VOOZH about

URL: https://huggingface.co/FireRedTeam/FireRed-Image-Edit-1.1

⇱ FireRedTeam/FireRed-Image-Edit-1.1 Β· Hugging Face


πŸ‘ Hugging Face
πŸ‘ Hugging Face Model
πŸ‘ Hugging Face Model
πŸ‘ Hugging Face Model
πŸ‘ HF Demo
πŸ‘ ModelScope Model
πŸ‘ ModelScope Model
πŸ‘ MS Demo
πŸ‘ Image
πŸ‘ License
πŸ‘ Image

πŸ€— HuggingFace | πŸ€– ModelScope | πŸ–₯️ Demo | πŸ“„ Technical Report

πŸ‘ Image

πŸ”₯ 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.

✨ Key Features

Strong Editing Performance

  • πŸ†” 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 stitchingβ€”no more struggles with short prompts.
  • πŸ’„ Comprehensive Portrait Makeup: Dozens of styles from professional beauty retouching and yellow/olive skin tone brightening to Halloween witch makeup and creative looks.
  • πŸ“ Text Style Reference: Maintains high-fidelity typography and stylized text comparable to closed-source solutions.
  • πŸ–ΌοΈ Professional Photo Restoration: High-quality old photo repair and enhancement with superior detail recovery.

Ultimate Engineering Optimization

  • πŸ”§ 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 compilationβ€”delivering 4.5s end-to-end generation with just 30GB VRAM
  • πŸ€– Intelligent Agent Workflow: Automatic multi-image processing handles complex compositions like virtual try-on without requiring lengthy prompt engineering
  • πŸ”Œ Universal Deployment: Native ComfyUI node support and GGUF lightweight format compatibility for seamless production integration

🎨 Showcase

Some real outputs produced by FireRed-Image-Edit across general editing.

Portrait(More Cases | ζ›΄ε€šη»“ζžœ)

πŸ‘ Image

Multi-image-fusion(More Cases

πŸ‘ Image

Makeup(Lora)

πŸ‘ Image

Text Style Reference(Lora)(More Cases)

πŸ‘ Image

πŸ† 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 dimensionsβ€”a distinction further corroborated by human evaluations highlighting its superior prompt following and visual consistency.

πŸ‘ Image

Downloads last month
20,668

Model tree for FireRedTeam/FireRed-Image-Edit-1.1

Adapters
6 models
Finetunes
5 models
Quantizations
3 models

Spaces using FireRedTeam/FireRed-Image-Edit-1.1 100

Collection including FireRedTeam/FireRed-Image-Edit-1.1

Paper for FireRedTeam/FireRed-Image-Edit-1.1