Flux 2
imageBlack Forest Labs' FLUX.2 [flex] stills model, labeled Flux 2. The same kind of photograph as Flux 2 Pro, with their control-oriented model.
What it supports
- Aspect ratios
- 1:1, 4:3, 3:4, 16:9, 9:16, 3:2, 2:3
- Resolutions
- 1K, 2K
- Per request
- up to 4
What it costs
- 1K
- 10 credits
- 2K
- 16 credits
Credits come with a Generator plan. The exact cost is shown on the Generate button before anything is spent.
Flux 2 is Black Forest Labs' FLUX.2 [flex] stills model. It is not a setting on Flux 2 Pro, and it is not Flux 3.
What it is good at
Black Forest Labs describes [flex] as the FLUX.2 model that gives you more control, and the one that excels at type and fine detail. Use it for a still you can afford to try again, especially when words in the picture have to read.
How to use it on Visxy
Write the picture in the prompt. To edit or combine pictures, attach one to four of them and name them @image1, @image2, @image3, and @image4 in the prompt.
Where it differs
Flux 2 Pro is the production-quality FLUX.2 model. Flux 2 is the control-oriented sibling. Flux 3 makes a clip with sound. The way you attach pictures is the same on Flux 2 and Flux 2 Pro.
FAQ
Why is it called Flux 2 if the maker says flex?
Black Forest Labs' name is FLUX.2 [flex]. On Visxy the name is Flux 2, so it is not confused with Flux 2 Pro.
Who makes it?
Black Forest Labs. On Visxy this model is labeled Flux 2. Flux 2 Pro is the production sibling.
Can I edit?
Yes. One to four pictures, named @image1 onward.
When do I move to Pro?
When the still has to look like a finished photograph of a real surface, Black Forest Labs points you at [pro].
Official sources
More image models
All image modelsIdeogram 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.
Grok Imagine
xAI's earlier Grok image model. Speed or quality, two pictures each time, and an editor that takes up to four pictures you can name.
Nano Banana 2.1
Google's newer Gemini image model, an update of Nano Banana 2. Sharper pictures and type, still a prompt plus up to four pictures you name.
Imagen 4
Google's Imagen 4 text-to-image model. Fine detail and readable type, from a prompt alone. It does not take a picture to edit.
Imagen 4 Fast
Google's fast Imagen 4. A text-to-image picture when you want the idea quickly. It does not take a picture to edit.