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 FireRed Image Edit AI Image Generator!

FireRed Image Edit

0/2000
Upload Image0/3

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

10 Editing Capabilities

Add

Add new objects or elements to images. The model understands spatial context, lighting, and perspective to seamlessly integrate new elements into existing scenes.

Adjust

Modify attributes like color, lighting, expression, and texture. Fine-tune visual properties while maintaining overall image coherence and natural appearance.

Replace

Swap specific objects in images with alternatives. The replacement automatically adapts to surrounding context, matching lighting, shadows, and perspective.

Remove

Clean removal of unwanted elements with intelligent inpainting. The model fills removed areas with contextually appropriate content, preserving scene integrity.

Background

Replace or transform backgrounds while perfectly preserving foreground subjects. Automatic lighting and shadow adjustment ensures photorealistic composites.

Stylize

Apply artistic styles — anime, oil painting, vintage film, and more — while preserving subject identity and facial features. Goes beyond simple filters.

FireRed Image Edit FAQ

FireRed Image Edit FAQ

FireRed Image Edit is an open-source, instruction-driven AI 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 covers 10 editing categories: Add, Adjust, Replace, Remove, Background, Stylize, Text, Restoration, Multi-Image, and Virtual Try-on. Licensed under Apache-2.0 for commercial use.
Trusted Feedback

What Creators Say About FireRed Image Edit

"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."

S

Sarah Chen

E-commerce Photographer

"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."

M

Marcus Liu

Content Creator

"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."

E

Emily Zhang

Social Media Manager

Limited Time Access

Try FireRed Image Edit Free

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