Spaces:

multimodalart
/

Liquid-Image-to-JSON

Running on Zero

App Files Files Community

Liquid-Image-to-JSON / README.md

multimodalart HF Staff

Upload folder using huggingface_hub

0c8a825 verified 3 days ago

preview code

raw

history blame contribute delete

866 Bytes

A newer version of the Gradio SDK is available: 6.17.3

Upgrade

metadata

title: Liquid Image to JSON
emoji: 💧
colorFrom: yellow
colorTo: green
sdk: gradio
sdk_version: 6.15.1
app_file: app.py
short_description: Turn any image into structured JSON with LFM2.5-VL Extract
python_version: '3.12'
pinned: true

💧 Liquid Image → JSON

A visual studio for structured field extraction from images, powered by LiquidAI's LFM2.5-VL Extract models:

LFM2.5-VL-450M-Extract — ⚡ fastest
LFM2.5-VL-1.6B-Extract — 🎯 most accurate

Define the fields you care about with the visual schema builder (or pick a preset), drop an image, and the model streams a clean JSON object back — rendered as animated cards. Built in the gr.Citrus visual style on ZeroGPU.