1.0osmotic intelligencehttps://www.myshirtai.com/enIvesFeng666https://www.myshirtai.com/en/archives/author/adminrich600338<blockquote class="wp-embedded-content" data-secret="0uR7vN1SHq"><a href="https://www.myshirtai.com/en/archives/6536">NextStep-1：自回归图像生成的”终极形态”，14B参数模型开源了！</a></blockquote><iframe sandbox="allow-scripts" security="restricted" src="https://www.myshirtai.com/en/archives/6536/embed#?secret=0uR7vN1SHq" width="600" height="338" title="“NextStep-1：自回归图像生成的”终极形态”，14B参数模型开源了！” — 渗透智能" data-secret="0uR7vN1SHq" frameborder="0" marginwidth="0" marginheight="0" scrolling="no" class="wp-embedded-content"></iframe><script> /*! This file is auto-generated */ !function(d,l){"use strict";l.querySelector&&d.addEventListener&&"undefined"!=typeof URL&&(d.wp=d.wp||{},d.wp.receiveEmbedMessage||(d.wp.receiveEmbedMessage=function(e){var t=e.data;if((t||t.secret||t.message||t.value)&&!/[^a-zA-Z0-9]/.test(t.secret)){for(var s,r,n,a=l.querySelectorAll('iframe[data-secret="'+t.secret+'"]'),o=l.querySelectorAll('blockquote[data-secret="'+t.secret+'"]'),c=new RegExp("^https?:$","i"),i=0;i<o.length;i++)o[i].style.display="none";for(i=0;i<a.length;i++)s=a[i],e.source===s.contentWindow&&(s.removeAttribute("style"),"height"===t.message?(1e3<(r=parseInt(t.value,10))?r=1e3:~~r<200&&(r=200),s.height=r):"link"===t.message&&(r=new URL(s.getAttribute("src")),n=new URL(t.value),c.test(n.protocol))&&n.host===r.host&&l.activeElement===s&&(d.top.location.href=t.value))}},d.addEventListener("message",d.wp.receiveEmbedMessage,!1),l.addEventListener("DOMContentLoaded",function(){for(var e,t,s=l.querySelectorAll("iframe.wp-embedded-content"),r=0;r<s.length;r++)(t=(e=s[r]).getAttribute("data-secret"))||(t=Math.random().toString(36).substring(2,12),e.src+="#?secret="+t,e.setAttribute("data-secret",t)),e.contentWindow.postMessage({message:"ready",secret:t},"*")},!1)))}(window,document); </script>https://www.myshirtai.com/wp-content/uploads/2025/11/image-8.png1260835阶跃星辰(StepFun)团队开源了NextStep-1，一款14B参数的纯自回归图像生成模型。该模型直接在连续视觉空间生成图像，无需依赖扩散模型或离散化处理，由14B参数Transformer骨干和157M参数流匹配头组成。它支持高保真文生图及精准图像编辑（如物体增删、背景修改），在GenEval（0.73）、GenAI-Bench等基准测试中表现优异，接近顶尖扩散模型。但存在生成不稳定、解码延迟等挑战，标志着自回归图像生成新阶段。