As some of you may know, I've been obsessing on AI art for the last several months.
The ability to quickly create unique graphics from text alone with no artistic experience, training or equipment is a game changer for many people. From concept art, technical diagrams, icons, avatars and pixel art to full blown intricate 4k+ wallpapers and even movies, this technology is incredibly useful and flexible and will change the world in ways we don't even fully understand yet.
The energy, innovation and excitement around the explosion of AI art tools reminds me of the very early cryptocurrency space with the notable difference that almost everyone that uses it "gets it" - they understand the value, without needing an extensive education about WHY it exists.
Everyone can appreciate a nice picture, but very few understand hyperinflation or the broken economic system they're trapped in.
Like every new technology that grabs my interest, I've jumped in head first and started creating tools that attempt to be useful for others whilst also giving me a hands on learning experience to give me a deeper understanding of how it all works behind the scenes.
My latest attempt is a discord bot that allows anybody to generate high quality graphics via discord, even if all you have is a phone.
Join my discord to use it (18+ NSFW) - https://discord.gg/DSdK9KRJxq
Open source code ftw - https://github.com/ausbitbank/stable-diffusion-discord-bot
Full documentation is still being created, but this post should serve as a ...
Basic guide to getting started.
The simplest way to get started is to join the discord server , enter the "artspam" channel, and start typing /dream
You should see "arty" bot with an anonymous icon similar to this, click it:
Then just enter a prompt for what you'd like to see. Prompt-engineering is an art form in itself, but even a novice can get some amazing results.
There are lots of options available for advanced users to really tweak the generation process, but its all optional - all you really need is an idea/prompt
You make your selection(s), and send the message and you'll see your request get added into the queue
A few moments later you'll get your result in a message similar to this
You get a bunch of info with each render that will allow you to recreate the results elsewhere.
The icons from left to right on the top row mean:
brain: Who we should blame/credit for this creation
seed: A unique number representing the random noise this image was made from (!)
scale: How hard the ai should "force" the prompt (default 7.5)
steps: How many iterations did it try to create the image (default 50)
time: How long it took from request, until receiving the completed image
filename: unique filename for this render (can be referred to later as a template)
sampler: the specific sampler used, advanced feature
coin: the credit cost of this render, and remaining balance (see below)
The buttons below the image and prompt mean:
refresh: Make a completely new interpretation of the same prompt
10% variant: Make a similar image, with 10% variation from the last one
template: Use this render as a template instead of starting from random noise
edit: Open a dialog to let you easily modify the prompt and re-render
random: Pick a completely different prompt from our library of random prompts
How the credit system works
I always intend for this to remain a free system for some level of basic use. Any hive user should be able to come get some unique graphics created for free .
However, rendering does have a cost even while the whole system is currently running from my home computer with an nvidia 1080ti gpu. I've made a basic credit system to attempt to lower abuse and stop a single user from dominating the render queue. It will evolve as I observe usage/abuse patterns.
The basic "rules" of the system right now are:
1credit =1image at the default settings- Every new user starts with
100credits - Users with a balance below
10credits will get a free recharge of another10, twice a day - Users with a balance below
0are blocked from rendering till they recharge
I've tried to keep the costs connected to the actual resource costs of rendering time, disk and bandwidth requirements of each tool. The specifics can be found in the source code here
If you require more then the free credits each day, or you just want to support the project you can send any amount of HIVE or HBD to ausbit.dev with the memo recharge-YOURDISCORDIDHERE.
You can get your unique memo code from the bot by typing !recharge, or by just trying to render when your balance is empty.
- HBD will be redeemed at
1USD each - HIVE will use the live market rate from coingecko
1USD buys500credits
Any earnings will be saved in the account to be eventually used for a long overdue GPU upgrade that will improve render times for us all.
Conclusion
There are way too many features to try to document them all in a single post, but I'm hoping this is enough to get some people interested enough to come experiment for themselves. I'll do my best to answer any questions in the discord server or the comments of this post.
Please don't spend money you can't afford on credits, and even though this bot has already been generating 10's of thousands of images for a month+ already you should expect occasional (minor) bugs as I continue to refine a running system.
Come have some fun, make some art or memes and help test out the bot so I can fix any remaining bugs. I'll also give upvotes, reblogs or free credits to anybody writing quality posts to help promote and/or document the project.
Do you think this service to create royalty free images for your hive posts is valuable ?
That bot is amazing!!
This is just awesome!!! I work at stability.ai and have been beating the "AI art is gonna be a big effing deal" drum here on hive for two years now. Amazing to see you integrating Hive and stable diffusion in such a clever and powerful way :)
I joined midjournery server, I am yet to generate anything there. I am excited to see what arty will come up with. But I wanted to know what you think the future of illustrators will be in thins new future with AI illustration. Recently an art competition was won with AI and the artist that participated were all so heartbroken by this.
In my unprofessional opinion, I think that people will develop a bigger appetite for better art works.
I see it as just another tool that creative people will use to advance art even further. This could be a new renaissance, I understand the fear from some artists but a famine/competition based mindset will only make this transition more painful. There's no putting this genie back into the bottle, its better to evolve with it imo
Well said. Things like this have never stopped people from achieving things in life. I'm currently taking an art course. I plan on reaching a respectable level with my digital art and then incorporating AI into it.
So this AI page you have going on is like a testing phase before making a website or a side project?
Totally agree, I always try to understand why people complaining every time new tech coming and some people feel threaten by that. There's no point to fight against advancement, human need to constantly adapt and overcome to whatever coming to their life. Challenges sharpen us.
Next week we have to get you set up to accept lightning payments too 😎
Done, the bot now accepts lightning network payments - thanks for the help :)
I just played around for about 2 hours lol. Such an amazing bot and great sink for my hbd.
Love it!
Fun! I have been playing with midjourney the last 2 months. But I am always getting in trouble for using banned words. 😂😇
Dude! This is so incredible!!! You're making a big contribution to the people who would like to create awesome pictures without graphic design knowledge. My respects, I'm just testing your bot 💪
Best thing ever! can only recommend it!
This is fun. :D
Wow I actually find the bot so fantastic. Keep it up man. Your post are always amazing that's why I love reading them. Once again I say, keep it up. Your efforts will not go in vain
Do red corvettes usually have a yellow stripe through the middle? Seems like the easiest bit to get right, would be making the car completely red.
I was curious about this so I had a look at the clip database https://rom1504.github.io/clip-retrieval/?back=https%3A%2F%2Fknn5.laion.ai&index=laion5B&useMclip=false&query=corvette
"corvette" has a bunch of yellow results and stripes like this
So it ended up with the concepts of sports car+yellow+stripe+red on this roll, click refresh and it'll be totally different :)
The rewards earned on this comment will go directly to the people( @wanderingmoon ) sharing the post on Twitter as long as they are registered with @poshtoken. Sign up at https://hiveposh.com.
Generated this on midjourney. You can probably sell these irl.
What do you mean you can "probably sell this"?
You can only sell it if you pay for the subscription on Midjourney.
I don't mean as an NFT.
It would look fantastic as wall art. I have already downloaded a few of my prompts to hand on my living room wall. I could sell some to my friends.
Source: https://www.creativindie.com/midjourney-ai-for-book-cover-design-how-is-this-legal/#:~:text=EDIT%3A%20if%20you're%20using,paid%20version%2C%20then%20you%20are.
What a aweome tool it is! mind blowing. With the development of technology, tasks are becoming easier. We like your efforts. It will make graphic design easier. Thank you @ausbitbank, really appreciated
Very cool bot, have to try it :)
very interesting project :)
I have hear about AI writer but not AI art. Seems eventually AI is changing the world
This is super and thank you for making it so open for the Hive community. I tried stable defusion on my home PC but will need to upgrade first.
Wow that's cool, what a project
I think it's time to try! 😎
"Application not responding" - gives out like this. I wanted to try. Very interesting
Try again maybe you had unlucky timing to try during a script update
Very neat idea and a cool set of features, wonder if InvokeAI can compete with Midjourney someday.
Keep an eye on the stabilityio guys and Emad https://twitter.com/EMostaque
They already absorbed a bunch of midjourney/openai staff, I'm really excited to see what comes else out of these guys, I think they will be a much bigger deal then midjourney soon
I think this project has a lot of potentials. You can even create a new coin connected to it.
I gotcha. Watch this.
I'm on my way to your discord server but first a posh share.
😁😁😁
https://mobile.twitter.com/Farmsteader/status/1574240260543991815
Congratulations @ausbitbank! Your post has been a top performer on the Hive blockchain and you have been rewarded with the following badge:
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
STOPCheck out the last post from @hivebuzz:
I've been loving my journey on midjourney, I think it's obvious...
Wow I find that your bot so amazing.its fantastic bro. Well done. Keep it up 👍
Amen
It's definitely possible, and the ideas are cool enough the it feels inevitable
A few months ago, a friend messaged me asking for my opinion about the AI-generated arts.
He wanted to know what I will have to say about such inventory since to some it seems to be some kind of a threat to their hand-sketched works.
I really wouldn't say AI-generated art is a bad idea, I mean it can help save us time and stress of having to work painstakingly on art and the details.
But again, doesn't this lack some kind of originality? I mean the bot having to generate arts based on what we text it? I don't know anyway. But both ways, AI art is good.
A great post which I love throughout my reading, what a bit you have created and this will really help people that wish to check it out
Ohh, so it's you.
You're the one who is responsible for those that amazing AI art that I've been seeing lately. 😍
GREAT JOB!!!
I am personally interested how the AI generates those wonderful images. For example, how does it generate, like, the clouds. Do you store a bank of raw graphics that would be fetched and modified by the BOT or the BOT draw them from scratch?
Sorry, I am a bit lazy to browse the code. 😊
haha I can't take credit for that I'm just making an interface to the Stable Diffusion ai, I don't need to store any graphics just a ~7gb AI "brain" (+ hundreds of gb's of python libraries to support it). It was trained on a massive collection of images scraped from the public internet, heres some more info https://waxy.org/2022/08/exploring-12-million-of-the-images-used-to-train-stable-diffusions-image-generator/
Ohh. I thought you're the one made it. 😁
Anyways, you still did a great job for making the interface and sharing it with us. 😊
Thanks for the answer regarding my question. I will read and try to understand about this Stable Diffusion image generator.
First and foremost in my days of living on this earth, I have not heard of Artificial Intelligence Art and i am a temporary artist. But with what i read @ausbitbank I wish to learn and please i didn't really understand much can you break it down for me a little.
Best way to learn is to try it for yourself by joining the discord server with this link https://discord.gg/DSdK9KRJxq
And have a look at the artspam channel
Alright I will
Amazing
Dear, @ausbitbank
May we ask you to review and support our @cryptobrewmaster GameFi proposal on DHF? It can be found here
If you havent tried playing CryptoBrewMaster you can give it a shot. Our @hivefest presentation available here on the YouTube with a pitchdeck of what we building in general
Vote with Peakd.com, Ecency.com, Hivesigner
Thank you!
Voted :)
thanks mate!
Wow, thanks a lot for this! I recently got into AI, and it’s so much fun. I’ve played a little with midjourney and stable diffusion.
I’ve used up my free credits in midjourney already and was a little sad, because I don’t have a bank account with which I could pay a subscription ^^ so it’s awesome that I could pay you in Hive!
Will definitely have a try the next days!
@ausbitbank,
I just found this post, from the old Ramble Discord... (Think PYPT). How cool is this?! Beauty is indeed, in the eye of the beholder. And with so many people trying to find positive, new, and relative images (without the plagiarism involved) I think this is pretty snazzy!
That's what it's all about... right? Not only learning but also sharing with others to help the blockchain? You... are awesomesauce...
!LUV
The bot is amazing I have installed this AI on my pc but here in discord it makes it much faster, good initiative, a question and you can install this bot in a personal discord or another community of artists?
Sure can, arty can be invited to other servers or used via direct messages https://github.com/ausbitbank/stable-diffusion-discord-bot#add-arty-to-your-discord-server-easy
Hi. From the comments it seems to be a marvel. It seems to me an excellent alternative, for our publications and similar activities. Does it feel the same sensation as drawing freehand? I will give it a try. Thanks
Translated with DeepL
You're doing absolutely amazing 👏!
This is cool. in fact crazy. @ausbitbank thanks for this.. I'm excited already. I'm saving this post for future references.