Kaiming He's All-Undergrad Team Achieves Text-to-Image With Only 258M Parameters
量子位 QbitAI39 days agoPaperA new research paper from Kaiming He's lab — notable for having an all-undergraduate team — demonstrates that high-quality text-to-image generation can be achieved with just 258 million parameters. This challenges the prevailing assumption that competitive image synthesis requires multi-billion-parameter models. The work signals a push toward leaner, more accessible generative vision architectures.
HiDream-O1-Image-1.5 Ranks #1 in China, #2 Globally in Text-to-Image Benchmarks, Surpassing Google and NVIDIA
量子位 QbitAI47 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.
PRX 第三部分：在 24 小時內訓練一個 Text-to-Image 圖像生成模型！★ 75
Hugging Face Blog146 days agoTutorialPhotoroom, the well-known AI image editing tool, recently published Part 3 of its technical blog series on Hugging Face about its in-house image generation…
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 Blog151 days agoReleaseGoogle DeepMind has officially released its latest image generation model, "Nano Banana 2." The core breakthrough of this model lies in its successful…
Text-to-Image 模型訓練設計：來自 Photoroom 消融實驗的實戰啟示★ 75
Hugging Face Blog175 days agoTutorialPhotoroom, the well-known image editing platform, recently published a series of technical blog posts about their in-house text-to-image model, PRX. In Part 2…
FLUX.2 正式上架 Replicate：支援多重參考與專業級圖像生成★ 80
Replicate Blog245 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 Blog245 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 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 Blog249 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…
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 Blog447 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…
Hugging Face 社群推出用於文字生成圖像的開源偏好資料集 (Open Preference Dataset)★ 75
Hugging Face Blog596 days agoRelease### Introduction: An Important Piece of the Open-Source Image Generation Puzzle As text-to-image (T2I) technology advances rapidly, ensuring that AI-generated…
Ideogram v2 局部繪製（Inpainting）模型上線 Replicate API：更強大的圖像編輯與文字生成能力★ 75
Replicate Blog644 days agoReleaseThe AI image generation and hosting platform Replicate has announced a partnership with the well-known image generation technology company Ideogram, officially…
Diffusers 正式支援 Stable Diffusion 3.5 Large：更強大的開源圖像生成模型與優化指南★ 85
Hugging Face Blog644 days agoReleaseStability AI officially launched the Stable Diffusion 3.5 (SD3.5) model series in late October 2024, and Hugging Face's Diffusers team simultaneously announced…
Stable Diffusion 3.5 正式登陸 Replicate：支援 API 快速部署與調用★ 75
Replicate Blog644 days agoReleaseStability AI has announced its latest text-to-image model, Stable Diffusion 3.5. At the same time, the well-known AI model hosting platform Replicate has…
FLUX.1.1 [pro] 正式推出：速度提升 6 倍、品質更佳的全新圖像生成模型★ 85
Replicate Blog663 days agoReleaseBlack Forest Labs has officially launched its latest image generation model, FLUX.1.1 [pro], which is now simultaneously available on the Replicate platform…
微調 FLUX.1 打造專屬個人寫真：Replicate 官方 LoRA 訓練教學★ 80
Replicate Blog697 days agoTutorialThis official Replicate tutorial walks through in detail how to use LoRA (Low-Rank Adaptation) technology to fine-tune FLUX.1 [dev] — currently the most…
Replicate 推出 FLUX.1 微調功能：用一行程式碼即可訓練專屬的 LoRA 圖像生成模型★ 80
Replicate Blog712 days agoReleaseReplicate, the well-known cloud AI execution platform, has announced official fine-tuning support for FLUX.1, the image generation model that has taken the…
FLUX.1 首發實測：開源圖像生成的新巔峰與第一手體驗★ 85
Replicate Blog725 days agoReleaseFLUX.1 is a new family of text-to-image models developed by Black Forest Labs — a startup founded by the original core research team behind Stable Diffusion…
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 Blog726 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…
Replicate Intelligence #6：Google Gemma 2 模型上線、LLM 排行榜更新與 Stable Diffusion 3 實用技巧★ 75
Replicate Blog760 days agoReleaseThis issue of Replicate Intelligence summarizes three major core updates from the recent open-source AI landscape: 1. **Google Gemma 2 officially launches**…
使用 API 運行 Stable Diffusion 3：Replicate 雲端部署指南★ 70
Replicate Blog776 days agoNew ToolStability AI officially launched its latest text-to-image model — Stable Diffusion 3 (SD3). This release brings major upgrades across several key areas…
Diffusers 正式支援 Stable Diffusion 3：更強大的圖像生成與記憶體優化★ 80
Hugging Face Blog776 days agoReleaseHugging Face's official blog announced that its diffusers library now officially supports Stable Diffusion 3 (SD3), the latest release from Stability AI. SD3…
迎來 aMUSEd：高效的輕量級 Text-to-Image 文本生成圖像模型
Hugging Face Blog936 days agoReleaseThe Hugging Face official blog formally introduced a brand-new open-source text-to-image model called "aMUSEd." This model is based on a reproduction and…
探索 SDXL 的簡單優化方法：大幅提升速度與節省顯存的實用指南★ 75
Hugging Face Blog1,008 days agoTutorialStable Diffusion XL (SDXL) is a powerful but architecturally large text-to-image model whose parameter count far exceeds that of the previous SD 1.5, placing…
使用 TRL 透過 DDPO 微調 Stable Diffusion 模型★ 75
Hugging Face Blog1,033 days agoReleaseHugging Face published a blog post introducing how to use the DDPO (Denoising Diffusion Policy Optimization) algorithm within the TRL (Transformer…
介紹 Würstchen：超快速且高效的圖像生成擴散模型★ 75
Hugging Face Blog1,049 days agoReleaseHugging Face, in collaboration with the research community, has introduced a new text-to-image diffusion model called "Würstchen." The model's standout feature…
畫筆化為文字：文字生成圖像 AI 的演進簡史
Replicate Blog1,071 days agoCommentaryOn the occasion of the first anniversary of Stable Diffusion and Replicate's launch of Stable Diffusion XL (SDXL) fine-tuning services, this article provides…
Hugging Face 倫理與社會電子報 #4：文字生成圖像模型中的偏見問題
Hugging Face Blog1,128 days agoCommentaryThe Hugging Face Ethics and Society team has published the fourth edition of its newsletter, this time focusing on the problem of "bias" in text-to-image (T2I)…
在免費版 Google Colab 上使用 🧨 diffusers 運行 DeepFloyd IF 模型
Hugging Face Blog1,189 days agoTutorial### Core Background and Challenges DeepFloyd IF is an advanced text-to-image model released by DeepFloyd, a research lab under Stability AI. Unlike the…
VQ-Diffusion：基於離散擴散模型的文本到圖像生成技術
Hugging Face Blog1,336 days agoReleaseIn late 2022, while continuous-space diffusion models represented by Stable Diffusion were stealing the spotlight, diffusion models operating in discrete space…
Stability AI 發布 Japanese Stable Diffusion：專為日語優化的文字生成圖像模型
Hugging Face Blog1,392 days agoReleaseIn October 2022, Stability AI officially released "Japanese Stable Diffusion," a model specifically designed for the Japanese market and culture, hosted on the…