Hugging Face 推出 Modular Diffusers：為擴散模型管線打造的可組合模組化積木★ 78
Hugging Face Blog101 days agoReleaseThe Hugging Face official blog has announced the launch of "Modular Diffusers" — a major architectural overhaul of its widely popular `diffusers` library. In…
Google DeepMind 推出 Nano Banana 2：結合 Pro 級功能與閃電般速度的全新圖像生成模型★ 70
Google DeepMind Blog108 days agoReleaseGoogle DeepMind has officially released its latest image generation model, "Nano Banana 2." The core breakthrough of this model lies in its successful…
如何為 Seedream 5.0 撰寫 Prompt：掌握多步驟推理與範例編輯的新一代影像生成技術★ 75
Replicate Blog110 days agoTutorialReplicate recently published a prompt-writing guide for the new image generation model Seedream 5.0. Seedream 5.0 introduces three revolutionary features to…
Recraft V4 登陸 Replicate：具備「設計品味」的圖像與可編輯 SVG 生成模型★ 75
Replicate Blog116 days agoReleaseThe AI image generation space has welcomed a powerful new tool built specifically for designers and creative professionals. Replicate, the well-known AI…
Vercel AI Gateway 正式支援 Recraft V4 圖像與向量圖生成模型
Vercel Changelog117 days agoReleaseOn February 17, 2026, Vercel announced in its changelog that its AI Gateway officially supports the Recraft V4 model. This update provides developers with more…
Vercel AI Gateway 正式支援 Recraft 圖像生成模型
Vercel Changelog146 days agoReleaseVercel has announced in its official update log that its AI Gateway service now officially supports Recraft's image generation models. Recraft is an AI image…
Pixel Portraits：Vercel 推出 AI 驅動的像素風交易卡牌生成器
Vercel Changelog173 days agoRelease### Project Overview Vercel's official blog introduced a new open-source project called "Pixel Portraits." This is a fun application that demonstrates how to…
FLUX.2 Pro 影像生成模型現已支援 Vercel AI Gateway★ 70
Vercel Changelog201 days agoReleaseVercel has announced in its Changelog that the latest image generation model FLUX.2 Pro is now officially available on Vercel AI Gateway. This update provides…
FLUX.2 正式上架 Replicate：支援多重參考與專業級圖像生成★ 80
Replicate Blog201 days agoReleaseThe cloud AI hosting platform Replicate has officially announced support for FLUX.2, the next-generation image generation model developed by Black Forest Labs…
Diffusers 正式支援 FLUX-2：下一代開源圖像生成模型降臨★ 85
Hugging Face Blog201 days agoReleaseThe Hugging Face official blog has announced that the popular diffusion model library `diffusers` now officially supports FLUX-2, the next-generation…
Google DeepMind 將 AI 圖像驗證技術（SynthID）導入 Gemini 應用程式★ 80
Google DeepMind Blog206 days agoReleaseWith the rapid advancement of generative AI technology, identifying the authenticity of images and defending against deepfakes has become an urgent priority…
Google DeepMind 發表 Gemini 3 Pro 圖像模型「Nano Banana Pro」：開啟下一代視覺生成與構建★ 78
Google DeepMind Blog206 days agoReleaseGoogle DeepMind has unveiled a new model called "Nano Banana Pro," which is also the Pro-tier image model of the Gemini 3 generation (Gemini 3 Pro Image…
如何為 Nano Banana Pro 撰寫 Prompt：Replicate 影像生成與編輯新模型提示詞指南
Replicate Blog206 days agoTutorialThe official Replicate blog recently published a prompt-writing guide for the new image generation and editing model "Nano Banana Pro." As generative AI…
Retro Diffusion 像素藝術模型正式上架 Replicate：輕鬆生成遊戲素材、角色精靈與地圖瓷磚
Replicate Blog207 days agoNew ToolThe well-known pixel art AI model suite Retro Diffusion has officially launched on the cloud AI hosting platform Replicate. For indie game developers, game…
Gradio 推出視覺化浮水印功能：輕鬆為 AI 生成圖像添加防偽與版權標記
Hugging Face Blog272 days agoReleaseWith the explosive growth of generative AI — particularly in image and multimedia generation — how to identify AI-generated content and protect copyright has…
使用 Claude 與 Hugging Face 產生圖片：透過 MCP 協定無縫整合★ 85
Hugging Face Blog299 days agoNew ToolThe Hugging Face official blog has announced an exciting new integration: through Anthropic's Model Context Protocol (MCP), users can now generate images…
使用 Diffusers 與 PEFT 實現 Flux 的快速 LoRA 推論★ 80
Hugging Face Blog326 days agoTutorialThis technical guide from Hugging Face takes an in-depth look at how to accelerate LoRA (Low-Rank Adaptation) inference for Flux.1, the powerful open-source…
如何生成一致的角色？Replicate 評測主流圖像模型的一致性生成能力★ 75
Replicate Blog328 days agoTutorialIn the field of AI image generation, maintaining visual consistency for the same character across different scenes, actions, and expressions — known as…
Bria 圖像生成與編輯模型正式上架 Replicate，主打 100% 授權數據的安全商業應用
Replicate Blog332 days agoReleaseReplicate has announced a partnership with Bria, officially bringing Bria's suite of commercial-grade image generation and editing models onto the Replicate…
Replicate 如何優化 FLUX.1 Kontext [dev]：深入解析 Taylor Seer 優化技術★ 75
Replicate Blog334 days agoTutorialIn the generative AI space, the FLUX.1 model developed by Black Forest Labs is renowned for its outstanding image quality and text rendering capabilities…
Replicate 與 Black Forest Labs 聯手舉辦 FLUX.1 Kontext 黑客松：探索下一代 AI 圖像生成應用
Replicate Blog348 days agoReleaseCloud AI deployment platform Replicate recently announced that the "FLUX.1 Kontext Hackathon," co-hosted with renowned open-source image generation model…
在消費級硬體上微調 FLUX.1-dev：使用 QLoRA 技術指南★ 80
Hugging Face Blog360 days agoTutorialFLUX.1-dev is a state-of-the-art open-source text-to-image model with 12 billion parameters (12B), developed by Black Forest Labs. However, due to its enormous…
FLUX.1 Kontext 社群應用大盤點：探索 AI 圖像「上下文生成」的全新創意
Replicate Blog377 days agoCommentary### FLUX.1 Kontext Sparks a New Wave of "In-Context Image Generation" Since Black Forest Labs introduced FLUX.1, this open-source image generation model has…
使用 FLUX.1 Kontext 用文字輕鬆編輯圖片：Black Forest Labs 最新圖像編輯模型實戰指南★ 80
Replicate Blog381 days agoReleaseBlack Forest Labs (the development team behind the FLUX series of models) has launched a new image editing model called "FLUX.1 Kontext." This model is…
Google 旗艦級影像生成模型 Imagen 4 正式上架 Replicate
Replicate Blog388 days agoReleaseGoogle's flagship image generation model, Imagen 4, has officially launched on the popular AI hosting platform Replicate, opening it up for testing and…
Ideogram 3.0 正式登陸 Replicate：強大的設計、風格遷移與寫實影像生成★ 75
Replicate Blog403 days agoReleaseIdeogram, a standout in the AI image generation space, has launched its latest-generation model Ideogram 3.0, which is now officially available on the AI model…
Easel AI 正式上架 Replicate：提供進階換臉與 AI 頭像生成 API
Replicate Blog424 days agoReleaseWell-known AI imaging brand Easel AI has officially announced that its advanced face swap and AI avatar generation models are now available on the popular…
Replicate 創意精選：頭像生成、光劍特效與 LoRA 實用技巧
Replicate Blog443 days agoReleaseReplicate recently published the latest edition of its "Creative Roundup," showcasing fun experiments and practical tools built by community members using…
Groq、fal 與 DeepInfra 正式加入 Vercel Marketplace★ 75
Vercel Changelog453 days agoReleaseVercel has officially announced that three prominent AI infrastructure service providers — Groq, fal, and DeepInfra — have formally joined the Vercel…
Hugging Face 推出 Remote VAE 功能：優化 Inference Endpoints 的圖像解碼與 VRAM 佔用★ 75
Hugging Face Blog475 days agoReleaseIn the generative AI domain, latent diffusion models (such as Stable Diffusion, FLUX.1, etc.) operate in two main stages: first, denoising and generation take…