Update README.md

README.md

@@ -35,10 +35,53 @@ arxiv: 2602.13344
 We introduce FireRed-Image-Edit-1.1, an upgrade to our general-purpose image editing foundation model. Building upon the capabilities presented in the FireRed-Image-Edit-1.0 Technical Report, version 1.1 significantly enhances identity consistency, multi-image conditioning, and domain-specialized editing performance, bringing the model closer to real-world creative production needs.
 
 
-## ✨ What's New
+## ✨ 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.
 
-- **Stronger Identity Consistency** — Substantially improved facial and character consistency during edits, with better texture stability and reduced identity drift in portrait and cosmetic scenarios.
-- **Enhanced Multi-Image Injection** — Native support for multi-image conditioning enables more reliable identity transfer, reference-guided editing, virtual try-on, and group photo composition.
-- **Artistic Typography (CoverCraft)** — Improved decorative font rendering and stylized text generation for cover design, poster creation, and expressive title layouts while preserving structural clarity.
-- **Professional Makeup Editing (Makeup LoRA)** — Refined cosmetic editing capabilities including skin enhancement, color harmonization, and detailed eye and lip adjustments, with strong realism and identity preservation.
-- **High-Speed Distilled Variant (Lightning 8-step)** — An optimized 8-step distilled model that significantly reduces inference latency while maintaining strong instruction alignment and visual coherence.
+#### 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.
+
+
+
+## 🎨 Showcase
+Some real outputs produced by FireRed-Image-Edit across general editing.
+
+### Portrait
+<p align="center">
+    <img src="https://github.com/FireRedTeam/FireRed-Image-Edit/blob/main/assets/showcase_portrait.png" width="800"/>
+<p> 
+
+
+### Multi-image-fusion
+<p align="center">
+    <img src="https://github.com/FireRedTeam/FireRed-Image-Edit/raw/main/assets/showcase_multi_fusion.png" width="800"/>
+<p> 
+
+### Makeup([Lora](https://huggingface.co/FireRedTeam/FireRed-Image-Edit-LoRA-Zoo/blob/main/FireRed-Image-Edit-Makeup.safetensors))
+<p align="center">
+    <img src="https://github.com/FireRedTeam/FireRed-Image-Edit/raw/main/assets/showcase_makeup.png" width="800"/>
+<p> 
+
+
+### Text Style Reference([Lora](https://huggingface.co/FireRedTeam/FireRed-Image-Edit-LoRA-Zoo/blob/main/FireRed-Image-Edit-Covercraft.safetensors))
+<p align="center">
+    <img src="https://github.com/FireRedTeam/FireRed-Image-Edit/raw/main/assets/showcase_mult_text.png" width="800"/>
+<p> 
+
+
+## 🏆 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.
+<p align="center">
+    <img src="https://github.com/FireRedTeam/FireRed-Image-Edit/raw/main/assets/eval_benchmark.png" width="800"/>
+<p>