All models

Florence-2 (Caption & Detect)

Caption, tag or read text out of an image.

Edit & Analyze Imagev1.0.03 inputsTEXT
Florence-2 (Caption & Detect) input

{'<DETAILED_CAPTION>': 'The image shows a golden retriever puppy sitting in a field of daisies, surrounded by lush green grass and a bright blue sky.'}

Image captioned in one line

Try it right here

Fill the inputs the node publishes and run it on your own account. The same ports, defaults and types the studio uses.

Inputs

IMAGE
TEXT
TEXT
Sign in to run

Running a model executes it on your account. Browsing the catalog stays free and needs no account.

Output

Fill in the inputs and run the node to see its output here.

Call it from your code

The same node, called by id from any surface. Every tab pins this node and passes the ports below.

import { BlitClient } from "@blitflow/sdk";

const { runNode } = new BlitClient({ apiKey: process.env.BLITFLOW_TOKEN });

const { outputs } = await runNode("florence-2", {
  image: { ref: "https://..." },
  task: { value: "Caption" },
  textInput: { value: "" },
});

Schema

Every port this node publishes, with its type, its hint and the default it runs with. florence-2 is the id you call.

Inputs

image*IMAGE
taskTEXT
Caption · Detailed Caption · More Detailed Caption · Caption to Phrase Grounding · Object Detection · Dense Region Caption · Region Proposal · OCR · OCR with Region
Caption
textInputTEXT

Outputs

textTEXT

Chain it with the rest of the catalog

Open the studio