Black Forest Labs 推出全新開源影像生成模型 FLUX.1：Replicate 已支援 API 運行
Original: Run FLUX with an API
Black Forest Labs — a new AI team founded by the original creators of Stable Diffusion (including core developer Robin Rombach and others)…
由 Stable Diffusion 核心團隊創立的 Black Forest Labs 發表了全新文字生成圖片模型 FLUX.1。該模型擁有 120 億參數，在文字渲染、細節描繪與指令遵循上皆超越現有開源模型。Replicate 已同步上架 FLUX.1 的 schnell、dev 與 pro 三種版本，開發者可直接透過 API 進行整合與部署。
Black Forest Labs — a new AI team founded by the original creators of Stable Diffusion (including core developer Robin Rombach and others) — has officially launched a next-generation open-source text-to-image model family called "FLUX.1." This model is widely regarded as surpassing existing open-source models (such as Stable Diffusion 3) in image quality, text rendering, complex instruction following, and human anatomy (particularly hand details), and is even considered competitive with top closed-source models like Midjourney v6.
Free shows the 3-line summary; Pro unlocks the full deep summary (~300 words) so you never have to click through.
See Pro plans →Want the original English / full article?
Read on Replicate Blog →Summaries are AI-generated; the original article is authoritative.