发现反推文本编码器,前天还是自然语言输出,进早忽然变成tag输出了。不知道为啥。

@wailovet
Copy link
Contributor

wailovet commented Jun 6, 2024

真不行啊,而且我发现反推文本编码器,前天还是自然语言输出,进早忽然变成tag输出了。不知道为啥。

你试一下这个
image

@wailovet
Copy link
Contributor

wailovet commented Jun 6, 2024

真不行啊,而且我发现反推文本编码器,前天还是自然语言输出,进早忽然变成tag输出了。不知道为啥。

有个后处理字段,关掉试试
image

@KennyChan3389
Copy link
Author

7b59288f170711821a5b4f6010dd5334
您别介意,感觉今天用起来,推理很慢很慢,而且很多都变了。上面拿一张是刚刚推理的。
下面这张是昨天的
fa095d9662c38ab00a5a4556140bf785

@KennyChan3389
Copy link
Author

7b59288f170711821a5b4f6010dd5334 您别介意,感觉今天用起来,推理很慢很慢,而且很多都变了。上面拿一张是刚刚推理的。

### 下面这张是昨天的 !

fa095d9662c38ab00a5a4556140bf785

@wailovet
Copy link
Contributor

wailovet commented Jun 6, 2024

7b59288f170711821a5b4f6010dd5334 您别介意,感觉今天用起来,推理很慢很慢,而且很多都变了。上面拿一张是刚刚推理的。 下面这张是昨天的 fa095d9662c38ab00a5a4556140bf785

相同图片相同种子会吗

@KennyChan3389
Copy link
Author

image
左边是随机出tag或者自然语言(不同种子),右边那个就肯定是TAG输出的

@wailovet
Copy link
Contributor

wailovet commented Jun 6, 2024

image 左边是随机出tag或者自然语言(不同种子),右边那个就肯定是TAG输出的

左边没啥问题吧,右边的话你把连着的线断掉再跑一下

@wailovet
Copy link
Contributor

wailovet commented Jun 6, 2024

image 左边是随机出tag或者自然语言(不同种子),右边那个就肯定是TAG输出的

左边没啥问题吧,右边的话你把连着的线断掉再跑一下

把连接的模型和自定义指令都断了,让他用默认的跑一下

@KennyChan3389
Copy link
Author

image
就是这样了,
您有没有比较好用的自定义指令,我想哪来配合打标配置,用ipa弄个脸模。改尝试一下练LORA了

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

No branches or pull requests

2 participants