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.

Show HN: Realtime LCM tool

12 pointsby dvrpover 1 year ago

4 comments

brucethemoose2over 1 year ago
Are y&#x27;all running the diffusion in PyTorch eager mode?<p>AITemplate, stable-fast, or even a torch.compile could get that down to 60ms, I bet. Though I&#x27;m not sure the example implementations would work on a non SD architecture.
评论 #38255622 未加载
评论 #38255651 未加载
erwannmillonover 1 year ago
i worked on the gpu&#x2F;infra side of this, so feel free to AMA Ultimately the LCM is just a SD Unet trained with a new objective, so a lot of SD optimizations are transferable to LCMs
评论 #38255361 未加载
dvrpover 1 year ago
will write an essay about it later, but servers exploding even with experimental alpha users.<p>I&#x27;m excited about what H200s or B100s will mean for technology like this one.
评论 #38255530 未加载
vmatsiiakoover 1 year ago
Can you use custom images?
评论 #38255253 未加载