HiAPI
flux-1.1-pro 详情页 Hero 图:21:9 宽幅,左侧为明亮光晕留白,右侧玻璃棱镜浮卡与光轨延展,名号以发光立体字蚀刻于玻璃,冷调蓝青配奶油暖金。

Black Forest Labs

FLUX 1.1 Pro

flux-1.1-pro

Black Forest Labs' flagship text-to-image model, roughly 6 times faster than Flux.1 Pro with better prompt adherence, ideal for image generation at scale

flux-1.1-pro

Try flux-1.1-pro

Input

Output

image
Fill in the parameters and run — results show up here.

Pricing

flux-1.1-pro per image

Unit Price $0.050

Overview

flux-1.1-pro is a production-oriented text-to-image and image-to-image model from Black Forest Labs, which developers can call through the unified HiAPI.ai interface. It supports generating images directly from text prompts, and can also perform image-conditioned generation by attaching a reference image URL; its prompt adherence is strong, making it suitable for business workflows that require stable output of high-quality images. Aspect ratios cover common specifications such as 1:1, 16:9, 3:2, 4:5, and 9:16, and custom sizes are also supported. Output format and quality are adjustable, making it easy to integrate into batch image generation and automated production pipelines.

Key Highlights

  • Dual text-to-image and image-to-image modes — the same interface supports both pure prompt-based generation and image-conditioned generation by passing in a reference image URL, reducing the need to switch between multiple models.
  • Reproducible generation control — supports a fixed seed, so repeated calls yield consistent results, which is convenient for regression testing and reproducing batch tasks.
  • Output parameters adjustable as needed — offers aspect ratio, custom size, webp/jpg/png format, and output quality options to suit different downstream uses.
  • Designed for production workflows — the parameter structure is complete, making it suitable for integration into automated batch image generation and stable delivery business processes.

Capabilities

Text-to-image generation: generates images directly with prompt as the core input, suitable for creative work and asset production starting without source material.

Reference-image-conditioned generation: pass in a jpeg, png, gif, or webp reference image URL via image_prompt to generate based on existing visuals.

Canvas and size control: includes multiple common aspect ratios; when custom is selected, width and height can be set from 256 to 1440 pixels and are aligned to multiples of 32.

Output format and quality: choose webp, jpg, or png output and set output quality from 0 to 100; png output is not affected by the quality parameter.

Reproducible generation and detail adjustment: a fixed seed reproduces results, prompt_upsampling can automatically rewrite prompts, and safety_tolerance can adjust how permissive content filtering is.

Use Cases

  • Batch image generation for marketing and advertising assets — operations and marketing teams input campaign copy and produce promotional images in multiple aspect ratios for ad channels and landing pages.
  • Product visualization scene images — e-commerce teams use product descriptions or reference images as input to generate product scene images for detail pages and presentation materials.
  • Illustration production for content creators — creators input prompts based on article topics and produce illustrations with a consistent style for article content and social media publishing.
  • Visual presentation for design prototypes — designers use concept descriptions or reference images as input to quickly produce visual drafts for proposal discussions and prototype direction confirmation.
  • Image generation nodes in automated workflows — engineering teams integrate the interface into pipelines to stably produce images with fixed parameters and seeds for large-scale content production.

Limitations and Selection Advice

It only outputs static images and does not support video or other modalities; generation results depend on prompt quality, and complex or specific requirements need multiple rounds of tuning. The maximum width and height is 1440 pixels, custom sizes are aligned to 32-pixel multiples, and oversized requirements need to be handled separately. Output quality is mainly adjusted for webp/jpg; the quality parameter does not take effect for png. Lowering the safety tolerance may affect the pass rate of image generation. If a task requires video generation or batch control beyond the scope of a single image, a model with the corresponding modality should be used instead.

Frequently asked questions

View all FAQs →
  • What is FLUX1.1 [pro] best for?

    Generate polished photography, architecture, food, nature, and commercial visuals with custom sizing and prompt upsampling controls.

  • Does FLUX1.1 [pro] accept reference images?

    No. This route is text-to-image only.

  • Which output settings are supported?

    The page exposes Custom width / height and Custom, 1:1, 16:9, 9:16; use the Playground contract for the final available set.

  • How is FLUX1.1 [pro] billed?

    Billing is per successful generated image. Resolution or quality differences, when present, are reflected by the live page price.

Related Models

View all models →

Same Type