feeday/FireRed-Image-Edit-1.1-GGUF

Quantized GGUF Versions of FireRed-Image-Edit-1.1

Original model Link: https://huggingface.co/FireRedTeam/FireRed-Image-Edit-1.1

Watch us at Youtube: @VantageWithAI

🤗 HuggingFace Model | 🤗 LoRA Zoo | 🖥️ Demo | 📄 Technical Report

🔥 FireRed-Image-Edit-1.1

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

• 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.

📊 ComfyUI FireRed-Image-Edit-1.1-Q4_K_M TEST

• https://pan.quark.cn/s/d807bb689ccd

• CPU & RAM: Intel i7-12700H | 32.0 GB

• GPU: NVIDIA RTX 3060 Laptop (6G VRAM)

• OS & Runtime: Windows 11 | Python 3.10

• Total Time: 149s