Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

A Web UI for Stable Diffusion

github.com

Post reply on HN
Print view View original

41–50 of 148 posts

Re: A Web UI for Stable Diffusion

#41

Post by l33tman »

jrm4 wrote: post #17

So, and this is an ELI5 kind of question I suppose. There must be something going on like "processing a kazillion images" and I'm trying to wrap my head around how (or what part of) that work is "offloaded" to your home computer/graphics card? I just can't seem to make sense of how you can do it at home if you're not somehow in direct contact with "all the data?" e.g. must you be connected to the internet, or "stable…

SD has 860M weights for the main workhorse part. At 16-bit precision that is only 1.6 GB of data, which in some very real sense has condensed the world's total knowledge of art and photography and styles and objects.

It's not a search engine, it's self-contained and the closest analogy is that it's a very very knowledgable and skilled artist.

Re: A Web UI for Stable Diffusion

#42

Post by jyrkesh »

nowandlater wrote: post #2

This is the one I've been using https://github.com/sd-webui/stable-diffusion-webui . docker-compose up , works great.

I've also been using this one (wasn't sure at first, they just migrated from the /hlky/ namespace on GitHub), but I have no idea at first glance what the differences are.

I will say that this one has had REALLY active development as new features have been coming out, and is pretty polished at this point (albeit I'm using it more as a toy than anything, but it's awesome to have a quick way to use the new features that have been shipping out).

Re: A Web UI for Stable Diffusion

#44

Post by throwaway1851 »

schleck8 wrote: post #27
ducktective wrote: post #15

It seems Midjourney generates better results than SD or Dall-E. What's with the "hyper resolution", "4K, detailed" adjectives which are thrown left and right, while we are at it?

Those are prompt engineering keywords. SD is way more reliant on tinkering with the prompt than midjourney https://moritz.pm/posts/parameters

MidJourney needs a lot of prompt engineering too. And Dall-E also. If you look at the prompt as an opportunity to describe what you want to see, the results are often disappointing. It works better to think backwards about how the model was trained, and what sorts of web caption words it likely saw in training examples that used the sorts of features you’re hoping it will generate. This is more of a process of learning to ask the model to produce things it’s able to produce, using its special image language.

Re: A Web UI for Stable Diffusion

#45

Post by geerlingguy »

sharps_xp wrote: post #4

if someone can dockerize this, please reply with a link!

The main one I've been testing (https://github.com/sd-webui/stable-diffusion-webui) has a Docker Compose file.

Grab that, install Docker, install Nvidia's Docker integration, copy the example Docker-env file, and docker-compose up is all you need.

Edit: here's a gist with exact steps I used: https://gist.github.com/geerlingguy/384ed4aba35e3118f2a0f358...

Re: A Web UI for Stable Diffusion

#46

Post by bootsmann »

jrm4 wrote: post #17

So, and this is an ELI5 kind of question I suppose. There must be something going on like "processing a kazillion images" and I'm trying to wrap my head around how (or what part of) that work is "offloaded" to your home computer/graphics card? I just can't seem to make sense of how you can do it at home if you're not somehow in direct contact with "all the data?" e.g. must you be connected to the internet, or "stable…

You can think of it more like this: If I do 100 experiments of dropping stones at variable heights and measuring the time it takes for the stone to land on the ground I have enough datapoints to make a linear estimation of gravity by using linear regression. So based on my data I create a model that the time it takes for a stone to fall is sqrt(2h/9.81). Now if you want to figure out how long it takes for your stones to fall, you don’t need to redo all the experiments and can instead rely on the parameters I give you (say 9.81 in this case) to calculate it yourself.

With these models it works exactly the same way. Someone dropped millions of rocks and created a formula of unbelievable complexity and what they now did is they released that formula with all their calculated parameters into the world. What you do when you ultimately use Stable Diffusion is you just calculate the result of this formula and that is your image. You never have to process those images.

Re: A Web UI for Stable Diffusion

#47

Post by palunon »

ducktective wrote: post #19
jrm4 wrote: post #17

So, and this is an ELI5 kind of question I suppose. There must be something going on like "processing a kazillion images" and I'm trying to wrap my head around how (or what part of) that work is "offloaded" to your home computer/graphics card? I just can't seem to make sense of how you can do it at home if you're not somehow in direct contact with "all the data?" e.g. must you be connected to the internet, or "stable…

As someone with ~0 knowledge in this field, I think this has to do with a concept called "transfer learning" in which you once train with that kazillion of images, then use that same "coefficients" for further run of the NN.

Nah, transfer learning is when you take a trained model, and train it a little more to better fit your (potentially very different) problem domain. Such as training a cat/dog/etc recognition model on MRI scans.

The goal is usually to have the more fundamental parts of your model already working and you thus need way less domain specific data.

Here, you're not training anything, you're running the models (both the CLIP language model and the unet) in feedforward. That's just deploying your model, not transfer learning.

Re: A Web UI for Stable Diffusion

#48

Post by cma »

ducktective wrote: post #15

It seems Midjourney generates better results than SD or Dall-E. What's with the "hyper resolution", "4K, detailed" adjectives which are thrown left and right, while we are at it?

Midjourney uses SD under the hood (you can see in their license), but they augnment the model in various ways.

Re: A Web UI for Stable Diffusion

#49

Post by qudat »

cma wrote: post #48
ducktective wrote: post #15

It seems Midjourney generates better results than SD or Dall-E. What's with the "hyper resolution", "4K, detailed" adjectives which are thrown left and right, while we are at it?

Midjourney uses SD under the hood (you can see in their license), but they augnment the model in various ways.

The results in midjourney are significantly better than SD. I find it much easier to get to a good result in MJ and I've been trying to understand why. Anymore insight you could share?

Re: A Web UI for Stable Diffusion

#50

Post by zenlikethat »

amelius wrote: post #33

Regarding the opening image: if it can't correctly put the marks on dice, how can it put eyes, nose and mouth correctly on a human face?

It can’t. :)

Well, I kid a bit. I’ve seen it produce some amazing results, but, generally, it has a hard time with that. Often faces end up looking blurry or having these creepy, dead white eyes. Hands likewise often end up malformed (seven fingers anyone?) and twisty. But, it seems to have a much easier time generating passable faces in close ups with the right key words. Especially if you give it an input image that already has a clear one. It also seems to have an easier time doing faces it already knows like a celebrity, presumably because it’s using a strong existing influence instead of inventing/hallucinating it.

Supposedly this is improved in their new 1.5 version which is in beta. The software is so compelling that I suspect this will be improved quite quickly. Also, I think either way workarounds will emerge, either by composing with other networks/software (some UIs have GANs for face correction) or the old fashioned way by photoshopping over the blemishes.

Post reply on HN