Hedra
  • Pricing
Docs
Get started
Hedra
Get started
A tiny clay house perched above a sea of clouds.

Flux.2 [klein] 9B

The lean Flux.2 tier — quick, inexpensive stills for concepting and high-volume work.

Get an API keyTry in Playground
All models

Overview

Flux.2 [klein] 9B is an efficient 9-billion-parameter image generation and editing model developed by Black Forest Labs. Distilled to require only four inference steps, it delivers high-quality text-to-image outputs and multi-reference edits in under a second. The model is best suited for real-time applications, rapid prototyping, and latency-critical workflows, offering a faster alternative to the provider's larger [Flux.2 pro] and [Flux.2 max] models.

Specifications · Text + image to image

Input mode
Text + image to image
Accepts
reference image (up to 4)
Aspect ratios
16:9, 9:16, 4:3, 3:4, 1:1

Pricing

Black Forest Labs
1.1¢/generation
plus 1.1¢ per reference image

Build with this model: the Flux.2 [klein] 9B API on the Hedra Developer Platform.

Flux.2 [klein] 9B API →

Real output · generated with Flux.2 [klein] 9B

Best of Flux.2 [klein] 9B

A tiny clay house perched above a sea of clouds.Clay House Riding a Cloud — Flux.2 [klein] 9BA wide landscape photograph of a serene mountain range during golden hour, perfectly reflected in the glass-like surface of a calm lake. Generated using the Flux.2 [klein] 9B model at 1024x576 resolution, the image captures warm light hitting the rocky peaks against a clear, soft gradient sky.Symmetrical Mountain Reflection — Flux.2 [klein] 9BA photorealistic wide shot of a rustic wooden cabin centered in a dense pine forest, generated by Flux.2 [klein] 9B at 1024x576 resolution. A thin trail of white smoke rises from the chimney into the sunny sky, with tall pine trees casting long shadows on the forest floor.Cozy Wooden Cabin in Pine Forest — Flux.2 [klein] 9BA landscape-oriented text-to-image generation at 1024x576 resolution using Flux.2 [klein] 9B. A young man in a dark trench coat stands on a high-rise balcony looking out at the Tokyo skyline during sunset. The glowing Tokyo Tower and city lights are visible in the background under a warm orange sky.Tokyo Skyline Sunset — Flux.2 [klein] 9BA powerful, translucent turquoise ocean wave crests and begins to break under a dramatic, cloudy sky at sunset. The sun shines through the mist and spray of the wave, creating a golden glow. Generated by Flux.2 [klein] 9B at 1024x576 resolution.Cresting Ocean Wave at Sunset — Flux.2 [klein] 9B

Prompting

Prompt tips

  • Write Descriptive Prose: Structure prompts like a novelist rather than a search engine. Define the subject first, followed by the environment, style, and technical lighting details.
  • Keep Steps Low: Because the model is step-distilled, it is optimized for exactly 4 inference steps. Pushing the step count higher wastes compute time without improving the output.
  • Leverage Multi-Image Inputs: Use its native multi-reference capabilities by feeding it 2–4 reference images to blend characters, clothing, and styles directly in the prompt.
  • Use KV Caching for Edits: When doing reference-based editing, enable KV caching in your workflow to maintain the logic of the original scene and prevent structural drift.
  • Consider Base Models for Complex Needs: If you need higher output diversity or want to train custom LoRAs, consider stepping up to the undistilled [Flux.2 pro] or [Flux.2 max].

About the model

Questions, answered

What is Flux.2 [klein] 9B best for?

Flux.2 [klein] 9B is Black Forest Labs' flagship compact model, designed for interactive, real-time workflows. It unifies text-to-image generation and multi-reference image editing into a single architecture. The community praises its ability to deliver production-quality photorealism, typography, and character consistency at sub-second speeds. It is highly recommended for rapid prototyping, product marketing assets, and workflows requiring instant visual feedback.

When was Flux.2 [klein] 9B released, and what is its lineage?

Released on January 15, 2026, by Black Forest Labs, this 9-billion parameter distilled rectified flow transformer is the higher-fidelity sibling to the 4B variant. It is part of the broader FLUX.2 family, which succeeded the FLUX.1 generation (such as Flux 1.1 Pro and Flux 1.1 Ultra). The FLUX.2 lineup also includes larger models like [Flux.2 pro], [Flux.2 max], and [Flux.2 flex].

How can I get the best results with Flux.2 [klein] 9B?

Because it is a step-distilled model, you only need 4 inference steps with a Guidance (CFG) scale of 1.0. For prompting, write like a novelist: describe your subject first, followed by the environment, details, and lighting. The model natively supports exact HEX color codes (e.g., #FFB400) and structured JSON prompts for precise layout control. For advanced techniques, consult the official prompting guide.

Same API · one key

Similar models

An over-the-shoulder shot of an artist's hand sketching a pencil portrait of a man with glasses on cream paper. The wooden desk is cluttered with pencils and a ceramic mug under warm morning sunlight. Generated using Flux Kontext Max at 1392x752 resolution.Flux Kontext MaxBlack Forest LabsThe same headphones moved into a moss garden.Flux Kontext ProBlack Forest LabsA high-resolution 1024x576 text-to-image generation using the Flux.2 [flex] model. A colossal orange tabby cat with its mouth wide open floats in deep space next to a small, glowing planet Earth. The background features colorful pink and teal nebulas and a distant spiral galaxy.Flux.2 [flex]Black Forest LabsA turquoise glacial river winds through Arctic tundra toward snow-dusted granite peaks at dawn.Flux.2 [max]Black Forest LabsA silver car and reflective architecture, reframed wide.Flux.2 [pro]Black Forest LabsA white buttercream cake decorated with vibrant purple, yellow, and pink edible flowers sits on a white ceramic stand. The image is a text-to-image generation using the GPT Image 2 Low model at 1280x720 resolution, showcasing a bright, softly blurred kitchen background.GPT Image 2 LowOpenAI

Build with Hedra

Get an API keyTry in Playground

Research expertise and GPU infrastructure for models you own.

© 2026 Hedra

Products

  • Inference
  • Model training
  • GPU Sandboxes
  • World Model Runtime
  • Pricing

Deployment

  • Deployment options
  • Sovereign deployment

Model Factory

  • Overview
  • Forward Deployed Researchers
  • Enterprise

Research

  • Overview
  • Recursive self-improvement
  • Mechanistic interpretability
  • Post-training
  • Inference
  • Blog

Applications

  • Physical AI
  • Defense
  • Media generation

Developers

  • Platform onboarding
  • SDKs & integrations
  • Documentation
  • Model APIs
  • MCP & CLI
  • Changelog

Company

  • About Hedra
  • Manifesto
  • Careers
  • Contact
  • Play
  • Play pricing
  • Play help
  • Status
  • LinkedIn
  • X
  • GitHub
  • Discord
  • Privacy Policy
  • Terms of Use
  • Acceptable Use
  • Cookie Policy
  • Biometric Data Policy
  • Security