FLUX.2 [flex]

FLUX.2 [flex]

black-forest-labs/FLUX.2-flex

About FLUX.2 [flex]

FLUX.2 Flex is a versatile, parameter-tunable image generation and editing model that inherits the technical advantages of the FLUX.2 series, supporting natural language prompts, multi-reference image input, and granular parameter adjustments. It delivers optimized text rendering accuracy, adaptive detail fidelity, and flexible speed-quality tradeoffs, making it ideal for UI/UX design, brand asset creation, high-precision infographics, and iterative creative prototyping. It enables step-adjustable generation (6-50 steps), hex color value restoration, and context-aware style alignment, empowering creators to balance efficiency and precision, turning rapid drafts into polished, production-ready visuals with tailored control.

Available Serverless

Run queries immediately, pay only for usage

$

0.06

Per Image

Metadata

Create on

Dec 11, 2025

License

Provider

Black Forest Labs

HuggingFace

Specification

State

Available

Architecture

Calibrated

No

Mixture of Experts

No

Total Parameters

32B

Activated Parameters

Reasoning

No

Precision

FP8

Context length

0K

Max Tokens

Supported Functionality

Serverless

Supported

Serverless LoRA

Not supported

Fine-tuning

Not supported

Embeddings

Not supported

Rerankers

Not supported

Support image input

Not supported

JSON Mode

Not supported

Structured Outputs

Not supported

Tools

Not supported

Fim Completion

Not supported

Chat Prefix Completion

Not supported

SiliconFlow Service

Comprehensive solutions to deploy and scale your AI applications with maximum flexibility

60%

lower latency

2x

higher throughput

65%

cost savings

Model FAQs: Usage, Deployment

Learn how to use, fine-tune, and deploy this model with ease.

Ready to accelerate your AI development?

Ready to accelerate your AI development?

Ready to accelerate your AI development?