lbouaraba GitHub avatar

comfyui-krea2edit

lbouaraba

A ComfyUI node pack that enables instruction-based image editing using Krea 2 with dual conditioning via VAE latent tokens and Qwen3-VL text encoder.

Stars

357

7-day growth

No data

Forks

19

Open issues

8

License

Apache-2.0

Last updated

2026-07-25

AI repository intelligence
FR-AI / ANALYSIS

Why it is worth attention

It provides a practical implementation of identity-preserving image editing through a LoRA, with detailed control over reference fidelity and grounding resolution, and includes community-validated workflows.

Who it is for

  • ComfyUI users
  • AI image editing enthusiasts
  • Developers working with Krea 2
  • Researchers in identity-preserving generation

Use cases

  • Editing images by instruction (e.g., recolor car to matte black)
  • Inserting subjects into new scenes with identity preservation
  • Swapping faces or persons (with v1.2)
  • Making scene translations

Strengths

  • Dual conditioning for better adherence to source image
  • Adjustable ref_boost and grounding_px for fine control
  • Supports both single and two-image edits
  • Active community contributions and detailed usage notes

Considerations

  • Requires specific model and LoRA weights (Krea 2, Qwen3-VL, identity edit LoRA)
  • Generation limited to ≤2MP to avoid artifacts
  • Removal edits need higher CFG and Raw model; two distinct people still imperfect

README quick start

Installation

Description

Instruction-based, identity-preserving image editing for Krea 2 in ComfyUI — nodes + workflows for the Krea 2 Identity Edit LoRA

Related repositories

Similar projects matched by category, topics, and programming language.

lopopolo
Featured
lopopolo GitHub avatar

harness-engineering

Harness Engineering is a methodology for improving coding agent outputs by carefully crafting the environment around them—providing curated context, tools, and executable constraints that encode an organization’s nonfunctional requirements and cumulative lessons.

AI & Machine LearningAI Agents
2,390
slvDev
Featured
slvDev GitHub avatar

esp32-ai

A 28.9 million parameter language model runs on an $8 ESP32-S3 microcontroller entirely on-device, generating simple stories at about 9.5 tokens per second.

AI & Machine LearningLarge Language Models
1,960
littledivy
Featured
littledivy GitHub avatar

mimic

mimic captures traffic from any iOS or web app and automatically generates a Python client library that lets you call the app's API like a regular library.

AI & Machine Learning
1,482