Update README.md

0e3f587 verified 4 days ago

6.34 kB

metadata

license: apache-2.0
language:
  - en
tags:
  - flux
  - flux-2-klein
  - flux-lora
  - lora
  - object-removal
  - inpainting
  - image-editing
  - image-to-image
  - fal-ai
  - template:diffusion-lora
pipeline_tag: image-to-image
widget:
  - text: Remove the highlighted object from the scene
    output:
      url: examples/example1_output.jpg
  - src: examples/example1_input.jpg
    prompt: Remove the highlighted object from the scene
    output:
      url: examples/example1_output.jpg
  - text: Remove the highlighted object from the scene
    output:
      url: examples/example2_output.jpg
  - src: examples/example2_input.jpg
    prompt: Remove the highlighted object from the scene
    output:
      url: examples/example2_output.jpg
  - text: Remove the highlighted object from the scene
    output:
      url: examples/example3_output.jpg
  - src: examples/example3_input.jpg
    prompt: Remove the highlighted object from the scene
    output:
      url: examples/example3_output.jpg
  - text: Remove the highlighted object from the scene
    output:
      url: examples/example4_output.jpg
  - src: examples/example4_input.jpg
    prompt: Remove the highlighted object from the scene
    output:
      url: examples/example4_output.jpg
base_model: black-forest-labs/FLUX.2-klein-4B
instance_prompt: Remove the highlighted object from the scene

Prompt
Remove the highlighted object from the scene

🗑️ Flux Object Removal LoRA

Remove unwanted objects from images with AI-powered inpainting

🎯 What does this model do?

This LoRA removes highlighted objects from images and fills the area naturally with contextually appropriate content. Simply mark the object you want to remove, and the model will erase it seamlessly.

┌─────────────────────────────────────┐
│                                     │
│     🏠  🌳  [🚗]  🌳  🏠            │  Highlighted object
│         ↓                           │  gets removed
│     🏠  🌳  ~~~~  🌳  🏠            │  and filled naturally
│                                     │
└─────────────────────────────────────┘

Perfect for cleaning up photos, removing distractions, and creating seamless backgrounds.

🖼️ Examples

Input (with highlighted object)	Output (object removed)

🚀 Quick Start

Prompt

Remove the highlighted object from the scene

Highlighting Requirements

Mark the object to remove with a visible highlight/mask
The highlight should clearly cover the object boundaries
Works best with distinct, isolated objects

💻 Usage

Try it Live on fal.ai

▶️ Open Playground

With fal.ai SDK

import fal_client

def on_queue_update(update):
    if isinstance(update, fal_client.InProgress):
        for log in update.logs:
           print(log["message"])

result = fal_client.subscribe(
    "fal-ai/flux-2-klein/4b/base/edit/lora",
    arguments={
        "prompt": "Remove the highlighted object from the scene",
        "model_name": None,
        "loras": [{
            "path": "https://huggingface.co/ilkerzgi/flux-object-remove-lora/resolve/main/flux-object-remove-lora.safetensors",
            "scale": 1.1
        }],
        "embeddings": [],
        "image_urls": ["https://your-image-with-highlighted-object.png"]
    },
    with_logs=True,
    on_queue_update=on_queue_update,
)
print(result)

📦 Model Files

File	Use Case
`flux-object-remove-lora.safetensors`	fal.ai
`kDEkt5q7tDLKOpQJIVMPx_pytorch_lora_weights_comfy_converted.safetensors`	ComfyUI

🎓 Training Details

Click to expand

Dataset

Size: 100 image pairs
Content: Diverse scenes with objects to remove including:
- People: individuals, groups in various settings
- Objects: furniture, vehicles, electronics
- Animals: pets, wildlife
- Text: signs, watermarks, logos
- Nature: plants, debris, unwanted elements
Highlighting: Objects marked for removal
Aspect ratios: Various (1:1, 16:9, 9:16, 4:3, 3:4, etc.)

Training

Base Model: FLUX.2-Klein 4B
Platform: fal.ai
Method: LoRA training
Steps: 4000
Learning Rate: 0.00005

🎮 Use Cases

Photo Cleanup: Remove photobombers, trash, or unwanted objects
Product Photography: Clean backgrounds for e-commerce
Real Estate: Remove furniture or personal items from property photos
Social Media: Create cleaner, more focused compositions

⚠️ Limitations

Works best with clearly highlighted/masked objects
Very large objects may leave visible artifacts
Complex backgrounds may require multiple passes
Reflections and shadows of removed objects may persist

📄 License

Apache 2.0

fal
/

flux-2-klein-4B-object-remove-lora