~ Paint By Numbers ~
To say A.I. has a mind of it's own is a paradox. In one sense, the statement couldn't be more true... but on the other hand, without an intelligence to guide the intelligence there wouldn't be much intelligible to ascertain.
I am probably going to get lynched for this post once the singularity occurs and A.I. takes over. Shhhhh
As a curator for the Alien Art Hive Community i've come across numerous posts that feature the use of generative art. In fact, generative art is one of our featured topics. There are numerous methods for using Artificial Intelligence solely to generate art as well as augmenting one's own work.
I will share some of those options and methods for you all to check out and play around with... but to be honest, most all of it has already been covered in depth by other awesome community members. I don't really feel like i have a lot of new information to add or share but i know there will be some folks on my blog that are not familiar with our Art community and the posts that have delved deep into this subject. So, i hope they don't mind me tagging them and adding their links.
Essentially, many of the most common methods could be linked and described here along with explaining the technical jargon but i will summarize it with an analogy of my own. Feel free to correct me in the comments below if necessary because i know this is a gross oversimplification.
Generative Art is basically using numbers to paint based on prompts that the A.I. uses pitting it's left brain vs. it's right brain against each other. This conflict refines each iteration and run to try and best come to the conclusion it deems to be what you asked for. I find it to be really cool that order is drawn out from mathematical chaos. Sometimes, it still results in chaos though...
~ Skynet Dreams ~
All the ways i have experimented so far have been free options. I am sure paying to play would produce faster, more efficient, and better results... but free ain't bad either.
There are two website platforms we will start with that you can try out and play around with for free (or upgrade to a paid service) if you want to. You don't have to know how to code or understand the technical terms because the platforms do most of the work. You just select what you want and input your options and press a few buttons and boom... you have art! They are easy to use and fun to explore.
The first one is ArtBreeder which has a bunch of cool options to try out. You should go and look and see what all you could do there to have some fun!
I made that portrait in ArtBreeder from a portrait i drew in pencil on paper. You can see the initial source portrait here below. The A.I. removed the piercing but other than that i really loved all the refinements. A very realistic recreation of my artwork that i was quite pleased with. I will probably tweak some of the settings and play around with all the options now that the main image is uploaded in there. It's crazy all the tweaking you can do on ArtBreeder.
I also made a post a long time ago called Giant Slayer and Artificial Intelligence when i tried out ArtBreeder for the first time. I took a character i drew and cropped his head and had the program make a portrait of him. Here is that outcome.
The second website is called DeepDreamGenerator which also has a lot of really cool features you can try out for free too.
I put in one of my old portraits that i did back in high school with Crayola Crayons, some ink pens, and i think some highlighter to move the wax around. It's a bit abstract so i thought the A.I. would have some fun with it and i was not wrong!
Here is the initial image i gave the program to work with.
I am currently still running the image back through to get to a deeper A.I. dream state... but so far i am on pass 5 of 13 on Dream Level 5. If i can get to 13 passes then i will level up to Dream Level 6 and have created a Rare Deep Dream! I will share the final result for you to compare at the end of the post.
Some have used one program to create an output artwork and then run it through the other program to tweak the art further. The fun and experimentation is really only limited by your own creativity. These tools are just now in their infancy and this technology is burgeoning... so hop on now and enjoy the wild ride!
~ A Lot of Help from my Friends ~
My primary method of Augmenting my Art with Artificial Intelligence has been through Google Colab Notebooks. @kaliyuga has a nice post with a Library of AI Google Colab Notebooks. She also created a community called The Latent Space for A.I. generated art if you are interested in joining the fun over there.
I have to take my hat off (if i was wearing one) to @jotakrevs for all his hard work refining and bug fixing code for many of those Google Colab Notebooks. He and i spent a good deal of time troubleshooting the VQGAN+CLIP with video options notebook. For some reason that one really seems to be the buggiest. For all of Jotakrevs hard work (which i imagine isn't completely finished yet) i am going to make him a small beneficiary to some of my part of the rewards for this post. Thanks bro!
As we speak (and i type) i am running the VQGAN+CLIP with video options notebook in the background. Hopefully, no bugs or code errors will pop up and i will be able to share that video with you all at the end of this post. It's actually the first time to get a video in this fashion.
I would recommend reading all the information in that notebook before giving it a go... and it may be helpful to play around with the original notebook to get a bit more familiar with the process first. You can find the regular VQGAN+CLIP notebook to play around with at that link. You will have to translate the page to English unless you speak Spanish, but that is not so difficult.
Prior to this video option notebook method, i was having to run the normal gamut of just the images produced from the normal notebook and then splicing together the timelapse video results in an editor after the fact. I would do a run, save the final image, and then use that image as the starting point for the next run and so on.
Here is an example of the normal and more cumbersome method i was using. This example uses 7 runs of around 400 iterations per run all spliced and edited together. I also added some music for effect!
Yes, that's right... i guess the A.I. at Youtube realizes the A.I. output is NSFW. So, you have to be logged in to view the video. I will be adding the NSFW tag just to be safe here. I did file an appeal as this is an abstract output of art that has no real discernable issues that would truly justify the restriction in my humble opinion.
(Looks like my appeal was successful and the restriction has been lifted! yay)
I wanted to also take a little time to mention a few other people that have been very encouraging and supportive to one another as we all try to navigate our way through this stuff figuring it out together!
@dbddv01 was the first person i saw that was using A.I. to tell a story with a theme. He used a theme to create a fictional city guide to a music city. You have to go check out his posts with that theme because they are part of what truly inspired me to go and play around with all this... and look where we are now! His last post was also incredible. Here is the link to his first post on the city Broozel and in there are links to the continuation of his story! Utimate City Guide of Broozel for the enchanted traveller lost in music. A Rare non-existing books.
@lavista was also clever enough to have a theme and use the A.I. as an illustrator for creative writing. I would highly recommend his blog and to check out all the old posts from the beginning! I think you will be more than entertained and inspired when you finish! Here is his latest post titled The Forest Chronicles- The Portals. The creative writing alone is worth the visit to go check out the content... but the augmentation of A.I. illustrations is the icing on the cake!
And last but not least... (sorry if i left anyone else off my list here) is @juecoree who i think had some wonderful success experimenting. His last post After the Apocalypse- AI Art and Experiment was really cool along with his post Inside the Dungeon- AI Art and Experiment.
Kaliyuga has probably been the most prolific of us all. Go check out the blog there linked in her name and see what there is to see. Quite the spectrum of content and topics artistically expressed!
Jotakrevs blog has some amazing art and commentary on the processes. I would highly recommend going and checking some of the content he has produced! His portraits turned out amazing.
~ A.I. for the Assist ~
I personally don't believe that Artificial Intelligence of any kind is going to replace the analog artist or traditional mediums and methods. In fact, i really think it helps encourage the creativity and artistic side in those that don't feel to be artists themselves. It seems to me that the assistance provided by machine learning and all the different digital methods to generate or augment art is quite useful and inspiring.
For artists that perhaps doubt their skills or techniques... these digital options can be used to bolster their creative efforts and possibly influence them to grow and develop the skills that are lacking by being able to see it firsthand. I know there is a real concern for automation and it's impact on many industries and many livelihoods.
I really don't feel that concern is merited in the realm of art. Not unlike digital photography though, many people who actually suck will be able to be the next Ansel Adams or Leonardo DaVinci though because of their dependence on technology to do all the work for them. So, i guess it's kind of a double-edged sword.
Personally, i don't mind if folks are heavily dependent on the technology to produce art so long as they add or contribute something to the process. Not everyone continues art when they are a kid and grows to develop the skills and techniques. I do believe that everyone is an artist and somewhere along the line they turn away from that part of themselves.
So, using A.I. for the assist or as your personal illustrator is a great way to utilize the modern tools at our fingertips. I would encourage everyone to get back in touch with that part of themselves and playing around with some of the links in this post might just be a way to get that ball rolling!
~ NFTs & Final Forms ~
A couple of weeks ago the NFT Showroom, built here on the Hive Blockchain crossed 10,000 NFTs sold by artists on the platform! It's a pretty amazing feat and milestone to surpass and i am honored to have a few of my NFTs in the lot of the first 10k sold. I have collected a few as well along the way.
For this incredible achievement the NFT Showroom is hosting a contest which you can read about here for the rules to participate. There is going to be a lot of Hive that will be given away in prizes for Artists and Collectors. As of writing this post, there are 11 days left to get your entries in.
The cool thing is you don't have to be an artist you can simply be a collector. I thought that was a cool way to reward those that appreciate the artworks by including them in the celebration contest.
So, with this in mind, i will be participating by minting an NFT from some of the art in this post. If you want to see what i have up for sale you can click here to visit my NFT ShowRoom Gallery.
I said earlier that i would share the video that was produced from the notebook with those options. I wasn't able to take advantage of the slow motion feature so i just edited it to the slowest speed and added some music! Hopefully, my appeal for this video will go through as fast as the first one and it will be available for all by the time this post drops!
I have been running that video feature notebook in the background for a second video and hopefully, it will go without a hitch. Time will tell... hahahaha I've been running it for about 6 hours so far.
Now that we are close to the end of this post... time did tell and the slo-mo feature didn't work for me once again so i improvised! Thanks to @clayboyn for helping me troubleshoot cropping MP4s coming through in the clutch! It kind of works out better since i was able to add music again. I'm still waiting for some of the editing features before adding that as a final touch here!
I did say that i would share the DeepDream Generator image here at the end like i said i would. Rare Deep Dreams are any dreams or artworks produced by the site which went deeper than level 6.
I made it to the 3rd pass out of 19 at level 7... well beyond the limits of normal sanity. I guess this artwork is like inception... a dream within a dream. Let me know if you see any Electric Sheep in there!
So, here is the first video produced from the A.I. notebook experiment. After much travail, i just decided to go with it and get it minted. This will be by Genesis A.I. minted NFT. I hope you all like it. If the first one is this cool i really look forward to experimenting and playing around for future projects.
To celebrate the NFT Showroom 10k event i have listed the last 7 of 10 minted Genesis A.I. artworks for auction. The auction will be for the next seven days so don't miss your chance to scoop them up for only 10 Hive a pop.
Here is the link to hop over there and check them out. If you want editions 1-3 it will be a bit more costly. I would go for the auction price if i were you.
https://nftshowroom.com/gallery/castleberry_ai-augmentation-creations_red-glow-ai-genesis-mint
So, with a long day of creating all that went into this post and more i am going to call it a night! Thanks for taking the time to stop by and check out what's been going on! I appreciate your precious time spent here with me! I hope you all have the best week ever! Until next time... Castleberry signing out!
Bob Ross
First of all, thanks a lot for your kind mention, and beneficiaries tip as well! (:
I'm very glad to see hoe at end achieved to make these awesome videos! To help with the bugs and technical problems have been a pleasure. By the way, you gave some advice to work with photography datasets and it has been very helpful, so thanks a lot!
And this is what I like more of this group of AI artist that have appeared organically, we help each other sharing our knowledge, helping to grow. I'm happy to see how along the weeks, the quality of the artworks of everybody is getting better and better!
Like the stuff you are showing in your post, it is pleasantly disturbing, and yeah I know, both adjetives are not supposed to be together, but hey, that's how I feel after look at them. Especially the last video, and nice zoom and rotation tricks by the way.
Regards and never forget your !PIZZA!
Hey buddy! Glad to hear that the dataset recommendation produced some good fruit for your labor! It has been cool to see how organic this group of folks has come together and how well everything has synergized. Hive has been quite the blessing in helping bring us all together!
I take pleasantly disturbing as the highest compliment when it comes to this stuff. If it's not disturbing a little... then it's probably not augmented or produced by A.I. hahaha
That last video was the one i was working on while we chatted yesterday. It's the first one to get a video saved in the end. Still have some tweaking to do in my next experiments. I wish it could have rotated the whole time... but beggars can't be choosers.... until they know how to choose right! hahaha
Thanks for the Pizza and all your help! Looking forward to you sharing your video. It blows mine away!
Cheers
Well we posted at same time this morning (European morning), so the video is already there hehe
Now i feel deceived, thought the disturbing stuff came from you haha just kidding :p
And yes your tips are helpful... anyway there is a long way to make look decent something that comes from sflickr dataset. I like too much the paintings I guess...
Regards!
There we are! I was just about finishing my mini guide kind of post with a lot of similar mentions and I got a notification regarding my mention :). Thank you for our mentions and the very kind words :). I will comment more once I have fully assimilated your work here, thank you for sharing it with us and hoping to see much more!
You are most welcome! This post was long overdue and a labor of love. I have a feeling it's just the beginning. I know we are all going to produce some amazing art with our digital friend A.I. I'm looking forward to seeing what all comes of this stuff. If anything, i am just glad we are all having a good time. Thanks for stopping by and taking the time to assimilate as well as comment!
Cheers!
can u make an ai art for me and grimes please? :)
I am sure i can. Gonna be a busy day today but here this week i will see if i can get something worth sharing! Thanks for stopping by and thank you for supporting the comments in this post as well!
Cheers
That was an awesome post! I agree that it is just the beginning. This is the most fun I have had with art in a long time, 🤪 .
Regarding your point about AI replacing/not replacing traditional art, I too feel that traditional art will hold its own and I feel traditional artists should be well rewarded too. Of late, that has not been the case....
Quote: I find it to be really cool that order is drawn out from mathematical chaos. Sometimes, it still results in chaos though...
As a Surrealist it is chaos I look for, or "method in madness". Or as Isidore Ducasse (better known as the Comte de Lautréamont) said: 'As beautiful as the chance meeting, on a dissecting table, of a sewing machine and an umbrella'.
For my own purposes, I find Deep Dream probably the best AI. I used it since it first started (back then, it only had one choice, Deep Dream), but since then you had to create an account and log in. It expanded into 3 different styles, plus you could upload your own images for styles, which I mostly use.
Since you are using Deep Dream you have an account, so you can check out mine here: https://deepdreamgenerator.com/u/artofthemystic/
I also used Deep Dream images in videos, one of them is Artists Eye, which I posted January 2019.
Another still picture I ran through several passes, but then cloned the portrait face back from the original in photoshop, and called it Muse in Deep Dream (best viewed full screen) - included on this page on my website: Deep Dream.
This is actually a clue that I had not posted my "Muse" on the blockchain (I wanted to link to it, but apparently I never did post it here - so: coming up shortly!). Since this was a 'reminder', I am running one of my old paintings through Deep Dream as we speak.
Hawaiian Selfie (1995) - Deep Dream
That shirt looks rad! Your Hawaiian Selfie looks a bit like Predator.
That's awesome you were reminded to create more and inspired by from this post. I have seen a bit of your Deep Dream generated artworks and it definitely adds a methodical layer of chaos on top of your art, which was already chaotic. I will have to check all the links and explore all the stuff you shared here in a bit.
I appreciate you dropping by and taking the time to comment so thoughtfully, as usual! Looking forward to seeing what you will share soon. I used the Fathomless setting and just adjusted the numbers of neuro links while deciding to rotate and/or zoom from time to time. That Rare Deep Dream image i got was pretty trippy... but your stuff is always trippy... A.I. augmented or not!
Cheers
Hi @castleberry,
Your post is a great synthesis of the state of the art so far. What a work and artwork !
It clearly demonstrates the added value an artist can bring when you just give him new tools, bringing back the original definitions of latin artifex, where the artisan who has acquired a technique, a mastery of execution and a know-how, allows him to skilfully produce a model or even to invent new ones; here in this case, we forge digital matter as raw material and our hammers are notebooks and programs.
Interesting to see that you touch the sensitive bias of NSFW detection algorithms. They are too sensitive to my opinion, but this might be my own cultural perceptions. But at least it shows how much work there is still to do in that field to cope with our human judgement and way to perceive reality, and also how dangerous massive filtering can become massive censorship.
For example, so far an Ai is still not able to perceive the Carmen music association to your "Red Spawn" clip, bringing to my perspective a much more lustful call to joyful pleasures than the Red Dawn clip. Altough the two pieces are sharing organic similarities, "Red Dawn" is a total different emotion because of the dramatic tense sustained by the musical layer.
We are far from a real AI takeover. The human added value is to my opinion still necessary to produce emotions and expressivity, otherwise we will loose nuance and freedom which is antinomic with artistic expression.
And also thanks for sharing the contests info, this is still a world for me to explore.
PS: I'm more than honored to be mentioned here but you are without doubts a community driver connecting people togheter and providing them support and motivations in a way that everyone is eager to continue exploring with you these new fields of expression.
That is an epic quote there! I have run some experiments using a photo as the initial input and my art as the target image... and vice versa. I will do some more playing around before i share some of those... but it proves your point from the quote!
I forgot to put the NSFW tag in this post but i don't think that will be an issue! Glad you picked up on that irony though of A.I. censoring A.I. hahaha That may be a greater example of the digital Right Brain vs. the digital Left Brain! The massive censoring and the lack of oversight is definitely one of the great challenges and problems of our time. I fear that if we don't get ahead of that it could get out of control very easily.
From a few techy people i know... the fear of A.I. is unwarranted at this time. However, the future implications are definitely worth being concerned over. Once again, it's something we should get ahead of before it becomes an issue like a Pandora's Box situation.
It was an honor to honor you in the post and honestly, if it weren't for you i may have not gotten on board this art train at this time. Your posts inspired me to delve in. So, thank you. I also appreciate your comments and thoughts on the videos with music overlayed. I wasn't sure if i liked the music added or not completely. I was pretty selective in my choices and felt like the music went with the art somewhat and distracted from the art a little.
I think there are 10 more days to enter the contest as an artist or a collector! The discord links are in the Weekly Community Curation post if you need any help. There is always somebody in the NFT Showroom discord to help you navigate getting set up as an artist and/or collector!
Cheers
I also appreciate your feedback on how the art moved you from one form to another. So, i do appreciate your thoughtful commentary!
Hi, wonderful post.
I have been using AI for a long time, I started with Artbreeder, and now with VQGAN+CLIP notebooks.
I like generative art, and it's not easy to place the right words to get the result you are looking for, it's hours and hours of trial and error.
Then I edit that image in Photoshop, it can be before, during or after.
Every time we use a notebook we are training the AI. In the future a person will just tell the AI, I want "surrealistic pink and purple digital art" and the AI, which is already trained, will make that art.
Artists by that time will be experimenting with other more advanced art forms. Because the artist is the essence of art.
You were the one i knew i was forgetting in my list to mention folks. You have had some amazing outcomes with your experience and it's been a pleasure to see your artwork.
You ain't lying there... and that's not including the tweaks in photoshop etc. I am still in the infancy of my explorations and it's nice to hear about everyone's experiences!
I was just mentioning about the training and if it's collecting a generated memory from all our experiments. Digital Neuro-Plasticity i think i called it. hahhaa
Thanks for stopping by and taking the time to check out the post and comment!
I also use art breeder and deep dream generator more and more as time goes on.
It's good to see you bro! Thanks for taking time to check out the post and comment. Those two are fantastic to get the feel for it as well as the itch. It can become addicting. You should check out some of those notebooks if/when you get some free time!
OK. I found some code on Github on the notebook link, but I'm not really sure how to use it. It's not self explanatory to me.
!LUV
<><
@castleberry, you've been given LUV from @mineopoly.
Check the LUV in your H-E wallet. (5/5)
Thanks for the love! You don't really need any codes from Github to run the notebooks. I think that is more for patches and fixing bugs or adding new features etc. The fact you actually found code on Github for it tells me you may be more advanced than me already! hahahah
Which notebook did you use or come into?
This is the one i would start with. I can't find the most basic one i use... but this one will do just to play with.
https://colab.research.google.com/drive/1sP-8FZdj_COwlF3Lbnz-URrwhAkm3qX-?usp=sharing
Basically, start at the top and hit the play buttons in each cell. Skip the extra storage features one for now.
You will see libraries... hit the play button there.
Then you will see models. Whichever one you select there and hit play to load.... will have to be the same model you use on the parameters section.
The next one is load libraries... hit play.
While those things load you can fill in the parameters. It's basically the text prompt part you will adjust. The presets are all mostly there and don't need to be adjusted. This notebook is set to run endless iterations so you can change that one to a fixed number or just stop it when you want.
The play buttons will spin until they are done. Then move on to the next one etc. I hope i didn't just confuse you more. Looks like we need to get a real HOW TO POST soon!
art breeder?
https://en.wikipedia.org/wiki/Seaman_(video_game)
Japanese really get into Sea men... oh sorry, semen.
Wow, that is really interesting. It is amazing how much AI has grown in the past couple of years. It is also kind of interesting how it is starting to find a place in the art world. It seems that is somewhere you would never expect it to have a home.
whose the bozz
Hey, it's good to see you Bozz! Thanks for stopping by. I agree, Machine Learning and all the A.I. stuff has boomed in the last few years and it's not slowing down anytime soon. It is counter-intuitive to think the Art realm has been one of the most proactive in using this style of interface. I guess it's kind of like a new medium. You would think the art folks would be purists about it... and i am sure there are many with that sentiment. But we don't see or hear much from them considering the traction this stuff has achieved.
Yeah, I guess it is kind of like the whole NFT thing. There are some artists who are against the idea, but there are many who are embracing it and thriving.
Yes, the NFT craze is a double edged sword. You have some great artists minting NFTs with little traction and you have some artists-so-called minting garbage and getting millions. Not unlike Andy Warhol pop-arting a can of Campbell's Soup. I guess we all just gotta get in where we fit in and hope for the best! hahaha
The illustration presented are interesting. And I also resonate with this statement:
AI doesn't replaces art as it is today, but only amplifies Art in a new way. Traditional means of creating art will here to stay, and NFTs and AI can help make it reach more audience than it does.
I never tried the video generation of the AI tools. I might as well try it out. Enjoy a slice of !PIZZA
Thanks for the pizza and for checking out the post and taking time to comment! I also appreciate you kind compliments of the outputs. You have some great success yourself! I agree that the A.I. and digital art is an extension of the traditional methods which will be and are here to stay. I don't think either is mutually exclusive. I think we are participating in a revolution of sorts.
Give the video stuff a try... but don't make my mistake and NOT SAVE the images of interest. When making this post i realized i didn't save many images and had mostly the video outputs.
Looking forward to seeing more of your experiments!
Cheers!
I'll definitely give the video a try, and take note to save the images.
I wonder if AI could replace digital artists one day as it is very capable to create art 24/7. Interesting nsfw experiments haha. I was never sure of what I was seeing though boob or belly button lol. But still fun to watch
I don't think A.I. will replace digital artists in a way that makes digital and analogue artists extinct or obsolete. But, there is technology just now blossoming that could potentially outperform as you mentioned due to a lack of time constraints or no need to rest etc. I guess time will tell though. Automation will be more efficient for some art applications in the near future. I kind of think of it like print media vs. digital media. Books will never completely become obsolete.
I think it may have been boob-belly buttons! hahahha I guess it may depend on where one works if that is considered safe or not! hahhaa
Thanks for stopping by and taking time to comment!
I agree on books never becoming obsolete. I am one of those people who prefer a physical book over a digital version anytime. And I bet there are many like me
I used that analogy because i knew how much you appreciate books and reading. I could be wrong, but i feel like that same principle applies to the arts as well. Thanks again for stopping by! =)
I just saw your discovering your interesting post on this IA which allows can allow to make the abstract with the concrete. I will try it all right away. Not being an English speaker I translate with google trad and before reading the posts I always look at the images before, at the time I thought they were paintings on canvas.
Goodbye
Thank you stopping by and taking the time to comment. I know English isn't an easy language so thank you for using translate and giving it a try. You can also use your native language and let me translate if it makes you feel better. I appreciate your kind words.
I look forward to seeing what you may come up with!
Cheers
Merci
Your article is very interesting, you have brought some fantastic examples. The A.I. can create procedures, automatisms, but it is the artist who chooses where to start, who cleans up the image, gives it added value. The A.I. in my opinion it should be considered as a 2.0 brush. It is also a style that perfectly matches digital art, NFTs. Compliments.
I think your comment was put it all very well. I like the 2.0 brush analogy. It's almost like a new digital medium as well as a new digital tool as well. I agree that the artist still reigns supreme, for now! hahaha
Thanks for stopping by and for your thoughtful comments!
The rewards earned on this comment will go directly to the person sharing the post on Twitter as long as they are registered with @poshtoken. Sign up at https://hiveposh.com.
Multiple auto-playing videos on the same post? Come on.
None of the videos autoplay for me when i open the post. You may need to change autoplay settings on Youtube. If you know of a way to change autoplay on my end, which i don't think is on, let me know @greatesteem I personally hate autoplay myself and i would definitely not put one, let alone three, to play automatically on any post.
PIZZA Holders sent $PIZZA tips in this post's comments:
@jotakrevs(1/10) tipped @castleberry (x1)
juecoree tipped castleberry (x1)
Learn more at https://hive.pizza.