TE
科技回声
首页24小时热榜最新最佳问答展示工作
GitHubTwitter
首页

科技回声

基于 Next.js 构建的科技新闻平台,提供全球科技新闻和讨论内容。

GitHubTwitter

首页

首页最新最佳问答展示工作

资源链接

HackerNews API原版 HackerNewsNext.js

© 2025 科技回声. 版权所有。

Show HN: LLM draws SVG, StableDiffusion polishes it

4 点作者 benzguo10 个月前

1 comment

benzguo10 个月前
i had this idea for an AI workflow:<p>1. describe an svg drawing in great detail<p>1.5. ask the llm to label its drawing because it&#x27;s fun to watch<p>2. generate the svg<p>3. img-to-img with sdxl<p>it&#x27;s a silly demo but kinda fun, source: <a href="https:&#x2F;&#x2F;www.val.town&#x2F;v&#x2F;substrate&#x2F;scribble" rel="nofollow">https:&#x2F;&#x2F;www.val.town&#x2F;v&#x2F;substrate&#x2F;scribble</a><p>you can coax Llama3 into generating better SVGs using multiple steps, actually – in a previous version the SVG had gradients, stacked layers, dot grid textures... even animations<p>but i had to do a roundabout thing to rasterize the SVG in the val sandbox so i removed all that<p><a href="https:&#x2F;&#x2F;x.com&#x2F;vprtwn&#x2F;status&#x2F;1811710646729277740" rel="nofollow">https:&#x2F;&#x2F;x.com&#x2F;vprtwn&#x2F;status&#x2F;1811710646729277740</a>