AI工具客户端

Setup

Your ComfyUI server needs to be started using the --listen parm, so the API can be accessed.

After running it, a config.txt will be made. There is a config edit button inside the app, it's kind of self-documented, just go through it and update as necessary.

If your ComfyUI server is password protected, for example with the ComfyUI-Login custom node, append its direct API bearer token to the add_server line:

add_server|http://secured-box.lan:8188|token=$2b$12$qUfJfV942n...

This is optional; leave |token=... off for normal open ComfyUI servers. For ComfyUI-Login, use the token it prints for direct API calls, not your web UI password. AITools sends it as an Authorization: Bearer header for ComfyUI HTTP and WebSocket requests.

Building from source

You only need to download the zip and run the .exe to use this, However, the source might be useful to generate a build for other platforms, fork or steal pieces to use for yourself. Go ahead!

• Requires Unity 6000.3.1f+
• Open the scene "Main" and click play to run
• Assets/GUI/GOTHIC.TFF and Assets/GUI/times.ttf are not included and might break the build because I was having trouble and switched some settings around that might require them now (dynamic vs static TMPro font settings...)

---

Credits and links

• Audio: "Chee Zee Jungle"

Kevin MacLeod (incompetech.com)

Licensed under Creative Commons: By Attribution 3.0

http://creativecommons.org/licenses/by/3.0/

• NotoSansCJKjp-VF font licensed under the Open Font License (OFL)
• Audio: JOHN_MICHEL_CELLO-BACH_AVE_MARIA.mp3 performed by John Michel. Licensed under Creative Commons: By Attribution 3.0

http://creativecommons.org/licenses/by/3.0/

• Written by Seth A. Robinson (seth@rtsoft.com) twitter: @rtsoft - Codedojo, Seth's blog
• Special thanks to the ComfyUI and llama.cpp projects

Screenshots

<a href="Media/ai_tools_dungeons_generate.png"><img src="Media/ai_tools_dungeons_generate.png" width="300"></a> <a href="Media/ait_dungeon_twine_export.png"><img src="Media/ait_dungeon_twine_export.png" width="300"></a> <a href="Media/ait_twine_stored_html2.png"><img src="Media/ait_twine_stored_html2.png" width="300"></a> <a href="Media/ait_quiz_kyoto.png"><img src="Media/ait_quiz_kyoto.png" width="300"></a> <a href="Media/ai_tools_birdy_to_bird.jpg"><img src="Media/ai_tools_birdy_to_bird.jpg" width="300"></a>

Setting up with ComfyUI

First, install ComfyUI and get it rendering stuff.

Then install my Workflow to API Converter Endpoint via ComfyUI Manager

This node allows us to only work with normal workflow json files, and never have to export "API" versions. The API conversions will happen under the hood automatically when needed, makes life much better. Click its page above for help.

It will work if you don't, but this allows modified or new workflows to work as it can convert them to "API" versions on the fly when needed.

Next, just for a test to make sure the workflows included with AITools are going to work, inside ComfyUI's web GUI, drag in aitools_client/ComfyUI/FullWorkflowVersions/text_to_img_flux.json or any others. The neat thing about ComfyUI is it will read this and convert it to its visual workflow format, ready to run. (you might want to change the prompt from <AITOOLS_PROMPT> to something else during testing here) - Click Queue. Does it work? Oh, if you see an Image Loader set to the file "<AITOOLS_INPUT_1>" you'll need to change that to a file on your ComfyUI server if you want to test.

You'll probably see a bunch of red nodes and errors - no problem! Make sure you have ComfyUI-Manager installed, you can use it to install any missing nodes. You'll probably have to track down various model files though, but at least when you try to render it will shows exactly the filenames that are missing. (look for red boxes around certain nodes)

Adjust it until it works (change paths or models or whatever you need, you could even start with a totally different workflow you found somewhere else), and make sure the prompt is set to <AITOOLS_PROMPT>. (<AITOOLS_NEGATIVE_PROMPT> can be used if your workflow has a place for that too) Then do Workflow->Export if you wanted to save your own. (note: we no longer use "API" versions at all, thank god, just normal workflows and dynamically convert them as needed)

So you don't have to create custom workflows for every checkpoint/filesize etc, you can use AITools' "@replace" to change any part of a workflow before it's sent to ComfyUI's API, but after it's been converted to an "API" version of the workflow. You'll see it used in various presets.

Check discussions for some more info here

List of keywords that can be used in ComfyUI workflows so AITools can modify things