首頁 › FLUX
FLUX Prompts
FLUX is the image model family from Black Forest Labs (FLUX.1 schnell/dev/pro through FLUX.2), known for strong prompt adherence, realistic rendering and reliable in-image text — and hugely popular in ComfyUI. Below are prompt examples that work well with FLUX, filterable by scene. FLUX responds well to full natural-language descriptions, so be specific about lighting, lens and materials.
Product 奢華香水瓶棚拍
Product 漂浮花瓣面霜罐
Product 球鞋潑濺動態拍攝
Product 奢華腕錶微距棚拍
Product 無線耳機漂浮概念
Product 汽水罐冰塊飛濺
Product 保養精華滴管瓶
Product 鑽戒珠寶微距拍攝
Product 煙霧中漂浮的智慧型手機
Product 高級包裝盒棚拍展示
Product 智慧手錶主打棚拍
Product 智慧手錶生活風格細節微距
Product 球鞋漂浮主打棚拍
Product 高級皮革球鞋棚拍
Product 無線耳機充電盒棚拍
Product 耳罩式耳機漂浮主打
Product 香水瓶水花主打
Product 黑底琥珀香水潑濺
Product 保養精華滴管棚拍
Product 精華瓶漂浮潑濺
Product 設計師太陽眼鏡主打棚拍
Product 反光表面上的太陽眼鏡
Product 無反相機主打棚拍
Product 復古相機漂浮展示
FAQ
How do FLUX prompts differ from SD prompts?
FLUX prefers coherent natural-language descriptions over stacked quality tags. Write the scene as a fluent paragraph covering subject, lighting, lens and composition; SD-style weighting syntax may not apply.
Does FLUX need negative prompts?
FLUX.1 dev/schnell typically runs without negative prompts (CFG-distilled). A clear positive description matters more; follow your ComfyUI workflow settings where applicable.
Which FLUX version do these prompts target?
They are generic across FLUX.1 and FLUX.2. Detail and text rendering vary by version, so tweak based on output.