I

Icedit MoE LoRA

Developed by sanaka87
ICEdit is an instructional image editing method based on large-scale diffusion transformers, achieving state-of-the-art editing effects with only 0.5% of training data and 1% of parameters.
Downloads 4,202
Release Time : 4/30/2025

Model Overview

ICEdit enables instructional image editing through in-context generation, supporting high-precision multi-round editing and diverse single-round editing effects, excelling particularly in style transfer, attribute modification, and background changes.

Model Features

Efficient Training
Achieves state-of-the-art editing effects using only 0.5% of the training data and 1% of the parameters required by previous SOTA methods.
Multi-Round Editing
Supports high-precision execution of continuous multi-round editing operations.
Diverse Editing
Produces diverse and visually impressive results in single-round editing.
Lightweight
Compact model parameters suitable for deployment in resource-limited environments.

Model Capabilities

Add objects
Modify color attributes
Apply style transfer
Change background
Object removal (lower success rate)

Use Cases

Artistic Creation
Style Transfer
Convert photos into different artistic styles
High-quality style transfer effects
Attribute Editing
Modify attributes such as clothing and hairstyle
Natural and realistic editing effects
Commercial Design
Advertisement Material Editing
Quickly modify product displays in advertisements
Efficient generation of diverse advertisement materials
Featured Recommended AI Models
AIbase
Empowering the Future, Your AI Solution Knowledge Base
Š 2025AIbase