Hacker News new | past | comments | ask | show | jobs | submit | Karuma's comments login

It wouldn't be too hard to do any of the things you mention. See ControlNet for Stable Diffusion, and vid2vid (if this model does txt2vid, it can also do vid2vid very easily).

So you can just record some guiding stuff, similar to motion capture but with just any regular phone camera, and morph it into anything you want. You don't even need the camera, of course, a simple 3D animation without textures or lighting would suffice.

Also, consistent look has been solved very early on, once we had free models like Stable Diffusion.


Maybe removing the lazy posts from the training data.


That game is from a second-party developer.


"second party developer" is kind of a loose term. Rare had close relationship with Nintendo at the time, and were allowed to produce games for some of Nintendo's IP, but they ultimately ended up being acquired by Microsoft, so they weren't so exclusive that Nintendo could prevent that outcome.


With SD I can generate at least 15k images daily on my old laptop, I can train it with new styles, characters, real people, etc.; download thousands of new styles, characters, real people, etc. from Civitai, and best of all, never worry about ever losing access to it, being censored, having to jailbreak it, being snooped on, etc.

Plus a million other tools that the community has made for it, like ControlNet or things like AnimateDiff to create videos. I can also easily create all kinds of scripts and workflows.


The most interesting bit for me is that "he deciphered the Mayan script when he learned that the world scientific community considered it impossible."

This part is sadly very common in all sciences: https://en.wikipedia.org/wiki/Yuri_Knorozov#Critical_reactio...


It's always been bad for you.


Tell that to the Massai, that live basically on a diet of milk, meat and blood. Just because you wish it to be bad it doesn't change reality my dude.


https://medlineplus.gov/genetics/condition/lactose-intoleran...

"Lactase nonpersistence is most prevalent in people of East Asian descent, with 70 to 100 percent of people affected in these communities."

Masai herdsmen are East Africans; so I find that statistic bewildering. "Lactase nonpersistence" means the decline of the production of the enzyme lactase beyond infancy. I don't know whether lactase nonpersistence is equivalent to lactose intolerance.


A (very small) percentage of the population is alergic to peanuts. They can even die if they ingest a peanut by accident. Does it make so that "peanuts are bad for you"? Can I make this argument? Milk is perfectly fine and is an important part of a healthy diet, for 90% of the population of the Americas, Europe, Africa etc. The magnitude of the propaganda to make people think otherwise simply baffles me.


> Milk is perfectly fine and is an important part of a healthy diet, for 90% of the population of the Americas

Is this true ? I’ve understood milk is for babies and adults don’t need it


> Tell that to the Massai, that live basically on a diet of milk, meat and blood

They also live a mainly active, nomadic lifestyle herding cows rather than sitting down staring at a computer screen - and usually die in their forties.


They specifically adapted to survive on that diet due to both group level isolation and individual upbringing (gut bacteria development). Different socio-cultural groups often have different tolerance for common food items.


Comparing hn-ers lifestyle/needs to that of Massai? not the best idea.


It's indifferent to the question. Some food is either healthy for human consumption or it's not. The argument is: if a population of humans exist that makes milk a very substantial portion of their diet, and is perfectly fine, arguing that it's bad for humans is complete stupidity.


There are forks that even work on 1.8 of VRAM! They work great on my GTX 1050 2GB.

This is by far the most popular and active right now: https://github.com/AUTOMATIC1111/stable-diffusion-webui


> This is by far the most popular and active right now: https://github.com/AUTOMATIC1111/stable-diffusion-webui

While technically the most popular, I wouldn't call it "by far". This one is a very close second (500 vs 580 forks): https://github.com/sd-webui/stable-diffusion-webui/tree/dev


That's why I said "right now", since I feel that most people have moved from the one you linked to AUTOMATIC's fork by now. hlky's fork (the one you linked) was by far the most popular one until a couple of weeks ago, but some problems with the main developer's attitude and a never-ending migration from Gradio to Streamlit filled with issues made it lose its popularity.

AUTOMATIC has the attention of most devs nowadays. When you see any new ideas come up, they usually appear in AUTOMATIC's fork first.


Just as another point of reference. I followed the windows install. I'm running this on my 1060 with 6GB memory. With no setting changes takes about 10 seconds to generate an image. I often run with sampling steps up to 50 and that takes about 40 seconds to generate an image.


While AUTOMATIC is certainly popular, calling it the most active/popular would be ignoring the community working on Invoke. Forks don’t lie.

https://github.com/invoke-ai/InvokeAI


> Forks don’t lie.

They sure do. InvokeAI is a fork of the original repo CompVis/stable-diffusion and thus shares its fork counter. Those 4.1k forks are coming from CompVis/stable-diffusion, not InvokeAI.

Meanwhile AUTOMATIC1111/stable-diffusion-webui is not a fork itself, and has 511 forks.


Welp - TIL.

Thanks for the correction.

Any idea on how to count forks of a downstream fork? If anyone would know... :)


Subjectively, AUTOMATIC has taken over -- I have not heard of invoke yet but will check it out.


The only reason to use it imo has been if you need mac/m1 support, but that's probably in other forks by now


What settings and repo are you using for GTX 1050 with 2GB?


I'm using the one I linked in my original post: https://github.com/AUTOMATIC1111/stable-diffusion-webui

The only command line argument I'm using is --lowvram, and usually generate pictures at the default settings at 512x512 image size.

You can see all the command line arguments and what they do here: https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki...


I guess then it could even work on a Jetson Nano(4GB) then, I run models of ~1.6 GB on it 24*7; Would give this a try.


This needs Windows 10/11 though?


Nope. There are instructions for Windows, Linux and Apple Silicon in the readme: https://github.com/AUTOMATIC1111/stable-diffusion-webui

There's also this fork of AUTOMATIC1111's fork, which also has a Colab notebook ready to run, and it's way, way faster than the KerasCV version: https://github.com/TheLastBen/fast-stable-diffusion

(It also has many, many more options and some nice, user-friendly GUIs. It's the best version for Google Colab!)


Brilliant thanks.


I think something similar already exists. See this, for example: https://koe.ai/recast/

Although I don't know if they're using anything similar to what you suggest. Very cool idea, anyway!


Google is paying, and yes, you can, but they will disconnect you after a while. And if you abuse it too much, you won't be able to use it until the following day...

You can also buy Colab Pro and Colab Pro+, which have fewer limitations and faster GPUs.


How fast is the Colab stuff? Is Colab Pro/Pro+ a lot faster too?

I run it locally and can generate images with 50 steps in about 6 seconds per image, would it be faster for me to use Colab Free/Pro/Pro+?


In my usage Colab and Colab Pro were similar, with plain Colab occasionally OOMing during model loading. That said I've actually been seeing times slower than yours on Colab and I think they're slower than on my RTX 3080. ~15 secs per image. I'm not sure why, though.


You are much better off running it locally at those speeds. P100 does 13 to 33 seconds a batch in my experience. Cloud to cloud data transfer (Hugginface to Colab) is ridiculously fast tho.


I'm on Colab Pro and get about 3 steps per second when generating a single 512x512 image at a time, with slight throughput improvement when I batch 2-3 images


Yes, you can run it on your Intel CPU: https://github.com/bes-dev/stable_diffusion.openvino

And this should work on an AMD GPU (I haven't tried it, I only have NVIDIA): https://github.com/AshleyYakeley/stable-diffusion-rocm

There are also many ways to run it in the cloud (and even more coming every hour!) I think this one is the most popular: https://colab.research.google.com/github/altryne/sd-webui-co...


Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: