FireRed-Image-Edit

Summary

• Introduction
• Model Architecture
• Key Features
• Evaluation Results
• Parameters
• Examples
• Usage for developers
• Reference
• License
• Citation

Introduction

FireRed-Image-Edit-1.1 Based on the FireRed-Image-Edit-1.0 foundation model, it optimizes portrait consistency, multi-element fusion, stylized text reference, and portrait makeup effects. FireRed-Image-Edit-1.0 is a general-purpose image editing model that delivers high-fidelity and consistent editing across a wide range of scenarios. FireRed-Image-Edit delivers leading open-source results with accurate instruction following, high image quality, and consistent visual coherence.

Model Architecture

Key Features

Strong Editing Performance

• 🆔 State-of-the-Art Identity Consistency: Open-source SOTA in character identity preservation, ensuring subjects remain recognizable across complex edits.
• 🧩 Multi-Element Fusion: Freely combine 10+ elements with Agent-powered automatic cropping and stitching—no more struggles with short prompts.
• 💄 Comprehensive Portrait Makeup: Dozens of styles from professional beauty retouching and yellow/olive skin tone brightening to Halloween witch makeup and creative looks.
• 📝 Text Style Reference: Maintains high-fidelity typography and stylized text comparable to closed-source solutions.
• 🖼️ Professional Photo Restoration: High-quality old photo repair and enhancement with superior detail recovery.

Ultimate Engineering Optimization

• 🔧 Open LoRA Training Ecosystem: Full training code released for custom style creation, optimized samplers maximize GPU efficiency for identical tasks, sizes, and input counts.
• ⚡ Extreme Speed Optimization: Complete acceleration suite featuring distillation, quantization, and static compilation—delivering 4.5s end-to-end generation with just 30GB VRAM
• 🤖 Intelligent Agent Workflow: Automatic multi-image processing handles complex compositions like virtual try-on without requiring lengthy prompt engineering
• 🔌 Universal Deployment: Native ComfyUI node support and GGUF lightweight format compatibility for seamless production integration

Native Editing Capability from T2I Backbone

• 🏗️ Backbone-Agnostic Architecture: Editing capabilities injected through full Pretrain → SFT → RL pipeline, transferable to any T2I foundation model.

Evaluation Results

FireRed-Image-Edit establishes a new state-of-the-art among open-source models on Imgedit, Gedit, and RedEdit, while surpassing our closed-source competitors in specific dimensions—a distinction further corroborated by human evaluations highlighting its superior prompt following and visual consistency. Detailed information can be found here.

Parameters

Inputs

• input_image - (image -.png|.jpg|.jpeg): The source image to be edited.
• prompt - (text): A text description that guides the model in generating the desired output.
• seed - (integer): Controls randomness for reproducibility. Using the same seed will produce consistent results. Range: 0 to 4,294,967,295, step 1
• cfg_scale - (float): Controls how strongly the model follows the input prompt. Range: 1.0 to 10.0, step 0.1
• steps - (integer): The number of inference steps used during generation. More steps generally improve quality but increase computation time. Range: 1 to 30, step 1

Output

• output_image - (image -.png): The edited version of the input image, generated according to the text prompt.

Examples

Usage for developers

Please find below the details to track the information and access the code for processing the model on our platform.

Requirements

pip install -r requirements.txt

Code based on AIOZ structure

import torch
from PIL import Image
from diffusers import QwenImageEditPlusPipeline

def load_pipeline(model_path: str):
    ...

def do_ai_task(
        input_image: Union[str, Path],
        prompt: Union[str, Path],
        seed: Union[int, int],
        cfg_scale: Union[float, float],
        steps: Union[int, int],
        model_storage_directory: Union[str, Path],
        device: Literal["cpu", "cuda", "gpu"] = "cpu",
        *args, **kwargs) -> Any:
    """Define AI task: load model, pre-process, post-process, etc ..."""
    # Define AI task workflow. Below is an example
    
    # Pipeline loaded.
    model_path = model_storage_directory + ""
    pipeline = load_pipeline(model_path)

    # ── Load all input images ──
    images = Image.open(input_image).convert("RGB")

    ...

    output_image = open("output_image.png", "rb")  # io.BufferedReader
    return output_image

Reference

This repository is based on and inspired by FireRedTeam's work. We sincerely appreciate their generosity in sharing the code.

License

We respect and comply with the terms of the author's license cited in the Reference section.

Citation

@article{firered2026rededit,
      title={FireRed-Image-Edit-1.0 Technical Report}, 
      author={Super Intelligence Team},
      year={2026},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2602.13344}, 
}