Flux 3 Klein
imageBlack Forest Labs' FLUX.3 Klein. A still from a prompt, or an edit of up to four pictures, at 1K, 2K, or 4K.
Other versions
What it supports
- Aspect ratios
- 1:1, 4:3, 3:4, 3:2, 2:3, 16:9, 9:16, 21:9, 9:21
- Resolutions
- 1K, 2K, 4K
- Per request
- up to 4
- Prompt enhance
- Supported
What it costs
- 1K
- 2 credits
- 2K
- 3 credits
- 4K
- 7 credits
Credits come with a Generator plan. The exact cost is shown on the Generate button before anything is spent.
Flux 3 Klein is Black Forest Labs' compact FLUX 3 image model. It is its own model, not a setting on Flux 2 or Flux 2 Pro, and it is not Flux 3, which makes video.
What it is good at
Black Forest Labs describes Klein as the fast, compact member of FLUX 3 Image: a still from a prompt, or an edit that can follow several pictures at once. On Visxy that is up to four pictures.
How to use it on Visxy
Write the picture. To edit, attach one to four pictures and name them @image1, @image2, @image3, and @image4 in the prompt. Choose 1K, 2K, or 4K.
Enhance starts off. Turn it on to expand the prompt. Black Forest Labs trains Klein on those expanded captions, and a prompt sent as written is the weaker of the two.
Where it differs
Flux 2 and Flux 2 Pro are the previous FLUX.2 stills models. Flux 3 Klein is the newer, smaller image model, and the one that reaches 4K here. Flux 3 is a video model.
FAQ
Can I edit a picture with it?
Yes. Attach one to four pictures and name them @image1 onward in the prompt.
What resolution can I get?
1K, 2K, or 4K.
Should I turn Enhance on?
Black Forest Labs trains Klein on expanded captions. Enhance starts off; turn it on when you want that expansion.
Who makes it?
Black Forest Labs.
Official sources
More image models
All image modelsGrok Imagine Image Quality
xAI's Grok Imagine image model at the Quality tier. A still at 1K or 2K, or an edit of up to three pictures.
Ideogram V3
Ideogram's image model for readable type, posters, and photoreal frames. Pick a rendering speed, and remix one picture when you already have it.
Grok Imagine 2.0
xAI's current Grok image model. A picture from a prompt, or an edit of one to four pictures on Grok Imagine 2.0 Edit.
Krea 3
Krea 3 makes a still from a prompt, in one of six frame sizes. There is no editor. The price follows the size you pick.
Higgsfield Qwen Image 3
Alibaba's Qwen Image 3 as Higgsfield serves it. A still at 1K or 2K, ten frames, and an edit of up to three pictures. Enhance is off until you turn it on.
Recraft V4.1 Pro
Recraft V4.1 Pro. An image from a prompt, at 2k, with no picture to attach.