Workflow Features

• ✅ Pre-configured Qwen-Image-Edit + Inscene LoRA inference
• ✅ Optimized settings for in-scene editing quality
• ✅ Enhanced spatial understanding and scene coherence
• ✅ Effortless prompt and parameter tuning
• ✅ Compatible with various input image types

🎯 What is Inscene LoRA?

This LoRA model is specifically trained to enhance Qwen-Image-Edit's capability to perform in-scene image editing. It focuses on:

• Scene Coherence: Maintains logical spatial relationships within the scene
• Object Positioning: Better understands object placement and movement
• Camera Perspective: Improved handling of viewpoint changes and camera movements
• Action Sequences: Enhanced ability to depict sequential actions within the same scene
• Contextual Editing: Preserves scene context while making targeted modifications

🔧 Training Information

This LoRA model was trained using the FlyMy.AI LoRA Trainer with:

• Base Model: qwen/qwen-image-edit
• Training Focus: In-scene image editing and spatial understanding
• Dataset: A curated collection of scene-based editing examples (InScene dataset)
• Optimization: Low-Rank Adaptation for efficient fine-tuning

📊 Model Specifications

• Model Type: LoRA (Low-Rank Adaptation)
• Base Model: qwen/qwen-image-edit
• File Format: SafeTensors (.safetensors)
• Specialization: In-scene image editing
• Training Framework: Diffusers + Accelerate
• Memory Efficient: Optimized for consumer GPUs
  

Reprinted from: qwen-image-edit-inscene-lora