Pass IndexThe State of AISign in

Dolphin

Dolphin (Document Image Parsing via Heterogeneous Anchor Prompting) is a novel multimodal document image parsing model that follows an analyze-then-parse paradigm.

text + image → text · made by ByteDance

Sold by

Nobody in the catalogue publishes a price for this yet.

About

Dolphin — a text model from ByteDance.

It takes text and images and returns text. It was published in May 2025. The catalogue files it under extract. Its weights are published under MIT, so you may run it on your own machine, or buy it from whoever serves it cheapest.

Every current figure

Maker
ByteDance
Register
model
Takes
text + image
Returns
text
Published
May 2025
Parameters
398 million · read from its own weights
Licence
mit

Known as 1 name

ByteDance/Dolphin