Imagev1.0.0

Florence-2 (Caption & Detect)

Caption, tag or read text out of an image.

3 inputsTEXT

{'<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

Output

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

Run it from your code

The same node, called by id from any surface. Every tab pins florence-2 and passes the ports below. Full guide.

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: "" },
});

# Install once, then sign in
npm install -g blitflow
blitflow login

blitflow node florence-2 \
  -i image=@https://... \
  -i task="Caption" \
  -i textInput=""

{
  "name": "runs_node",
  "arguments": {
    "node": "florence-2",
    "inputs": {
      "image": {
        "ref": "https://..."
      },
      "task": {
        "value": "Caption"
      },
      "textInput": {
        "value": ""
      }
    }
  }
}

curl https://studio.blitflow.com/api/v1/runs/node \
  -H "Authorization: Bearer $BLITFLOW_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"node":"florence-2","inputs":{"image":{"ref":"https://..."},"task":{"value":"Caption"},"textInput":{"value":""}}}'

Schema

Inputs

image*	IMAGE
task	TEXT	Caption · Detailed Caption · More Detailed Caption · Caption to Phrase Grounding · Object Detection · Dense Region Caption · Region Proposal · OCR · OCR with Region	Caption
textInput	TEXT

Outputs

text