Welcome to my 💫🌄 Friendly Flux 2 Klein UniEdit

✨ Less mess, more magic and control

I offer my workflow that requires at least 8GB of video memory and at least 32GB of RAM. No Tritons or SageAttention! Simply configure the required amount of video memory dumped to RAM in the "VRAM Optimizer+" node.

This is unique workflow with Edit & Inpaint modes that supports up to 5 images. Edit everything you want, restore old photos, face swap now is easy, qualitative and super fast!

The latest version of ComfyUI is required.

The FLUX.2 [klein] model family are our fastest image models to date. FLUX.2 [klein] unifies generation and editing in a single compact architecture, delivering state-of-the-art quality with end-to-end inference in as low as under a second. Built for applications that require real-time image generation without sacrificing quality.

FLUX.2 [klein] 9B is a 9 billion parameter rectified flow transformer capable of generating images from text descriptions and supports multi-reference editing capabilities.

Matches or exceeds models 5x its size—in under half a second. Built on a 9B flow model with 8B Qwen3 text embedder, step-distilled to 4 inference steps.

💻 System requirements:

• Minimum system requirements:

RTX 3000-s, 8GB+ VRAM, 32GB+ RAM, 8-core processor, SSD, latest ComfyUI

📌 Detailed tips and links to models in the workflow

✨ Workflow features:

• Extremely user-friendly interface

• Maximum performance even on low-end systems with at least 8GB of VRAM

• Support for up to 5 images

• Unique Edit & Inpaint modes

• Enchance details parameter

• Color correction parameters

• Support for up to 3 Lora

• Detailed tooltips

• Manual random seed for complete control over generations

🤗🙏🏼 Thanks to Black Forest Labs Team

Original repo — GitHub