Inside the Dungeon - AI Art and Experiment

avatar
(Edited)

We can't deny that artificial intelligence takes over how we deal with and operate the world. Arts have been subjected to AI too. There are tools that we can use to create digital illustrations and artworks or transfer art styles. One tool is VQGAN+CLIP, which I had been experimenting with for the past few weeks.

The first round of experiments was a disappointment. I get a digital illustration that is patches of the image used to train the model but, going through iterations, find out that we need to be specific with the concept and the art style. Throwing a word or sentence without a vision of art style can be disastrous to the output image. I think AI models generate illustration by relating our word prompt, and without giving a prompt for the art style throws a curveball to what we look forward to in the output illustration.

AI Art: Entrance to the Dungeon
a4vjWdK2Ch3FwYByu1eZ_out_out.png

After a disappointing run, I tried to be very specific with my prompt, accounting for what art style I wanted to see. So I tried to experiment with concept art and dungeons. I tried to have an initial prompt, the entrance to the dungeons. I am still disappointed with the initial results cause the digital illustration has patches of entrance signage. After changing the articles in the same prompt, I was able to get what I envisioned as the entrance to the dungeon.

After getting accustomed to how I should write my prompt, I continued experimenting with VQGAN+CLIP. The next phase was to create a series of illustrations that somehow tell a story inside the dungeon. Reflecting on that, I adjusted my prompt to what I look forward to in the dungeons' interior. I did add details like a pathway, monster, remnants of war, and others. It was a fun experiment, and I observed tendencies of AI from misspelled prompts to the art style. I was in awe of how two illustrations from misspelled prompts have similarities. I guess AI can still understand despite language errors in our prompt.

AI Art: Inside the Dungeon I
vkM1YjiGava8WTEYGbZ5_out_out.png


AI Art: Inside the Dungeon II
g018V0oOg6Cqqae8F1XX_out_out.png


AI Art: Inside the Dungeon III
85VmdmZR4zk1Xcy6MCjt_out_out.png

However, there are still illustrations that result in patches or tape of images from time to time. The output illustration is good, but I find it inconsistent with minor flaws from here to there. What I presented here is a more defined illustration. I added details and some elements in Photoshop and Illustrator to fix inconsistencies in the image. It ties up the digital artwork to what I envisioned.

AI Art: Healing well inside the Dungeon I
LPgvBw0j7DrzbkydzhaT_out_out.png


AI Art: Healing well inside the Dungeon II
5XdvA7WCBrSTEoByD3c5_out_out.png

I did another experiment to fully explore how I tie up my prompts to create an illustration. I did misspell words in the prompt like water well to water weel. I was astonished at how AI responded. At first, a misspelled prompt without context results in disruptive and bizarre patches of illustration. When I did put context like water well and water weel, the result was quite satisfying. It generates a correct representation, sometimes almost exactly similar output. It may be a coincidence since I may not try it for a handful of experiments, but, knowing it works like that, it was an awe-moment.

Also, I did run a similar prompt to see if AI replicates. I initialize the AI model with the same parameters and iterations. I run the experiment with different prompts. I wasn't able to see AI replicate the prior illustration. I couldn't fully understand yet how AI can work without plagiarizing, but it works. I did a reverse image search, and all digital artwork (non-edited) yields no match. Is that amazing? For me, it is.

AI Art: River inside the Dungeon I
BkFe13Ua3VSPa7CPpiqv_out_out.png


AI Art: River inside the Dungeon II
oZdQKHmiDQNQ3soUeL0l_out_out.png


Art is something that we make so that we understand ourselves better. It is an expression of our creativity and even craziness. Our definition of art changed from our ancestors' burned sticks to AI-generated or enhanced art. Some will argue if AI arts are art. But I think artificial intelligence is an ideal partner for us to create or enhances art. My digital illustration is base on AI, but these are sometimes out of context, and I still need to fix some lines, shades, or colors to tie it up. I guess this is the same for those who use AI for the arts. AI seems too foreign at first, but we can agree that it is still art.

AI Art: Inside the Dungeon IV
oCgnApKwSbZlSoSKXsV1_out_out.png


NFT Gallery
Check out Inside the Dungeon at OpenSea
Author's Note:
All content including digital illustrations is from the author. The illustrations are generated by VQGAN+CLIP (Notebook and Nightcafe), rescale resolution with Real-ESGAN, and added details and edited using Illustrator and Photoshop.





0
0
0.000
16 comments
avatar

I think these all turned out really well. Seems that these techniques are becoming quite popular here in the Alien Art community! Thanks for writing such a comprehensive post of your experiences while sharing the art along the way. I think you have a nice theme going and will be looking forward to seeing what else you create with the AI! Keep up the great work.

0
0
0.000
avatar

Seems that these techniques are becoming quite popular here in the Alien Art community!

Yeah, it is becoming popular in the community. I guess it is due to the creative freedom the community accepted and, with NFTs becoming relevant this days, AI arts or enhanced art through AI can be an easier way to join the artistic and creative journey, especially creating arts through traditional means takes longer (in my case).

I am glad to hear that you find the theme nice. I will gladly share more content and do engagement in the community. Once again, thank you! Enjoy a slice of !PIZZA

0
0
0.000
avatar

Thanks for the Pizza! Yes, it is cool how the AI art can help encourage people with fewer art skills or backgrounds to still engage and participate in creative processes making art. I think this journey has only just begun and i am looking forward to enjoying the ride with everyone! Cheers! =)

0
0
0.000
avatar

Congratulations @juecoree! You have completed the following achievement on the Hive blockchain and have been rewarded with new badge(s) :

You received more than 6000 HP as payout for your posts and comments.
Your next payout target is 7000 HP.
The unit is Hive Power equivalent because your rewards can be split into HP and HBD

You can view your badges on your board and compare yourself to others in the Ranking
If you no longer want to receive notifications, reply to this comment with the word STOP

To support your work, I also upvoted your post!

Check out the last post from @hivebuzz:

Feedback from the October 1st Hive Power Up Day
Hive Power Up Month Challenge - Winners List
0
0
0.000
avatar

I'm happy to see that you joined our VQGAN boat!

You have touched an interesting topic. This bad typos in the prompt. And yes, you are right, without context the AI can get lost, but giving one to it, most of the times figures what means that word that contains a typo.

Sometimes, a bad typo brings funny stuff. Once I wrote "monolithe" instead "monolith", when I was prompting "A monolith in the jungle, and they AI created some kind of little hairy creatures, that resembled a monkey.

After think a lot about it, I figured that as the AI didn't know that word, but I asked for it in the jungle, it concluded that unknown word should mean something that belongs to a jungle.

"Mono" means "monkey" in Spanish... "lithe" could be "little" with a typo... so I think that the AI brought me some little monkeys in the jungle lol

Thanks for share your experience and thoughts, If I can suggest it, I think that the MSE Notebook gonna give you more cohesivity and detail to the artworks, and you gonna have less problems about have to remove little inconsistences.

Regards and take this !PIZZA!

0
0
0.000
avatar
(Edited)

Sometimes, a bad typo brings funny stuff. Once I wrote "monolithe" instead "monolith", when I was prompting "A monolith in the jungle, and they AI created some kind of little hairy creatures, that resembled a monkey.

Yeah, I did experience this one too when I was trying to do experiments concerning misspelled word.

... "Mono" means "monkey" in Spanish... "lithe" could be "little" with a typo... so I think that the AI brought me some little monkeys in the jungle

That really interesting. I did some prompt that don't have known picture like "Before the Big Bang" and I get some weird stops and one iteration turns out just writing the word big bang in gibberish.

If I can suggest it, I think that the MSE Notebook gonna give you more cohesivity and detail to the artworks, and you gonna have less problems about have to remove little inconsistences.

I would try to explore the tool too. By the way, thank you for appreciating the content of this blog.

Enjoy a slice of !PIZZA and a glass of !WINE.

0
0
0.000
avatar

That really interesting. I did some prompt that don't have known picture like "Before the Big Bang" and I get some weird stops and one iteration turns out just writing the word big bang in gibberish.

Oh, interesting... it never happened to me, it writes gibberish often... but pure gibberish, it didn't write any word that could be recognized.

And you are welcome, your content is appreciated because deserves it!

Oh and thanks for the pizza and the wine, regards!

0
0
0.000
avatar
(Edited)

PIZZA! PIZZA! PIZZA! PIZZA!
PIZZA Holders sent $PIZZA tips in this post's comments:
@juecoree(2/10) tipped @jotakrevs (x1)
jotakrevs(7/10) tipped juecoree (x1)
juecoree(2/10) tipped ate.eping (x1)
juecoree(2/10) tipped castleberry (x1)
Learn more at https://hive.pizza.

0
0
0.000
avatar

All these images look nice. Thanks for sharing your process too.

0
0
0.000
avatar

Glad that you find the images good.

0
0
0.000