Flux 模型

FLUX 3 - Real World Models: Towards Multimodal Flow Models as the Backbone of Visual Intelligence.

FLUX.2 [max] is a top-tier visual-intelligence model from Black Forest Labs (BFL) designed for production workflows: marketing, product photography, e-commerce, creative pipelines, and any application that requires consistent character/product identity, accurate text rendering, and photoreal detail at multi-megapixel resolutions. The architecture is engineered for strong prompt-following, multi-reference fusion (up to ten input images), and grounded generation (ability to incorporate up-to-date web context when producing images).

FLUX 2 FLEX is the versatile, adaptable model designed for flexible deployment across various use cases and hardware configurations. It offers scalable performance with adjustable quality settings, making it ideal for applications requiring dynamic resource allocation. This model provides the best balance between quality, speed, and resource efficiency.

FLUX 2 PRO 是 FLUX 2 series 中的旗艦商用模型，提供最先進的圖像生成，呈現前所未有的品質與細節。為專業與企業級應用而設計，具備卓越的提示遵從度、照片級擬真輸出，以及非凡的藝術表現能力。此模型代表 AI 圖像合成技術的最尖端水準。

探索 flux-pro-finetuned API。

探索 flux-pro-1.1-ultra-finetuned API。

探索 flux-pro-1.1-ultra API。

探索 flux-pro-1.1 API。

探索 flux-pro-1.0-fill-finetuned API。

探索 flux-pro-1.0-fill API。

探索 flux-pro-1.0-depth-finetuned API。

探索 flux-pro-1.0-depth API。

探索 flux-pro-1.0-canny-finetuned API。

探索 flux-pro-1.0-canny API。

探索 flux-pro API。

探索 flux-kontext-pro API。

探索 flux-kontext-max API。

探索 flux-finetune API。

探索 flux-dev API。