TE
TechEcho
Home24h TopNewestBestAskShowJobs
GitHubTwitter
Home

TechEcho

A tech news platform built with Next.js, providing global tech news and discussions.

GitHubTwitter

Home

HomeNewestBestAskShowJobs

Resources

HackerNews APIOriginal HackerNewsNext.js

© 2025 TechEcho. All rights reserved.

Generating transparent images using Stable Diffusion XL

216 pointsby tracyhenryabout 1 year ago

5 comments

amlutoabout 1 year ago
Looking at the “woman, messy hair, high quality” image, the hair farther from her head looks wrong in much the way that iPhone portrait mode messes up hair. I wonder if this is an example of an AI training on partially AI-generated data and reproducing its artifacts.
评论 #39580066 未加载
GaggiXabout 1 year ago
Paper: <a href="https:&#x2F;&#x2F;arxiv.org&#x2F;abs&#x2F;2402.17113" rel="nofollow">https:&#x2F;&#x2F;arxiv.org&#x2F;abs&#x2F;2402.17113</a><p>The author Lvmin Zhang is the same person behind ControlNet.
评论 #39577488 未加载
评论 #39577577 未加载
vunderbaabout 1 year ago
The partial alpha blending support for translucent materials is really cool (glass, plastic, etc).<p>I&#x27;d be curious to see how well this plays with inpainting. Apparently img2img is also on the authors todo list.
评论 #39578207 未加载
swyxabout 1 year ago
reactions<p>1 - the way the dog at the end gets a reflection off the floor is pretty nice.<p>2 - i wonder how this compares in terms of latency&#x2F;complexity with a comfyui pipeline that just does a typical edge detection&#x2F;masking layer to achieve the transparency effect. however i dont think that method would work with the glass example as shown
dannywabout 1 year ago
Apache 2.0, the beauty of open source. Nice.
评论 #39577296 未加载