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。

CLIPasso: Semantically-Aware Object Sketching

78 点作者 lnyan超过 3 年前

3 条评论

yeldarb超过 3 年前
Continually amazed by how versatile CLIP is. I’m keeping a compendium of cool use-cases I run across here[1]. I’ll add this to it today!<p>[1] <a href="https:&#x2F;&#x2F;blog.roboflow.com&#x2F;openai-clip&#x2F;" rel="nofollow">https:&#x2F;&#x2F;blog.roboflow.com&#x2F;openai-clip&#x2F;</a>
评论 #30345897 未加载
pizza超过 3 年前
related: I had an idea to make a CLIP paint.NET image editing plugin. You would make a new layer, add some green (&#x27;towards&#x27;) and red (&#x27;away from&#x27;) splotches to the layer, and give a prompt to CLIP. Wherever there was green, CLIP would &#x27;nudge&#x27; the image along the direction of the gradients towards the semantic goal, keep it constant where there was nothing, and nudge it in the opposite direction where there was red. And you could do this over and over again, w&#x2F; different CLIP prompts all the while editing the semantic masks as you like. The end result would be a feedback process to use CLIP + feedback as an extremely creative and controllable image manipulation tool. But then I realized that I didn&#x27;t know how to make a paint.NET plugin :) so here is a free idea for anybody who does
评论 #30350454 未加载
mcphage超过 3 年前
Like most people, I&#x27;ve got piles of old photos that I&#x27;d like to be able to label who is who in the person. For some family photos, I&#x27;ve doodled sketches of the photo, labelled the sketch, and attached it to the back. But I&#x27;ve often thought there had to be a way to get the computer to take the photo and generate the sketch from it. This seems exactly like it!