HiDream-O1-Image-1.5 Ranks #1 in China, #2 Globally in Text-to-Image Benchmarks, Surpassing Google and NVIDIA
量子位 QbitAI3 days agoBenchmarkHiDream-O1-Image-1.5, a Chinese text-to-image model, has reached the top of domestic leaderboards and secured second place globally in the latest benchmark standings. The model reportedly outperforms image-generation offerings from Google and NVIDIA. The result marks a significant milestone for Chinese generative image research on the world stage.
Apple’s Image Playground doesn’t suck anymore
TechCrunch AI5 days agoReleaseApple announced improvements to Image Playground at WWDC 2026, positioning the iPhone’s built-in AI image generator as a more capable tool. The update emphasizes natural-language photo transformations, multi-person image use, flexible output dimensions, and integrations across lock screens, iMessage backgrounds, and contact posters. TechCrunch has not tested it yet, but the presentation suggests Apple Intelligence apps may become more practical.
Reve 2 and Ideogram 4: Layouts in Imagegen
Latent Space10 days agoReleaseLatent Space’s roundup frames image composition as a major barrier now being tackled by layout-aware image models. Reve 2.0 emphasizes precise generation and editing with layouts, while Ideogram 4.0 uses bounding boxes tied to region descriptions. The issue also covers MAI-Thinking-1, Gemma 4 12B, open audio models, agent execution layers, and model-routing cost debates.
Vercel AI Gateway 正式支援 GPT Image 2 模型★ 70
Vercel Changelog54 days agoReleaseVercel recently announced in its product update Changelog that the Vercel AI Gateway has officially added support for the "GPT Image 2" model. Vercel AI…
Vercel AI Gateway 現已支援純圖像模型 (Image-only models)★ 70
Vercel Changelog198 days agoReleaseVercel recently updated its AI Gateway service to officially add support for "image-only models." Previously, Vercel AI Gateway primarily provided API…
Fuel your creativity with new generative media models and tools★ 78
Google DeepMind Blog390 days agoNew ToolGoogle announced new generative media models and tools at I/O 2025, led by Veo 3 for video, Imagen 4 for images, and Flow for AI filmmaking. Veo 3 adds audio generation, while Imagen 4 improves detail, typography, aspect ratios, and up to 2K output. Google also expanded Lyria 2 and Lyria RealTime access, while continuing SynthID watermarking and launching SynthID Detector.
Hugging Face 推出首期「AI 藝術工具電子報」：匯整最新開源創意 AI 與 Spaces 工具
Hugging Face Blog499 days agoReleaseIn late January 2025, Hugging Face officially launched a brand-new initiative: the first edition of the "AI Tools for Art Newsletter." This newsletter was…
Black Forest Labs 推出全新開源影像生成模型 FLUX.1：Replicate 已支援 API 運行★ 90
Replicate Blog682 days agoReleaseBlack Forest Labs — a new AI team founded by the original creators of Stable Diffusion (including core developer Robin Rombach and others) — has officially…
在 Hugging Face Spaces 上透過 Gradio 免費運行 ComfyUI 工作流★ 75
Hugging Face Blog882 days agoTutorialThis official Hugging Face blog post provides a detailed guide on how to deploy and run ComfyUI workflows on Hugging Face Spaces for free using Gradio…
VQ-Diffusion：基於離散擴散模型的文本到圖像生成技術
Hugging Face Blog1,292 days agoReleaseIn late 2022, while continuous-space diffusion models represented by Stable Diffusion were stealing the spotlight, diffusion models operating in discrete space…
使用 Stable Diffusion、Replicate 與 Fly.io 為 Discord 伺服器打造 AI 繪圖機器人
Replicate Blog1,389 days agoTutorialThis hands-on tutorial from Replicate walks developers step by step through building a "bot artist" deployed on Discord. Users simply type a text prompt into a…
詳解擴散模型：The Annotated Diffusion Model 程式碼與原理實戰指南★ 85
Hugging Face Blog1,468 days agoTutorialThis classic blog post from Hugging Face, "The Annotated Diffusion Model," is an essential guide for learning about generative AI image synthesis. Modeled…