Giter Site home page Giter Site logo

controlnet-lllite-comfyui's Introduction

ControlNet-LLLite-ComfyUI

日本語版ドキュメントは後半にあります。

This is a UI for inference of ControlNet-LLLite.

ControlNet-LLLite is an experimental implementation, so there may be some problems.

image

Installation

  1. Clone this repository to custom_nodes.
  2. Put ControlNet-LLLite models to ControlNet-LLLite-ComfyUI/models. You can download sample models from here.

Usage

Load sample workflow.

You can specify the strength of the effect with strength. 1.0 is default, 0.0 is no effect.

You can apply only to some diffusion steps with steps, start_percent, and end_percent. Specify the number of steps specified in the sampler in steps, and specify the start and end steps from 0 to 100 in start_percent and end_percent, respectively.

(Because we cannot check the total number of steps in the node, this specification has been made. Please check the console output for the specific application range.)

Tips

  • If the generated image size is different from the control image size, resize it with image/upscaling/UpscaleImage as shown in the workflow.

  • You can create a Canny image from a normal image with the image/preprocessors/Canny node.

Acknowledgements

This repository is based on IPAdapter-ComfyUI by laksjdjf. Thanks to laksjdjf.

ControlNet-LLLite-ComfyUI:日本語版ドキュメント

ControlNet-LLLite の推論用のUIです。

ControlNet-LLLiteがそもそもきわめて実験的な実装のため、問題がいろいろあるかもしれません。

image

インストール方法

  1. custom_nodesにcloneします。
  2. ControlNet-LLLite-ComfyUI/models にモデルを入れます。サンプルはこちらからダウンロードできます。

使い方

サンプルのワークフローを読み込んでください。

strengthに効果の強さを指定できます。1.0でデフォルト、0.0で効果なしです。

stepsstart_percentend_percentで拡散ステップの一部にだけ効果を適用できます。stepsにsamplerに指定したステップ数を指定し、start_percentend_percentにそれぞれ開始と終了のステップを0から100で指定します。

(ノード内で全体のステップ数を確認できないためこのような仕様になっています。具体的な適用範囲はコンソール出力を確認してください。)

ヒント

  • 生成画像サイズと制御用画像サイズが異なる場合はワークフローにあるように image/upscaling/UpscaleImage でリサイズしてください。
  • 通常の画像からCanny画像を作るには image/preprocessors/Canny のノードが使えます。

謝辞

laksjdjf 氏の IPAdapter-ComfyUI を参考にしています。laksjdjf 氏に感謝します。

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.