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: Vignette – Image generation and animation with LLMs(not diffusion etc.)

1 点作者 notnotrishi大约 1 年前
I like to explore hidden capabilities of language models (LLMs), and I&#x27;ve been exploring how good text generation models are at media generation .<p>In this case, the experiment was, can we hack together a text-to-image&#x2F;animation app from basic text generation models (not image generation&#x2F;diffusion models)?<p>Turns out Claude API is pretty useful for generating images and animations. My theory is Claude is really good with XML (the underlying format for SVG) and thus enabling this specific use case. I haven’t tried with other LLMs but didn’t have much luck with Gemini so far.<p>Code open source, and demos on my repo: <a href="https:&#x2F;&#x2F;github.com&#x2F;notnotrishi&#x2F;vignette&#x2F;">https:&#x2F;&#x2F;github.com&#x2F;notnotrishi&#x2F;vignette&#x2F;</a><p>Feel free to try it for yourself or leave any notes. Thanks!

暂无评论

暂无评论