Generate a caption or alt text for any image

ViT-GPT2 gives a short factual caption in a 250 MB download; Mozilla's DistilViT is roughly a quarter the size for the same one-line style, and a flower-tuned variant handles botanical subjects. The obvious use is accessibility — writing alt text for a large image library without paying per call or exposing unpublished assets — and the second is bulk cataloguing. Everything runs on your GPU, so a folder of a thousand product shots costs nothing but time.

image caption generatorai alt text generatordescribe image ai freevit-gpt2 demodistilvit browserlightweight captioning modelautomatic alt textimage to text description

Frequently asked questions

Which model writes the best alt text?

ViT-GPT2 is the most reliable general choice; DistilViT is about a quarter of the size if you are captioning in bulk and can accept slightly plainer wording.

Can it answer questions about the image?

Not here. These captioners describe an image but take no text prompt, so they cannot answer questions about it. Vision-language models that can are not yet supported by the browser runtime.

Models available for this task

ViT-GPT2 Captioner — Xenova/vit-gpt2-image-captioning, 248 MB, 239M params
DistilViT — Mozilla/distilvit, 189 MB
ViT-GPT2 Flower Captioner — cristianglezm/ViT-GPT2-FlowerCaptioner-ONNX, 247 MB, 239M params

Explore the rest of the playground

Vision models

Background removal — Remove a background without uploading the photo
Object detection — Detect objects in an image, on your own hardware
Zero-shot object detection — Detect anything you can describe, with no training
Image classification — Classify an image with ViT, locally
Zero-shot image classification — Classify images against labels you invent, using CLIP
Image segmentation — Segment an image into labelled regions, locally
Depth estimation — Generate a depth map from a single photo
Image to 3D (point cloud) — Turn a single photo into a 3D scene you can orbit
OCR (image to text) — Extract text from images without uploading them

Guides & comparisons

Model catalog — The model catalog: what actually runs in a browser
WebGPU vs WASM — WebGPU vs WebAssembly for running models in a browser
Browser AI vs cloud API — Browser inference vs a hosted API: an honest comparison
Transformers.js vs WebLLM — Transformers.js vs WebLLM
Whisper model sizes — Choosing a Whisper size for browser transcription
fp32 vs q8 vs q4 — Picking a quantization level for browser inference
Why no image generation — Why this playground has no text-to-image generation
FAQ — Frequently asked questions about browser-based AI
About — About this project

This playground needs JavaScript and WebGPU. Models are downloaded to your browser and executed on your own GPU, so there is nothing to show without a script engine. Enable JavaScript, or read the FAQ for what the site does.