FLUX.2 [klein] released, with sub-second inference and open weights

We're excited to announce FLUX.2 [klein] — our fastest model family with sub-second inference.

Key Features

• Sub-second generation — Real-time image generation for interactive applications
• Two variants — 4B from ($0.014 / image) and 9B from ($0.015 / image) models
• Runs on consumer hardware — As little as 13GB VRAM required
• Open weights available — 4B under Apache 2.0, 9B under FLUX Non-Commercial License

API Endpoints

• flux-2-klein-4b — Fastest, ideal for high-volume and local deployment
• flux-2-klein-9b — Balanced quality and speed with 8B Qwen3 text embedder

Download open weights from Hugging Face or get started with the API documentation.