Hacker News new | past | comments | ask | show | jobs | submit login
Show HN: Face Maker AI. Sketch to create photorealistic faces (massless.io)
87 points by jack_a_cohen on July 13, 2021 | hide | past | favorite | 49 comments



Funny thing, the more people comment that it doesn't load, the more trending the post is and more traffic it gets and the loading wheel spins even more and more.


I noticed after you updated the canvas it would regenerate, which isn't the most efficient way to do things. Also, the output is pretty lame.


Oh my GOD, the horror :) I'll leave it alone now, the dev server loaded for me a bit. Some observations from one who tried to do weird things with it…

This generator expects realistic proportions, in a big way. If you try to create giant anime eyes you're liable to find they have become mouths, even though you colorcoded them to be eyes. Auxiliary eyes seem more do-able. Mouths that are too small and eye-shaped become eyes: ambiguous shapes become who knows what. Fun ensues :)

The generator's doing interesting things with the overall contour of the face. It'll shade pretty realistically for whatever you make; the thing is, you have to be a good artist to understand what the REAL shape of, say, a nose is. If you think 'triangle' or any sort of abstraction you get monster creations: if you go for a roughed-in representation of ALL the real features of a nose covering the real areas you get something pretty realistic. That shape will look very strange to a non-artist because we don't think of a nose as having all those features.

It seems like the colors aren't nearly as important as the shapes and sizes and positionings are. That might be a useful observation. Right now, it's monster fuel but there's also an interesting 'can you REALLY draw a nose, or do you only think you know what a nose is shaped like?' factor. Again, I can't tell if the colors even mean anything but you've got to get REAL close to the actual dimensions of facial features (and scale!) to get remotely photoreal results.

Of course the monstrosities are perhaps even more fun… because the generator will try its best to contextualise them against the background of what a real face would be shaped like to account for those departures. I would enjoy a slower and more painstaking version of this along the same lines.

Thanks for the nightmares… and insights! I'll take my very creditable photoreal nose and be off now :)


My drawing skills are atrocious, I just gave up and started drawing parts where they didn't belong. Experimenting was fun but I kinda regret doing that.


I've tried this in firefox and chrome on both linux and windows, but it never loads the right side, anyoen seen this work?


It worked - that's why I upvoted it - but it doesn't work anymore. It must be traffic related.


I've been exploring how machine learning can be incorporated into the artistic process or for content creation. This experiment generates faces from segment maps. We have a pipeline setup that could be applied to landscapes, architecture, cars... etc. It feels like to me AI assisted content creation is going to become commonplace.


Is this service out of order?


Looks like prod is overloaded. Have a try on the dev server: https://unstable.massless.io/tool/face-maker-ai/


Which also seems overloaded now


I'll just wait a few days and then try it, keeping this tab open


Didn't get a chance to see the result (due to hug of death), but I think it could be improved with a "clear" function in order to start from a blank canvas, as it's quite tedious to try and remove the existing guide picture.


We have added clear to the [...] menu. You can try it out on https://unstable.massless.io/tool/face-maker-ai/.

I am still trying to get the production servers back, however, our unstable ones do seem to be holding for now.


I am looking into what might be bringing this down for some people. I'm not sure yet, but I'll post any updates once I have them.


It says login required in the browser console


You can use it without being logged in. This particular problem doesn't seem to be affected by that.


Would love for someone with some patience and artistic skill to draw Marge Simpson (or the other Simpson family members) and see what pops out. preemptive shudder


Some feedback from someone who now has RSI clearing the screen:

1. Clear to background button

2. Brush sizes

3. Don't regenerate while the mouse is down, wait for mouse up


1. Pushing now as an option to the vertical [...] menu (give it 10 - 20 mins) 2. Long press on the brush icon for brush menu. Can set brush size numerically or use [-] [+], also can use keys "[" and "]". We will put preset sizes on the list. 3. Does currently generate on mouse up, but pushing fix to wait 3s before generation.


Awesome. I'll get some lunch and try again. I'd really love to read about /how/ this works if that's something you'd be interested in sharing.


Yeah for sure. I'll write up a blog post, but here is my high-level overview for now. Ollie (ML engineer) from our team will fill in the technical details.

This works by using a “segmentation map”. Deep Learning models are really good at performing per pixel labelling.

You’ve probably seen the Remove Background tools that classify parts of the image either as background or foreground to make an alpha mask. But we don’t have to stop at two classes. We can classify an image with much more detail such as what parts contain an Eye, Ear, Nose, Mouth… etc. Passing an image of a face to a ML classification model can return a so-called “Segmentation Map”, which assigns a unique color to each class of facial feature. This kind of object detection is commonly used in computer vision for manufacturing assembly lines, but we want to use it for art...

Now this is where it gets interesting, we can play this in reverse, give the ML model a segmentation map, and use a GAN to generate the most convincing image of a face that it can (given the dataset it was trained on).

The really cool thing is that this isn’t limited to just faces, you can do this with landscapes, buildings, cars, cats you name it. Anything where you can train a model by classifying the segments or "features" of an image.


Got a "Login required" error in the Console. Logged in to massless. Still no dice.

Now seeing "redirectUri: "https://massless.io/app/auth" in console and spinner.


I'm getting 504s from the `v1/image/ml/segment-to-face` endpoint with the message "The upstream server is timing out". There were initially auth redirect messages in the console too, but they go away once you log in (as you'd expect).


yeah, I tried "logging in" too, it only helped someones data-harvesting, but not me wanting to fool around with this tool


Dev version while prod is down: https://unstable.massless.io/tool/face-maker-ai/


To the user that clicks only once, there's little value to show a random initial image and compute the corresponding result.

You should prob just always show the same image and cache the result, so the site can always load. Or randomize in a fixed set of 10 if you really like the randomization part.


Sketch to real spinwheel?


Can someone explain what is it doing, since it's not working?


It looks to be similar to Nvidia Canvas - there's a good demo of that online.

Basically the user paints where they want a feature to be using a colour. The AI replaces the colour with a feature and makes sure that any features touching eachother blend together beautifully to create a believable human face.


nice one liner


Yeah, it's Nvidia Canvas for faces, except not trying to sell you RTXs. Instead we're trying (when we load balance) to offer a realtime service through the browser. I have some more background in a comment here https://www.producthunt.com/posts/face-maker-ai


Realistically though owning your own GPU is going to be cheaper than a cloud host...


That was an anticlimactic spinner. I guess if you are going to post on HN you better make sure you can handle more than 1 request concurrently?


I think this is very cool, but also pretty scary. My attempt at giving one woman bangs just left her with a mat of hair on her forehead.


Interesting. I wonder why the authors decided to include segments for jewelery but omit beard and moustache.


Ah, we don't actually distinguish these. Just use "hair" if you want to draw on a beard or moustache.


Very nice API guys! thank you! I've created account to try it, but what about pricing?


Just found it on producthunt! thank you :)


kudos to @masslessdom and @oacstevens, we should be back up: https://massless.io/tool/face-maker-ai/


It looks very interesting, too bad it doesn't seem to work at the moment.


All the generated faces have soul-dead eyes.


some questions:

- on which dataset was it trained?

- how big is the model?

and finally: can one compare the result to just picking the closest faces from the training set?


It's trained with a mixture of publicly available datasets of faces. The final model is several gigabyes in size, so it's fairly large. Actually that's one of the reasons we've made this tool - to test our infrastructure with larger generative models.

The model is learning the features that make a convincing face, and generating a synthetic face from those (controlled by the segment map), similar to Nvidia's GauGAN.


Haven't looked into these, but what is the proposed advantage over just picking an image (with a much smaller model maybe?) from the database?


The power in generative models lies in being able to flexibly generate images that belong convincingly to a set (e.g. faces, landscapes), but that are not actually in the input dataset. E.g. you can make images that look like faces, but that don't belong to any real individual.


And where is the use of that? (I guess somewhere, we're at deepfakes et al, but this site still seems to advertise the concept)


So, hug of death it is.


Wont load, right part of screen keeps loading.


what a scam! if you regenerate without changing anyhting it does not rezz anything but a blurry nothing...




Consider applying for YC's W25 batch! Applications are open till Nov 12.

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

Search: