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

<Gallery /> <div align="center">

🗑️ Flux Object Removal LoRA

Remove unwanted objects from images with AI-powered inpainting

<img src="images/banner.jpg" alt="Object Removal LoRA Banner" width="100%"> </div>

---

🎯 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

<table> <tr> <th>Input (with highlighted object)</th> <th>Output (object removed)</th> </tr> <tr> <td><img src="examples/example1_input.jpg" width="300"></td> <td><img src="examples/example1_output.jpg" width="300"></td> </tr> <tr> <td><img src="examples/example2_input.jpg" width="300"></td> <td><img src="examples/example2_output.jpg" width="300"></td> </tr> <tr> <td><img src="examples/example3_input.jpg" width="300"></td> <td><img src="examples/example3_output.jpg" width="300"></td> </tr> <tr> <td><img src="examples/example4_input.jpg" width="300"></td> <td><img src="examples/example4_output.jpg" width="300"></td> </tr> </table>

---

🚀 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

---

🎓 Training Details

<details> <summary>Click to expand</summary>

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

</details>

---

🎮 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

---

<div align="center">

Created by @ilkerzgi • Trained with fal.ai

</div>