Flux / README.md
nimraaaajhduksy's picture
Update README.md
9e64b6c verified

A newer version of the Gradio SDK is available: 6.0.2

Upgrade
metadata
title: Furniture Remover AI
emoji: πŸ›‹οΈ
colorFrom: indigo
colorTo: blue
sdk: gradio
sdk_version: 4.26.0
app_file: app.py
pinned: false

πŸ›‹οΈ Furniture Remover AI – Clean Any Room Image

This Space uses YOLOv8 and Flux.1-Kontext to detect and remove furniture or selected objects from any room image. Powered by πŸ€— Hugging Face, Gradio, and Diffusers.


✨ Features

  • πŸ“€ Upload a photo of a room
  • πŸ€– Detect objects using YOLOv8
  • 🎯 Two modes available:
    • Remove All Furniture – deletes all common furniture automatically
    • Selective Removal – choose which objects to remove from a detected list
  • 🎨 Clean and realistic image inpainting with Flux.1-Kontext (no mask needed)

πŸš€ How It Works

  1. Upload your room image
  2. Select a mode:
    • Mode 1: Remove all furniture
    • Mode 2: Select specific items (e.g., couch, vase, lamp)
  3. Click Submit and get a cleaned image

🧠 Models Used

  • YOLOv8 – for object detection (Ultralytics)
  • Flux.1-Kontext (black-forest-labs/FLUX.1-Kontext-dev) – prompt-based image inpainting using Hugging Face Diffusers

πŸ” Hugging Face Token Required

This app uses a private model. To use it:

  1. Go to Settings β†’ Secrets in your Space
  2. Add your token as:from huggingface_hub import login import os

Load token from HF secrets

hf_token = os.getenv("HUGGINGFACE_TOKEN") login(token=hf_token)

Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference