Subscribed to my new newsletter? Comment here, and I will give you access to the course "Newsletter Freebies" in our classroom. It is a collection of beautiful women's prompts, which will grow over time! Didn't subscribe yet? Let's go! Click here and subscribe!

I went from this idea to the first sale of 99$ just in a few days! In this post, I want to share my path to it with you and also celebrate the good news! In my courses and in communities, I share my personal experience, and because I've been working in the education space since I was 17 (I was a school and private teacher for a long time), online work for over 10 years, and with AI 1,5 years, it was time to create a community for AI educators (like myself)! But first, I validated my idea here in our community with a poll, and most people said they would be interested in such a paid community. I did NOT create a new paid community immediately! It costs 99$ a month to host a community, and I am paying for this community already. Before I start a second one, I wanted to have even more validation. And what shows you more interest than a payment email? 😊 So, I created this landing page for the new "Stellar AI Society" community and decided to pre-sell a "Lifetime pass" with a one-time payment! I would start the paid community for 29$/month, increase then to 49$ and 99$/month. But before the launch on 01.03, I will pre-sell lifetime access and see if someone is really interested enough to pay for it! If there would be no pre-sale, I would not start this community on 01.03. Probably I would grow my audience and my subscriber list more and try again later! I sent an email campaign to my tiny list of 202 people and made a few posts on Twitter. I was so tired from all the work in the last days with the landing page that I needed a nap.😅 And I woke up to the first sale of 99$! That was super exciting! Luckily for us all, a member of my email list decided to give it a try and purchased the 1. pass. That means 3 things: 1. The new paid community will be launched for sure on 01.03.24. 2. This means a ton of work in the next few days and in the future for me, but I really love it! 3. This means that if you are interested in this community for AI course creators, where I will teach you strategies like this and provide you with useful templates, Get your lifetime access now!

A beautiful woman with pink hair in nature, pink colors,, a purple space background with stars and glitter, felicia simion, in the style of joel robison, atmospheric ambience, bokeh panorama, gravity-defying landscapes --chaos 40 --ar 3:4 --stylize 700 --weird 0

MJ has a new update: (source: Midjourney's Discord server) David Holz: "Hey @everyone we're releasing our first test algorithms for 'Consistent Styles' today. We're calling the feature "Style References". They work similarly to image prompts where you give a URL to one or more images that 'describe' the consistent style you want to work over. How to use Style References - After your prompt type --sref along with a URL to an image --sref urlA - Our system will look at the image URL as a 'style references' and try to make something that 'matches' its style or aesthetic - This works for both V6 and Niji V6 (it does not work with V5 etc) Advanced Settings - Use multiple urls to multiple images like this --sref urlA urlB urlC - Set relative weights of styles like this --sref urlA::2 urlB::3 urlC::5 - Set the total strength of the stylization via --sw 100 (100 is default, 0 is off, 1000 is maximum) - Regular image prompts must go before --sref like this/imagine cat ninja ImagePrompt1 ImagePrompt2 --sref stylePrompt1 stylePrompt2 Please Note: - We'll likely update this in the next few weeks (and it may change things so be careful while it's all in alpha). - If your prompt tends towards photorealism and you want a conflicting style like illustration you may still need to add some text to your prompt saying so - Style References have no direct effect on image prompts, only on jobs that contain at least one text prompt - Our plan will be to add a "Consistent Character" feature at later date that works the same with a --cref argument. Please play around with this totally new algorithm and share results in ⁠sref-showcase and tell us what you think in ⁠ideas-and-features" I am testing it out. Here are 2 images the second one is MJ vanilla, the first is with style. I used 2 images from my blog post to make this style. Prompt: illustration of a beautiful woman with short red hair and green eyes wearing a black lace dress with white pearls --sref https://s.mj.run/GuyBDpHw6A0 https://s.mj.run/ymYolYZ_BAc --sw 500 --ar 3:4 --s 700 --v 6.0

I paid for MJ. Not going to switch since it is too good. However, I tried Leonardo Alchemy for free last week. It has many parameters to play with. And the real-time generation is fun to use. Can anyone tell the major difference between MJ and Leonardo?