Extensions/ComfyUI-Minitools
ComfyUI Extension

ComfyUI-Minitools

ComfyUI Mini Toolkit – Helps reduce node redundancy. Let’s see if there’s time to keep it updated regularly.

By lepiai·Created 2 years ago·Updated 13 days ago· 10
lepiai/ComfyUI-Minitools
Nodes16
On cloudLocal install
CategoryMiniTools, image/layer
Stars10
Updated13 days ago

Nodes (16)

Prompt Optimizer v1.2 👻

An LLM Prompt Optimizer That Speaks Bernini's Task Language

MiniTools
Aspect Ratio Selector 👻

A dropdown that hands you a latent, width and height — no calculator required

MiniTools
Chinese English Translate 👻

Chinese ⇄ English prompt translation that also knows which way you typed it

MiniTools
Color to RGB 👻

From a Color Picker String to Three Separate Numbers

MiniTools
Crop Transparent Edges 👻

Get Your Cutout Out of All That Empty Space

MiniTools
RGB or HEX Convert to DEC 👻

Every Color, Squeezed Into One Number

MiniTools
Image Layer Editor 👻

Actually move, rotate and scale layers by hand before ComfyUI keeps going

image/layer
Image to Mask (With Alpha) 👻

Any Image Into a Mask, With a Brightness Knob

MiniTools
MiniMax H3 Output Unpacker 👻

The 22-port hose that turns one H3 pipe into wires you can actually use

MiniTools
MiniMax H3 Prompt Optimizer 👻

The node that writes MiniMax H3 prompts so you don't have to learn the shot-timestamp grammar

MiniTools
MiniMax H3 Studio 👻

One node from rough idea to MiniMax H3 conditioning — text, first-frame, or all-reference

MiniTools
MiniMax H3 LLM Config 👻

One config node to feed every LLM-powered node in the pack — any OpenAI-compatible API will do

MiniTools
Sensitive Word Filter 👻

Swap the words your model won't touch for ones it will, one random pick at a time

MiniTools
Task System Prompt Selector 👻

Stop typing the same system prompt twice — Bernini's task roles, one dropdown away

MiniTools
Translate to English 👻

A Prompt Translator That Makes You Edit the Source Code

MiniTools
Numeric Slider 👻

Two Sliders That Just Pass Numbers Through

MiniTools
Readme

comfyui-minitools

comfyui小工具集,避免节点冗余,看有没时间持续更新吧~

安装方法:

git clone命令克隆本项目,即可完成所有节点的安装。

1、color2rgb 用于配合comfyui layer style中颜色选择器节点,转换成RGB,且分别输出R、G、B值 image

2、promptsTranslateEN 提示词翻译节点,将输入的内容转换成英文,用的百度翻译api,所以需要实现准备好appid(可在百度翻译官方免费申请) 节点演示: image

3、RGB or HEX Convert to DEC 将十六进制颜色码和RBG转换成十进制 image

4、CropTransparentEdges 按透明区域裁剪 微信截图_20250522224212

5、ImageToMaskWithAlpha 将图片转换成带有alpha通道的遮罩 微信截图_20250522223903

6、NumericSlider数字滑块,包含浮点数和整数 微信截图_20250522223929

7、PromptOptimizer 基于字节Bernini官方仓库中提示词增强优化而来,适用于提示词反推和优化、扩写(官方演示)

支持单图反推:可用于出图、出视频、首尾帧视频、视频编辑

多图反推:多图、视频反推,用于出视频、首尾帧视频、视频编辑

反推内容会自动根据Bernini官方提示词预设模板完成补全和优化,也就是说不只是用于Bernini,可以完全独立出来作为一个提示词生成器来用。 节点依赖阿里百炼大模型api,默认使用的是多模态模型,如果想节约token,可以分纯文本大模型和带有VL标识的视觉模型或多模态大模型,点这里可注册阿里云百炼后创建apikey,就可以免费获得不同模型100万token使用额度 <img width="1674" height="1056" alt="image" src="https://github.com/user-attachments/assets/10a13d69-81df-437d-af6d-cfa7e74a57b3" />

8、Minimax H3 Studio 海螺H3工作台 利用这个节点只用一套工作流完成文生视频、图生视频(含首尾帧)、全能参考;支持所有兼容openai api协议的接口,包括但不限于本地ollama和阿里百炼api。 支持在提示词输入框中输入@调用上传的图片,支持点击图片自动填入图片名到提示词。 在不适用llm接口的情况下,可以直接当作提示词编辑器离线使用,不走api来跑视频。 <img width="858" height="756" alt="image" src="https://github.com/user-attachments/assets/a597e3fb-457d-4122-9958-eac93ff00f27" />