FLUX.2 Klein 9B: Text to Image

ABOUT THE WORKFLOW

Text to Image Type a prompt describing the image you want, and the model generates it. That's it.

Open weights, so you only pay for generation time. All models pre-loaded on Floyo.

Model

• FLUX.2 Klein 9B by Black Forest Labs. An open-weight image model known for sharp detail and strong prompt following.

HOW IT WORKS

Step 1. Write your prompt Describe the image, the style, the lighting, and the composition. Klein 9B follows detailed prompts well, so the more specific you are, the closer the result. Works great with: photorealism · detailed scenes · concept art · product shots

Step 2. Set a negative prompt (optional) List what to keep out of the image, like "blurry, bad quality," to clean up the result.

Step 3. Hit run and download You get back a 1024px image in a few steps. Preview it in the workflow, then download. Ready for: Photoshop · Figma · Canva · any editor

First time? Leave every setting as-is. The defaults (1024 x 1024 · 20 steps · CFG 5) are the right starting point for almost everyone.

RECOMMENDED SETTINGS

Quick-start guide. Find the goal that matches yours and copy the settings.

• Standard generation (most people) ★ Start here — 1024 x 1024 · 20 steps · CFG 5. The right starting point for almost everyone.

• The prompt is not being followed closely — Raise the CFG toward 6 to 7. Higher sticks closer to your text, though too high can look harsh.

• Want a softer, more natural look — Lower the CFG toward 3 to 4 for a gentler result.

• Use a negative prompt — List what to avoid, like blur or artifacts, to clean up the output.

• Going for a specific style — Describe it plainly. Klein 9B handles photorealism and a range of styles, so style cues land.

• Want the cleanest detail — Keep the steps at 20. Klein 9B is sharp at the default, so there is little need to push higher.

• Reproduce a result you liked — Lock the seed to the number that produced it.

Prompt: Write detailed, natural descriptions. Name the subject, the lighting, and the composition. Klein 9B uses a Qwen3 text encoder and follows long prompts well, so specifics pay off more than a short keyword list.

USE CASES

🎨 Photorealism & Detail Generate sharp, realistic images and detailed scenes from a prompt.

🖼️ Concept & Art Produce concept art and a range of styles, not only photoreal.

🛍️ Product & Marketing Make clean product shots and design references with strong detail.

⚡ Fast Generation A few steps per image keeps iteration quick when you are exploring ideas.

WHAT WORKS BEST / WHAT TO AVOID

✅ Works great

• Detailed, natural-language prompts

• Photorealistic and stylized scenes

• Prompts with lighting and composition

• A negative prompt to clean up artifacts

⚠️ May produce softer results

• Short or vague prompts

• Dense in-image text

• CFG pushed too high

• Crowded multi-subject scenes

LEARN

📹 Videos

• Intro to Floyo

• ComfyUI 101 Free Course ft. Sebastian Kamph

• Floyo 101 for Team Collaboration

✨ Quick links

• Help docs

• LoRA Training guide

• Discover more workflows

FAQ

What is FLUX.2 Klein 9B? FLUX.2 Klein 9B is a fast open-weight image model from Black Forest Labs, part of the FLUX.2 family. It is a 9-billion parameter model that unifies generation and editing, using an 8B Qwen3 text embedder, and it is known for sharp detail and close prompt adherence. In this workflow it runs as text-to-image, so you type a prompt and get a finished image.

What settings should I use for text-to-image? Use 1024 x 1024 resolution, 20 steps, and CFG 5 with the euler sampler. Raise the CFG toward 6 or 7 when you want the prompt followed more strictly, and lower it toward 3 or 4 for a softer look. Add a negative prompt to keep out blur and artifacts.

Does FLUX.2 Klein render text well? Text is not its strength. Black Forest Labs notes that rendered text can be inaccurate or distorted, so for images that depend on clean, legible typography, a dedicated text-rendering model such as Seedream 4.5 will give better results.

How is this different from the Klein 9B editing workflows? This workflow generates an image from text alone, with no input image. The other Klein 9B workflows start from an image you upload: prompt-based editing, inpainting a masked area, and realism enhancement. Use this one to create from scratch, and the editing workflows to change an existing image.

Can I use the results commercially? Be careful here. FLUX.2 Klein 9B is released under the FLUX Non-Commercial License, and only the smaller 4B Klein models are Apache 2.0, so commercial use of the 9B model requires a separate license from Black Forest Labs at bfl.ai/licensing. Review the license before using it commercially.

How to run FLUX.2 Klein 9B online? You can run FLUX.2 Klein 9B online through Floyo. No installation, no setup, no GPU to rent. Open the workflow in your browser, write a prompt, and hit run. Free to try.

WHY FLOYO?

Floyo is the only platform with team collaboration for ComfyUI in the browser. You run workflows with no install. You share run history, assets, and models across your team. You pay only when you generate. Floyo supports open-source and closed-source models.

A designer runs a prompt and likes the result. A teammate opens that exact run from shared history and keeps going. No file handoffs. No version confusion.

For studios and enterprise teams, Floyo adds private workspaces, pooled resources, and a team usage dashboard. Other ComfyUI cloud tools run for one person at a time. Floyo runs for the whole team, with transparent per-generation costs.

Ready to try it? Type your first prompt and run it. The settings are already set.

→ Launch Workflow, Free

Questions? Watch the free course or check the FAQ above.