hydropix/AutoDescribe-Images
Tool to automatically generate text descriptions for images using Ollama vision models (LLaVA, Qwen3-VL, Llama Vision)
This tool helps AI artists and trainers automatically create detailed text descriptions, or captions, for images in their dataset. You feed it a folder of images, and it uses visual AI to analyze each picture and generate a `.txt` file with a consistent description, tailored to various AI image generation models like Stable Diffusion or Z-Image. This is perfect for anyone training custom AI models (LoRAs) who needs to quickly caption a large collection of images.
Use this if you are an AI artist or model trainer who needs to generate high-quality, consistent text descriptions for large image datasets to train AI image generation models.
Not ideal if you are looking for a general-purpose image captioning tool for personal photo collections or for web accessibility purposes, as its primary focus is AI model training.
Stars
32
Forks
3
Language
Python
License
—
Category
Last pushed
Dec 14, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/hydropix/AutoDescribe-Images"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related models
imSanko/Image_Caption_Generator_With_Transformers
This repository contains code for generating captions for images using a Transformer-based...
SkAndMl/captiongpt
Image Captioning using ViT and GPT. Notebook version in the following link
adityakapole/Caption-Generator
Captionify is a versatile and user-friendly image captioning project that harnesses the power of...