ComfyUI-PickScore-Nodes

★ 39

图像评分排序与筛选PickScoreComfyUI 插件

为 ComfyUI 提供基于 PickScore 的图像评分节点，批量评估并排序生成结果，快速找出最符合提示词的图像。

💡 批量给生成图像打分并挑出最符合提示的图像。

🍴 8 Forks💻 Python🔄 2024-09-08

🔗 GitHub 原文

📦

网盘下载

复制链接后前往夸克网盘下载

https://pan.quark.cn/s/86a6deb1b5f6

📄 README

ComfyUI PickScore Nodes

Image scoring nodes for ComfyUI using PickScore to predict which images in a batch best match a given prompt.

Installation

Clone the repository to custom_nodes:

git clone https://github.com/Zuellni/ComfyUI-PickScore-Nodes custom_nodes/ComfyUI-PickScore-Nodes

Nodes

Name | Description

:— | :—

Loader | Loads scoring models from Hugging Face or a given directory. Uses yuvalkirstain/PickScore_v1 by default.

Processor | Takes images/text and converts them to inputs for the Selector node.

Selector | Selects up to limit images and passes them to other nodes along with latents/masks of the same shape. Interrupts processing if the threshold isn’t reached.

Workflow

An example workflow is embedded in the image below and can be opened in ComfyUI.