Black Friday Annual Sale!Get 50% offClaim Now→





Have a different question and can’t find the answer you’re looking for? Reach out to our support team by sending us an email and we’ll get back to you as soon as we can.
Flux 2 Flex is Black Forest Labs' lightweight, fast-running model for high-quality image generation and editing. It balances speed and quality with adjustable inference steps and supports up to 10 reference images.
Adjustable quality steps for speed/fidelity trade-off, fine-tuned guidance scale, multi-reference editing with up to 10 images, excellent text rendering, JSON-structured prompts for precise control, and 1024×1024 PNG output.
Use positive constraints only. Good: 'A close-up portrait of a woman wearing a blue dress, clean background.' Bad: 'portrait, --no text, --no extra fingers.' The model ignores negative prompts.
Choose how many inference steps to run. Fewer steps mean faster results, more steps mean higher fidelity. This lets you balance speed and quality based on your needs.
Upload up to 10 reference images (total ≤ 14 MB) for style transfer, inpainting, or compositing. The model maintains consistency across references for cohesive results.
Structure prompts as JSON with keys like scene, subjects, style, lighting, and camera. This gives precise control over composition. Plain text works too for quick iterations.
Accepts PNG or JPEG inputs. Outputs 1024×1024 PNG images. The model excels at lettering, captions, infographics, and clean typography in generated images.
Yes. Free credits are included for new users. Buy additional credits or subscribe for more usage. Unused credits don't expire, and failed jobs are auto-refunded. See Pricing for model plans.