Black Forest Labs image model
Flux 3 image AI Image Generator
Structured, material-true images from 768 square to 4K, guided by up to ten references.
Prompt length 0
At a glance
- Provider
- Black Forest Labs
- Best for
- Product concepts, portrait direction, and multi-reference edits.
- Sizes
- 768SQ, 1K, 1.5K, 2K, 4K
- Reference images
- Up to 10
- Price
- 10 Credits at default settings
Character
Flux 3 image is the current image model in the Flux line: one image per run, a wide set of frames, and sizes from a 768SQ study through 4K.
Flux 3 image keeps the family’s interest in structure and materials, then gives the frame a real range of sizes. 768SQ is the small study. 1K is the usual start. 1.5K and 2K are the working sizes, and 4K is the large delivery. Each run makes one image.
Text to Image starts from the sentence. Image to Image starts from up to ten references of a product, a face, a material, or a layout. The prompt says which image does which job, and the picture has to respect that.
Style
How Flux 3 image tends to see a picture.
Structural clarity
Perspective, edges, and object boundaries stay legible.
Material truth
Surfaces look like substances. Name the material, not only the color.
Commercial calm
Light stays controlled. The picture can sit in a catalog or an architecture board.
Reference discipline
Several sources can agree when the prompt says how they agree.
In practice
The work this model is built to carry.
Product concepts
Objects with believable form, on a ground you specify.
Portrait direction
Faces and styling with a controlled setup.
Commercial visuals
Clean campaign and catalog frames.
Multi-reference edits
A picture built from several sources, up to ten.
Briefing
Describe construction. Camera height, what the material is, and where the key light sits. Flux uses those facts.
Look at 1K while you are choosing. Move up only when the structure is the one you will keep. Give each reference a role before you add another.
Start at 1K
Confirm the structure at 1K. 768SQ is the smaller study. 4K is the large delivery, so go there when the picture is the one you want.
One image per run
Change the prompt or the references, then run again for the next image.
Assign the references
Say what each image is for. Ten is the limit. The useful number is however many have a job.
How Flux 3 image compares
Not sure it is the right pick? Here is when another model is the better start.
- Flux.2 Pro
Choose Flux.2 Pro for crisp 1K or 2K images, with up to eight references on Image to Image.
- Flux.2 Flex
Choose Flux.2 Flex when the composition is known and the remaining question is precision.
- Flux.1 [schnell]
Choose Flux.1 [schnell] for fast text-to-image drafts and composition studies.
Flux 3 image FAQ
Flux 3 image is the current image model in the Flux line on image.cooking: one image per run, a wide set of frames, and sizes from a 768SQ study through 4K. It keeps the family’s interest in structure and materials.
Up to ten, and each can carry a role: a product, a face, a material, or a layout. Say in the prompt what each image is for. The useful number is however many have a job.
768SQ is the small study and 1K is the usual start. 1.5K and 2K are the working sizes, and 4K is the large delivery.
Flux 3 image adds 768SQ, 1.5K, and 4K and takes up to ten references. Flux.2 Pro makes crisp 1K or 2K images with up to eight references. Flux.1 [schnell] is text to image only, for fast drafts.
The price depends on the resolution, the number of outputs, and whether you use a reference image. At default settings, Flux 3 image costs 10 Credits. Create always shows the exact price before you start.
Yes. Images generated while a paid kitchen is in force include commercial use, including through the end of a period you already paid for. That permission stays with those images after the kitchen ends, subject to our Terms. Images generated with starter Credits, or while no paid kitchen is in force, are for personal, non-commercial use. See Pricing.
More in the Flux family
Same family, different jobs. Pick by the work in front of you.
- Flux.2 Pro
Crisp commercial images with convincing form, readable materials and up to 8 references.
- Flux.2 Flex
The closer Flux 2 pass for product and architecture, when the composition is already set.
- Flux.1 [schnell]
Sketch the composition fast, text only, then take the winner to Flux.2.
Cook with Flux 3 image
Create opens on this model. Write the prompt, set the frame, and keep the image on your private shelf.
Create with this modelFlux 3 image is a model made by Black Forest Labs. Model names and logos belong to their owners, and image.cooking is not affiliated with or endorsed by them.
Cook with something else.
Every model opens in the same workspace, with the same prompt box. Nothing to relearn when you switch.
OpenAI
Nano Banana ProBold color, finished for publication: faces, fabrics and fine detail hold up close.
- Nano Banana 2.1
Nano Banana color in extreme frames, from 1:8 tall strips to 8:1 banners.
- Nano Banana 2
The main Nano Banana for imaginative scenes, product stories and social frames.
- Nano Banana 2 Lite
The sketchbook Nano Banana: try ideas fast, then finish the winner on 2 or Pro.
- Nano Banana
The original Nano Banana: playful ideas, made to look intentional.
ByteDance
Seedream 5.0 ProArt-directed Seedream frames, finished rather than explored.
- Seedream 5.0 Flash
Quick art-directed Seedream frames for fashion and campaign looks, 1K to 2K.
- Seedream 5.0 Lite
The everyday Seedream: art-directed images from 2K to 4K, built for exploring.
- Seedream 4.5
Staged, atmospheric fashion and editorial scenes with the Seedream 4.5 grade, at 2K or 4K.
xAI
