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.

Video to video with Stable Diffusion

432 pointsby hui-zhengalmost 2 years ago

18 comments

hospitalJailalmost 2 years ago
I was going to get a 4090 this year, but I just don&#x27;t think 24gb VRAM is going to bee enough in the short term future(for AI related stuff).<p>Ended up getting a 3060 for 1&#x2F;4 of the cost, and I&#x27;m planning on using&#x2F;paying for Colab until some 6090 comes out with 128gb vram.<p>Something that kind of bothers me that I don&#x27;t understand. Why is there such an obsession about having small computers&#x2F;servers? I don&#x27;t care if I have to put my computer in the basement because its the size of a closet or two. Maybe there is an EE issue, like too much current or EMF if you make a large computer.<p>I&#x27;d usually use colab, for 99% of the jobs... but I admittedly want to do some nsfw stuff with me and the wife with AI Art.
评论 #36293668 未加载
评论 #36295819 未加载
评论 #36293850 未加载
评论 #36291420 未加载
评论 #36292515 未加载
评论 #36293634 未加载
评论 #36292631 未加载
评论 #36291756 未加载
评论 #36294489 未加载
评论 #36291466 未加载
DrSiemeralmost 2 years ago
Not going to bother with this until the temporal cohesion issue is solved. The results are cool, but the variety in frames makes it look like a very specific and distracting art style instead of true animation.
评论 #36289564 未加载
评论 #36291948 未加载
评论 #36290641 未加载
评论 #36289203 未加载
评论 #36292583 未加载
评论 #36291461 未加载
tetris11almost 2 years ago
It&#x27;s insane the speed of progress. That being said, the most smooth example in that tutorial (Temporal Kit) required a lot of outside processing.<p>I wonder if AUTOMATIC1111 ui will start handling workflow scripts, a.l.a blender workflow boxes.
评论 #36288958 未加载
padolseyalmost 2 years ago
Once the temporal fixes are applied, the residual morphing and flickering actually quite appeals to me. Reminds me of the animation style in A Scanner Darkly.
评论 #36294724 未加载
评论 #36292993 未加载
评论 #36291329 未加载
throwaway22032almost 2 years ago
Does anyone else find it weird that a huge amount of AI video&#x2F;imagery in tutorials etc seem to be sexy anime schoolgirls?<p>I&#x27;m a bloke, I&#x27;ve never been that particularly bothered by like, Lara Croft, Lena, muscular guys in action games etc, I get it, I want to look at idealized&#x2F;attractive things as much as the next person, but something about this makes me super uncomfortable.
评论 #36306347 未加载
评论 #36297320 未加载
评论 #36298690 未加载
karlesalmost 2 years ago
Same aesthetics as A-ha&#x27;s &quot;Take on me&quot;. Even with the flaws, I can see how this can simply be used with that exact aesthetic in mind, without the need for any improvement.
评论 #36292792 未加载
评论 #36291764 未加载
gareth_untetheralmost 2 years ago
Could people please add newbie resources to this post?
yargalmost 2 years ago
So all that&#x27;s happening is people are getting increasingly good at hiding violations of spatiotemporal invariants?<p>This is treating the symptom and ignoring the disease.
erybodyknowsalmost 2 years ago
Does anyone “in the know” have approximations on cost to run this on collab or similar? Maybe a very rough Dollars per minute of video?
评论 #36292566 未加载
plandisalmost 2 years ago
&gt; Something that kind of bothers me that I don&#x27;t understand. Why is there such an obsession about having small computers&#x2F;servers? I don&#x27;t care if I have to put my computer in the basement because its the size of a closet or two. Maybe there is an EE issue, like too much current or EMF if you make a large computer.<p>I’m not using my GPU for heavy machine learning tasks at home. I have a Ncase M1 with a ryzen 3950x (16core&#x2F;32 thread) and a 3090 and a few nvme m2 drives. It’s water cooled but for me the video card is the only pcie card I have, and water cooling keeps the temps reasonable even in the small space. It was a little tricky to build in but why take up a bunch of unnecessary space?
mherrmannalmost 2 years ago
Does someone know how long rendering these videos takes? Can it be done in real-time?
评论 #36292595 未加载
politelemonalmost 2 years ago
I&#x27;ve only been using stable diffusion in a very basic way, give some text, get some images back. Seeing what others produce with it is amazing and also just feels beyond me, I&#x27;m simply not familiar with all these other extensions and scripts. That said I appreciate a tutorial like this which isn&#x27;t glossing over steps, so it&#x27;s worth a try.
swayvilalmost 2 years ago
That first video is fabulous. It reminds me of a standard trope in generative art : You generate a whole bunch of prospective images and then pick the nicest ones.<p>Except in this case we get to see all the prospects (The variations in chestplate, wings etc). And in such a cool style.
m3kw9almost 2 years ago
The end result look like a a cartoon filter applied frame by frame. Or, each frame is basically going through stable diffusion in photo mode
torginusalmost 2 years ago
It looks to me there&#x27;s a tradeoff between how much SD changes the input, and how temporally coherent it is.
bulbosaur123almost 2 years ago
Isn&#x27;t runway vid2vid superior in the aspect of coherency? This flickering is horrible.
评论 #36289592 未加载
bulbosaur123almost 2 years ago
Did they finally fix the annoying flickering?
aantixalmost 2 years ago
The Temporal Kit write up was amazing.