<h2 id="short-description">🧠 Short Description</h2>ComfyUI workflow that automatically generates image captions using JoyCaption, compatible with both Stable Diffusion and Flux. Perfect for dataset preparation or qualitative comparison between caption models.<hr /><h2 id="detailed-overview">⚙️ Detailed Overview</h2>This workflow takes a folder of images and automatically produces text descriptions (captions) using JoyCaption. It supports three execution modes:<ol><li>Stable Diffusion only</li><li>Flux only</li><li>Both models simultaneously</li></ol>The pipeline is divided into five main sections:<ul><li>Input (orange): select the source folder, choose sorting method, and preview the images being processed.</li><li>Prompt &amp; Options (green): choose between a custom or automatic prompt and configure all JoyCaption parameters.</li><li>Description (yellow / blue): parallel caption generation for SD and Flux.</li><li>Output (right): automatically saves captions to separate files without overwriting.</li><li>Preview: optional visual check to ensure consistency before running a full batch.</li></ul>This system makes it easy to compare the quality and consistency of captions produced by different models, while fully automating large-scale dataset annotation.

Files with SHA256: beb44fe3e433d863b6ee206d8f941d71ffada886d87e8bd8211029b17e74406f