BoosterCore

[Bug]: recall saved style can not apply the dynamic prompts

2

### Is there an existing issue for this? - [X] I have searched the existing issues and checked the recent builds/commits ### What happened? I saved a style form prompt...

AI引擎有没有可能考虑支持一下ollama呢？

7

AI引擎有没有可能考虑支持一下ollama呢？非常期待，感谢感谢！

0.3.4版一按设置就出错

3


Request: 既然已经有了输出目录的管理，是否也能加一个输入目录的管理呢？

1

使用久了，难免需要手动点开输入目录，清理一些图。看到您这个插件已有的优秀功能，不禁想要一个针对输入目录的。 如能实现，万分感谢！

Save Text File: How about considering adding a function for custom document format in this node?

2

I have a rather special requirement; I'd like to output the text generated by Ollama in ComfyUI into note-taking software Obsidian, specifically formatted as .md files. I think that if...

Chinese Prompt节点似乎有问题

7

偶然尝试了一下这个节点，发现总是报错，检查了模型都下载齐全了，不太清楚是什么情况。与之对应的英文版节点Prompt Generate运行正常。 ` !!! Exception during processing!!! 'NoneType' object is not callable Traceback (most recent call last): File "K:\ComfyUI_windows_portable\ComfyUI\execution.py", line 151, in recursive_execute output_data, output_ui = get_output_data(obj, input_data_all) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File...

flash_attn安装并未出错，但运行时显示其没有被安装。

3

在官方的Portable版本中，整个插件安装失败。 然后在秋叶整合版中尝试，插件是装上了，但遇到如题所示问题。 ``` got prompt No module named 'flash_attn' flash_attn not installed, disabling Flash Attention !!! Exception during processing!!! No module named 'vector_quantize_pytorch' Traceback (most recent call last): File "J:\ComfyUI-aki-v1.3\execution.py",...

想问一下，秋叶版整合包该怎么安装`flash-attention`，谢谢。

How to fix "too many indices for tensor of dimension 4"?

11

I tried cogvideox_I2V_example_01.json, and the image is 720X480, but... CogVideoImageEncode Node got this error :"too many indices for tensor of dimension 4"