How to Use FLUX.2 [flex]
Make an FLUX.2 [flex] image in the CheaperGen Studio — no code, no install, no Black Forest Labs account. Pick a mode, write one clear prompt, set the size and press Generate. A test costs $0.046; developers can follow the API tutorial instead.
- Modes
- 1
- Text → Image
- Test image
- $0.046
- 1 MP
- Sizes
- up to 4 MP
- 4 options
- Failed runs
- $0
- refunded automatically
Prompt builder
Build a FLUX.2 [flex] prompt
Fill in the parts of the shot; the prompt assembles itself. Send it to the playground below and run it — the steps after it explain each part.
Your FLUX.2 [flex] prompt
Fill in a few boxes — or start from the example — and the prompt appears here.
Try it
Try FLUX.2 [flex] here
Runs on your balance at the price on the button; failed runs are refunded. Results are saved to your account.
Before you start
Which FLUX.2 [flex] mode to use
FLUX.2 [flex] has 1 mode. Pick by what you already have.
| Mode | You give it | Best for | From |
|---|---|---|---|
| Text → Image | A prompt | Images from a description: concepts, illustrations, ad visuals. | $0.046/image |
Step by step
How to use FLUX.2 [flex] in 6 steps
- 1
Open FLUX.2 [flex] in the Studio
Open the Studio (it opens with FLUX.2 [flex] selected), or choose the Image tab and pick FLUX.2 [flex] in the model menu. Sign in with Google or your email; you pay per generation from prepaid credits.
- 2
Choose what to make
- Text → Image — a prompt.
- 3
Write the prompt
One shot per prompt works best. Cover these, in plain sentences:
- Subject. The main subject and its key details: material, colour, expression, product features.
- Composition. Framing and angle: close-up, flat lay, three-quarter view, rule of thirds, negative space.
- Setting and light. Background, environment and lighting: studio softbox, golden hour, neon.
- Style. Photo, illustration, 3D render or painting — plus lens or medium details.
More structure and examples: the FLUX.2 [flex] prompt guide.
- 4
Set the options
The settings sit under the prompt; rarely needed ones are behind ⋯. What each does — and to the price — is in the table below.
- 5
Generate
The exact price is shown before you run: press Generate (or ⌘/Ctrl + Enter). The amount is held from your balance and refunded in full if the generation fails.
- 6
Download and iterate
Results appear above the prompt; download them from there. Change one thing per try — the prompt, the composition or a setting — so you know what helped. Compare runs the same prompt on several models side by side, and Code shows the same request for the API.
Settings
FLUX.2 [flex] settings explained
For Text → Image. Prices are per image.
| Setting | Choices | Default | What it does | Price |
|---|---|---|---|---|
| Aspect ratio | 1:1, 4:3, 3:4, 16:9, 9:16, 3:2, 2:3, 21:9, 9:21 | 1:1 | Output image shape. | Changes the price |
| Resolution | 1 MP, 2 MP, 3 MP, 4 MP | 1 MP | Output size in megapixels (1 MP ≈ 1024×1024). FLUX.2 is billed per megapixel. | $0.046–$0.1364/image |
| Steps(⋯) | 1–50 | 50 | Sampling steps. More steps add detail and take longer (same price). | No effect on the price |
| Guidance(⋯) | 1.5–10 | 5 | How closely the image follows the prompt (1.5–10). | No effect on the price |
| Prompt upsampling(⋯) | On / off | Off | Let the model expand and rewrite the prompt before generating. | No effect on the price |
| Seed(⋯) | Free text | — | Use the same seed and settings to reproduce a result. Leave empty for random. | No effect on the price |
Every tier and a calculator: FLUX.2 [flex] API Pricing.
Worked example
A first prompt to try
Text → Image with the default settings. Paste it into the Studio and change one thing at a time.
“Vintage travel poster for “KYOTO”, Mt. Fuji at dawn, bold serif lettering, screen-print texture”
Aspect ratio: 1:1 · Resolution: 1 MP
$0.046$0.05 for this image
Try it in the StudioAvoid these
Common FLUX.2 [flex] mistakes
Drafting at 4 MP
Every try at 4 MP costs 3.0× one at 1 MP. Settle the composition and motion at 1 MP, then render the keeper at the size you deliver.
Describing what you don't want
Prompts work better when they describe what should be on screen. "No blur" or "no extra fingers" can pull the result towards the very thing you name.
FAQ
How to use FLUX.2 [flex]: questions
FLUX.2 [flex] is developed by Black Forest Labs. CheaperGen provides API access and does not own the model. Trademarks belong to their respective owners.
