Open Source · Apache-2.0

FireRed Image Edit

Open-source instruction-driven AI image editing model by Xiaohongshu FireRed team — 10 editing capabilities covering add, remove, replace, background, stylize, text, restoration, portrait makeup, multi-image fusion, and virtual try-on. Built on Diffusion Transformer with bilingual Chinese-English support. Try it free in Nano Banana Pro!

About

About FireRed Image Edit

FireRed Image Edit is a general-purpose image editing model developed by Xiaohongshu's FireRed team. Built on Diffusion Transformer (DiT) architecture with Qwen2.5-VL as the vision-language encoder, it natively extends text-to-image generation into editing — not a post-hoc add-on. The model supports bilingual Chinese-English instructions and covers 10 editing categories: Add, Adjust, Replace, Remove, Background, Stylize, Text, Restoration, Multi-Image, and Virtual Try-on. It achieves state-of-the-art open-source results on REDEdit-Bench, ImgEdit, and GEdit benchmarks. Version 1.1 further enhances portrait consistency, multi-element fusion, stylized text rendering, and portrait makeup. Licensed under Apache-2.0 for commercial use.

About FireRed Image Edit
Core Features Overview

10 Editing Capabilities

Instruction-driven editing across 10 categories — describe what you want in natural language, no manual masking needed

Text Editing — Style-Preserving Typography Example
Text Editing — Style-Preserving Typography Example

Text Editing — Style-Preserving Typography

01

Modify text in images while preserving font style, lighting, and perspective

FireRed Image Edit maintains text styles with high fidelity when editing text within images — preserving original font, size, color, lighting, and perspective. This capability is comparable to closed-source solutions and is ideal for poster editing, signage localization, UI mockup updates, and any scenario requiring precise text modification in existing images.

Prompt

Change the store sign text from 'OPEN' to 'CLOSED' while keeping the same neon style

Text replacement preserving neon font style and lighting

Update the poster headline to '2026 Summer Collection' keeping the same typography

Typography-preserving text editing for commercial design

Output (Example)
2
Photo Restoration — Old Photo Repair & Enhancement Example
Photo Restoration — Old Photo Repair & Enhancement Example

Photo Restoration — Old Photo Repair & Enhancement

02

High-quality restoration of damaged, faded, or old photographs

Restore old, damaged, or degraded photographs to high quality. FireRed Image Edit handles scratches, fading, color degradation, noise, and blur — reconstructing missing details while maintaining the authentic character of the original photo. Supports both color correction and structural repair.

Prompt

Restore this old faded photograph, fix scratches and enhance colors

Old photo restoration with scratch removal and color enhancement

Enhance this low-quality photo, remove noise and sharpen details

Photo enhancement with noise reduction and detail sharpening

Output (Example)
2
Portrait Editing — Makeup, Hairstyle & Retouching Example
Portrait Editing — Makeup, Hairstyle & Retouching Example

Portrait Editing — Makeup, Hairstyle & Retouching

03

Professional portrait editing with identity preservation

Version 1.1 significantly enhances portrait editing. Supports professional beauty retouching, skin tone adjustment (yellow/olive skin brightening), dozens of makeup styles from natural beauty to Halloween creative looks, hairstyle transformation, and expression adjustment — all while maintaining facial identity with minimal drift. The LoRA-Zoo also provides a dedicated BeautyMaster adapter for enhanced beauty editing.

Prompt

Apply natural beauty retouching, smooth skin and brighten complexion

Professional beauty retouching with identity preservation

Apply elegant evening makeup with smoky eyes and red lips

Creative makeup application maintaining facial identity

Output (Example)
2
Multi-Image Editing — Up to 3 Reference Images Example
Multi-Image Editing — Up to 3 Reference Images Example

Multi-Image Editing — Up to 3 Reference Images

04

Combine multiple reference images for intelligent fusion and compositing

FireRed Image Edit supports up to 3 reference images simultaneously for multi-image conditioning. This enables identity transfer, reference-guided editing, group photo composition, and creative multi-element fusion. Version 1.1 significantly improves multi-image injection reliability with better lighting, perspective, and style harmonization across sources.

Prompt

Combine the person from image 1 with the background from image 2 and the lighting style from image 3

Three-image fusion with automatic harmonization

Create a group photo combining the people from these two separate photos

Group photo composition from separate source images

Output (Example)
2
Virtual Try-On — Clothing & Outfit Swap Example
Virtual Try-On — Clothing & Outfit Swap Example

Virtual Try-On — Clothing & Outfit Swap

05

Dress subjects in outfits from reference images with natural draping

Upload a person photo and an outfit photo, then instruct the model to combine them. FireRed Image Edit handles natural fabric draping, body proportion adaptation, lighting matching, and shadow generation. Reference images by number in your prompt for precise control — 'Put the person from Figure 1 in the outfit from Figure 2'. Ideal for e-commerce product visualization and fashion content creation.

Prompt

Put the person from image 1 in the outfit from image 2

Virtual try-on with natural fabric draping and body adaptation

Dress this model in the jacket from the second photo

Clothing swap with lighting and proportion matching

Output (Example)
2
FAQ

FireRed Image Edit FAQ

FireRed Image Edit FAQ

What Creators Say About FireRed Image Edit

What Creators Say About FireRed Image Edit

Read All Stories
Sarah Chen
Sarah Chen“The virtual try-on is a game-changer for product shoots. We show clothing on different models without reshooting — saves days of studio time. The multi-image fusion handles lighting automatically.”
Marcus Liu
Marcus Liu“Instruction-driven editing feels natural. I describe what I want changed and it handles the rest. Identity preservation during style transfer is impressive — faces stay recognizable across any artistic style.”
Emily Zhang
Emily Zhang“Background replacement used to take hours in Photoshop. Now I describe the scene and FireRed handles lighting, shadows, everything. Bilingual support is perfect for our global campaigns.”

Explore More AI Image Models

Flux 2

Flux 2

New

Flux 2 is the latest image generation model from Black Forest Labs, the team behind the original Stable Diffusion architecture. It delivers photorealistic images with remarkable speed, precise text rendering, and industry-leading prompt adherence. Flux 2 excels at complex compositions, human anatomy, and diverse artistic styles — making it one of the most versatile AI image generators available today.

Try now
Z-Image

Z-Image

Z-Image is Zhipu AI's advanced image generation model, built with deep understanding of both Chinese and English prompts. It excels at generating culturally rich visuals, from traditional Chinese art styles to modern commercial design, with precise control over composition, color, and detail.

Try now
GLM Image

GLM Image

GLM Image is Zhipu AI's image generation model built on the GLM architecture, offering exceptional bilingual prompt understanding in both Chinese and English. It excels at generating high-quality images with precise compositional control and rich artistic expression.

Try now
GPT Image 2

GPT Image 2

New

GPT Image 2 (ChatGPT Images 2.0) is OpenAI's latest image model, launched in April 2026 as the successor to GPT-4o image generation. It is the first OpenAI image model with built-in reasoning, achieving over 95% text rendering accuracy across Latin and non-Latin scripts. The model supports 2K resolution output, continuous aspect ratios from 3:1 to 1:3, and generates up to 8 consistent images from a single prompt. With Thinking Mode, it can search the web during generation, analyze uploaded brand guidelines, and self-verify outputs before rendering.

Try now
Seedream 5.0

Seedream 5.0

New

Seedream 5.0 Lite is ByteDance's unified multimodal image generation model, the first to integrate real-time web search and multi-step logical reasoning into AI image generation. It handles complex prompts involving current events and cultural trends, directly outputs 4K ultra-HD images without post-processing, and achieves 94%+ text rendering accuracy. The most intelligent free AI image generator available.

Try now
Seedream 4.5

Seedream 4.5

New

Seedream 4.5 is a free AI image generator that understands natural language narrative, not keyword stuffing. Describe scenes with flowing sentences and get cinematic-quality results online. It excels at HD lighting, switches between hyper-realistic photography and surreal art, and outputs up to 4K resolution with no watermark.

Try now

Try FireRed Image Edit Free

Experience FireRed Image Edit — 10 editing capabilities, bilingual instructions, identity-preserving edits. Start editing free with no watermark
Try FireRed Image Edit Free