ComfyUI Extension: ImageCLIPSimilarityPure
Run ComfyUI workflows without the setup
No installs, no CUDA version roulette, no GPU sitting idle on your bill. Bring a workflow and run it in the browser.
A ComfyUI custom node that calculates semantic similarity between two images using CLIP Vision models, outputting a numerical similarity score. (Description by CC)
README
ComfyUI Image Similarity Node
计算两张图片的语义相似度。
安装
手动克隆到此目录
依赖模型
需要下载 CLIP Vision 模型到 ComfyUI/models/clip_vision/:
- CLIP-ViT-H-14-laion2B-s32B-b79K.safetensors
- 或大模型CLIP-ViT-bigG-14-laion2B-39B-b160k
用法
输入两张图片，即可输出相似度数值
Run ComfyUI workflows without the setup
No installs, no CUDA version roulette, no GPU sitting idle on your bill. Bring a workflow and run it in the browser.