JoyCaption is an image captioning Visual Language Model (VLM) being built from the ground up as a free, open, and uncensored model for the community to use in training Diffusion models.

Joy Caption is a ComfyUI node using the LLaVA model to generate stylized image captions, supporting batch processing and GGUF models.

ComfyUI自定义节点，提供提示词翻译功能，支持多语言。comfyui custom nodes，translate prompt

ide-cap-chan is a utility for batch image captioning with natural language using various VL models

Caption Creator is a fast and portable tool for generating high-quality image captions and tags—ideal for custom dataset creation. Works seamlessly for both training and image generation.

My own JoyCaption frontend/UI node for ComfyUI. The main focus is in composability of the captioning prompt, so you see exactly what you will get, can also easily edit the prompt within the node.

Stable Diffusion WebUI extension that automatically refines prompts using local LLMs (JoyCaption + Qwen 2.5) based on visual context.

A simple app to generate caption for your instagram post using `JoyCaption` model hosted in RunPod.io