Garden journal notebook

Besides being an AI artist (and mind you: still a traditional artist) I create designs for products in my Zazzle store. I have been doing this since 2009. I used scans of my acrylic artworks, illustrations done with Inkscape, an open source alternative to Adobe Illustrator, and for almost one year now I have been using images created with AI Art generators. 

Just few days ago I created this notebook. The colorful tulips may encourage the use as a garden journal, but you can of course use it in whatever way you like. One of the big advantages of the Print on Demand platform Zazzle is that it offers the creators many ways to create a product which is easy to personalize. 

Colorful tulips Garden Journal
by ullahennig

Alebrije Style - tried with three AI Art Generators

I tried the same prompt with three AI Art Generators: Mage space, Openart AI and Leonardo AI. The prompt was:

aleprije style, man with hat, 

Originally Aleprije is not a style, but a way of crafting figurines in Mexico. The figurines are very colorful. 

So it might have been quite a challenge for an AI Art Generator to use "Aleprije" as a style. On the left you can see the image rendered by Mage AI.

The hat is colorful, and Mage even added some colorful earrings.

Obviously Openart AI did not understand "Aleprije" and simply generated an image of a man wearing a hat, although the hat does a bit look like a Mexican sombrero.

Leonardo AI, on the other hand, did quite well with the prompt.

I have been using quite a few AI Art Generators for some time, and more than once I try the same prompt on three or four of them. In my opinion the subject very much matters - and often I am pleasantly surprised by the result of one AI Art Generator which hadn't done well with other prompts. 

Merry Christmas!

When I was a child my father used to put up the Christmas Tree on the morning of Christmas Eve. I helped him to put all the candles, the ornaments and the christmas balls on the tree. We had real candles at that time. 

In the afternoon we went to church, and after church the gifts were put under the christmas tree, the candles were lit and then we - the children - were let into the living room. Usually we sang some christmas carols with me playing the piano. Later, when all the gifts were unpacked we had a meal which consisted of potato salad and sausages.

These times are long gone. I live alone, and I do not have a christmas tree. But I have candles, real candles, and I deeply enjoy them.

Feliz Navidad

 Most AI Art Generators fail in creating images with text in them. I tried quite a few and almost wanted to give up. Then I learnt that Dalle 3 seemed to do better. Bing Image Creator is based on Dalle 3, so I decided to give it a try.

I used the following prompt:

Text name “FELIZ NAVIDAD white polar bear, snowflakes, luminous poinsettias and a large luminous glass heart with colorful flowers, Watercolor, trending on artstation, sharp focus, studio photo, intricate details, highly detailed, by greg rutkowski full hdv0.2, 3d render, poster, typography, illustration

You can see the result on the left. Almost perfect, isn't it?

Cat is watching you

 

Colorful Ink art Cat Magnet
by ullahennig

Are you a cat lover and looking for cat magnets to enlarge the collection on your refrigerator? Then this magnet may be the perfect item for you! It is a magnet showing the cat in a certain style - colorful ink art.  

Peaceful winter landscape

 I love winter when the snow covers the ground, the sky is blue, and its cold. I love the noise my shoes make on fresh fallen snow. In the last years we in Germany had almost no snow during the winter months; this year was a bit different with loads of snow coming down in the South of Germany. Just now we're having a lot of rain and many grey days and I hope that will change a bit in January 2024.

Using Bard to generate prompts for AI images

Let us ask Bard first what he thinks he can do with creating prompts for AI Artists. Bard's answer:

"I can create prompts for AI artists that are both detailed and creative. I can also tailor my prompts to specific AI art models, such as DALL-E 2, Imagen, and Midjourney. ... I can also generate prompts for more specific tasks, such as: Creating an image that evokes a particular emotion, such as happiness, sadness, or fear...."

Well, I am a very curious person and someone who definitely likes to experiment. So I asked Bard:

Hi, I am an AI Artist and I want to generate an image depicting a snow covered garden in front of a modern house. Can you give me a prompt, please?

Bard`s answer is:

Create a vivid winter scene of a snow-covered garden in front of a sleek, modern house. The house should have a minimalist design, with large glass windows that showcase the snow-dusted landscape. The garden should be a peaceful oasis, with a winding path leading through a grove of snow-laden trees. The path should end at a small pond, where a frozen fountain stands majestically. The overall mood of the image should be serene and tranquil, reflecting the beauty of winter in the heart of a modern setting.

Now I looked for an AI Art Generator,  went to Ideogram AI.# and submitted the prompt. 

This is the result of the prompt as it is given above. The image is okay but in my opinion it is a bit too modern, something you would see in when somebody sells the property.

So I tried to get something different and replaced "sleek modern house" with "old house".

I must say I prefer this image to the first one. It almost looks a bit mysterious, and I definitely love the sky. 

By the way, you get three prompts (Bard calls them "drafts") and you can get more than those. 

In addition to that you can easily copy the prompts or create a google doc with them. 

Painted Stones

I've got quite a collection of Acrylic Paintmarkers, and beneath other things they can be used to paint on round stones. Of course the first thing to get are the stones. Then the question arises "What shall I paint on these surfaces?"

Well, here comes in Artificial Art Generation. 

This is an image I created with Full Journey. You can see birds, flowers and trees on the stones. In my opinion it is very inspiring and can give you many ideas what to paint on those stones.

So creating AI Art and traditional art is not an either / or. AI Art can help you with your traditional art projects quite a lot!

Advent wreaths

Advent wreaths are a very popular decoration item in German households. They consist of a wreath made by fir branches and four candles. The first candle is lit on the first Advent Sunday, and on the fourth Advent Sunday all four candles are lit together. You can buy those wreaths at flower shops and groceries.

But you can also make them yourself. When I used picFinder AI to generate an image of an advent wreath, I got this image:

I quite like this design. All you need is a wooden round tree disk, some fir branches, four candles and some additional items for decoration. It is easy to put together and easy to clear up when Christmas is gone.

This was the first time I learnt about the meaning of AI for design: Getting new ideas is - literally spoken - at your fingertips. 

St Nicholas

 

St. Nicholas, also known as Nikolaos of Myra, was a Christian bishop who lived during the 4th century in the city of Myra, which is now part of modern-day Turkey. He was born around 270 AD and became known for his acts of kindness, generosity, and compassion.

St. Nicholas is widely revered as a patron saint of children, sailors, merchants, and the falsely accused. Over the centuries, he has become the inspiration for the modern figure of Santa Claus, who is known for his gift-giving and benevolence during the Christmas season. Celebrated on December 6th in many countries, St. Nicholas Day commemorates his life and legacy.

Using Leonardo AI to refine your prompt

Leonardo AI has a great feature called "Prompt generation". You will find it when you click on "AI Image Generation". You have to take the following steps:

1. Insert a basic prompt, let's say: "Santa Claus riding a motorbike".
2. Choose the number of prompts to generate: Let's choose 2 prompts.
3. Click on "ideate"
4. You will get 2 elaborate prompts. One of these prompts is: In a modern twist on the classic Christmas tale, Santa Claus trades in his reindeer for a roaring motorbike. With a bag full of gifts strapped to the back, he speeds through the snowy streets, spreading holiday cheer with every rev of the engine.
   I can now save the two prompts on Googe Keep for later use or I can use one of the prompts to generate an image with Leonardo AI by clicking on "Generate".
   
   
   

 

Promptalot

Promptalot is a website for organzing and sharing prompts for Midjourney AI. I don't use Midjourney, but many other AI Art Generators. I am a very curious person, and so I want to know what happens when I use one of these prompts with Nightcafe Studio, for example.

The first step is to go to Promptalot and search for a subject. I searched for "Pattern" and one of the prompts I got was:

A digital artwork depicting a complex fractal pattern with a symmetrical design. The fractal features an ornate center resembling a blooming flower with a warm, luminous core of yellows and reds. This central motif is surrounded by intricate petal-like structures in a palette of blues, purples, and greens, suggesting layers of depth and texture. The background simulates a misty forest at twilight, with the soft silhouette of trees and a hint of a sunset in the distance, contributing to the mystical atmosphere of the composition

I copied the prompt and went to Nightcafe Studio. The result:

It definitely does not look like the image created with Midjourney. Nevertheless I like it. 

Now the question is: How about using Leonardo AI, or Ideogram AI, or Dreamlike AI or Deep Dream Generator AI? 

Or how about changing the colors in the prompt? Or shortening the prompt? 

For me the goal is not to create the same image as Midjourney would. For me the goal is to use the prompt as an inspiration to create something different, to play around.

Peace on Earth

 

This was an experiment done with Bing Image Creator. I wanted to find out which images Bing would create with the three simple words "Peace on Earth". 

The image on the left tells you that Bing did quite a great job. Not only did it combine "Earth" and "peace" but it also added the words as text - which is quite a revolution for AI Art Generators. The text itself is perfect.

All in all it produced a nice poster.

Bing Image Creator

 

I am absolutely fascinated by the quality of images you get with Bing Image Creator. I submitted the following prompt:

Striking, multi-hued crystal formation of a falcon with precise detailing in 3D, and a radiant sheen

And Bing pretty much did what I wanted it to do, as you can see with the image on the left.

However: you only get square images. Up to today I dealt with that problem in two different ways:

1. I uploaded the image to clipdrop.com and clicked on "uncrop" 2. I uploaded the image to limewire as starter image and used the same prompt as I had done with Bing.

Today I discovered https://redketchup.io/image-resizer, uploaded the image above and had it cropped with the aspect ratio of 2:3.

The next step would be to enhance the image. Of course, the image is cropped. But now I could have it printed in portrait format and put it into one of the usual frames.

How to organize your prompts with Google Keep

I also got a category like "sports" in Google Keep!

For quite some time I have been looking for an efficient way to organize the prompts for my AI images. I've got loads of them - some from ChatGPT, some from other AI artists, some of them made up myself. I like to try out the same prompt with different AI Art Generators, and I like to play with prompts, just change a bit there and there. That means I wanted to find a way to get access to them very quickly.

Using notion to store my prompts
In the first months of my AI Artist career this was a quick and efficient way. However the page got longer and longer, and the longer it was the longer it took for me to find the prompt I wanted to find.

Using Google Keep
In Keep you can tag your notes. The first tags I used for my prompts were "ai" and "prompt". But this was not efficient enough. So I thought of the way I organize my AI images on my hard drive: There I use categories like "landscape", "people", "surrealism", "objects" only to name a few. I decided to use the same categories for labelling my prompts in Google Keep, with one additional tag: "style". I apply this category for prompts which describe a certain style - like expressionism, or a certain artist and such. 

Creating Mockups for Your Zazzle shop

For quiet some time Zazzle is providing some Mockups together with the product you have created. However Zazzle encourages to create your own mockups, be it that you take photos with the product itself (which requires that you bought the product), or creating mockups using online mockup generators. 

Smartmockups.com
Smartmockups.com is a website which offers a lot of mockups - for mugs, t-shirts, cards and a lot of other products. Say you want to create a mockup with a mug. Select "mugs" and then "free" and you get all the free mug mockups you can use.

Which Zazzle products do you want to promote via Mockup?
Creating mockups is not very difficult, but it is time consuming. So I go through my store and look for products which I think could do with a bit of promotion on the one hand. Then I go to smartmockups.com and look which products offer the most free mockups.
After that I go to the product, go to "download" and download the design. This is the file you have to upload to smartmockups.com in order to place it on a mockup.

Edit your designs on the Mockup!
You can edit the design on the mockup - enlarge it or move it. Try to make it look as similar to the real product on Zazzle as possible.

Upload the mockup image to Zazzle
I have a free account on smartmockups.com which means that the images I download from there are relatively small. It could be that Zazzle requires a bigger image. However, there are several free photo enhancers on the web. Use one of them and then try it again. 

All in all, the process of creating mockups is time consuming, especially if you are just beginning to do this. So, as I said before, focus on the products you want to promote!

And here is one of my Mockups. You will find the mug here.

AI Happy Accident

With AI Art Generators you often do not get what you asked for. But sometimes you get what you did not ask for. 

See that beautiful woman? Well, I certainly did not ask for a woman in my prompt. The prompt reads:

Unleash your creativity with abstract cubism, as you experiment with different stylistic renderings and variations, from playful and whimsical to bold and dramatic, shades of red and orange, oil painting, intricate

Well the style of the image definitely is a cubist one. We also have shades of red and oranges. And we have a portrait of a beautiful woman. Obviously Leonardo AI unleashed its creativity and thought that it had to add the portrait. By the way, I like the image!

Creating Abstract Art with AI

 I love painting abstract pieces, be it with acrylicink, marker or any other medium. So why not create abstract images with AI Generators? 

The prompt for this image, done with Mage Space AI Art Generator is:

Immerse yourself in the world of abstract expressionism, where every brushstroke is a unique expression of emotion and energy, shades of blue, oil painting

I somehow like this image very much. Blue in all of its shades is my favorite color, and I also like the way lights and darks are distributed.

However I thought it might look nice if I added some orange, the colour from the other side of the color wheel.

So I changed the prompt to:

Immerse yourself in the world of abstract expressionism, where every brushstroke is a unique expression of emotion and energy, shades of blue and orange, oil painting

As you can see the orange itself is rather dark - in a next step I could change the "orange" to "yellow orange" and see what happens.

Focussing on the here and now

 

I am not a buddhist. However I learnt that Christian monks and Buddhist monks have one thing in common: They have learnt to focus on the here and now. 

Christian monks for example often have to do chores (such like sweeping the floor for example), and when they do them they focus on the task. They do not think what they will do when the task is done - they are doing the task and try to do it as perfect as possible.

It is the same with Buddhist monks: They have learnt to focus on the way they breathe, on the sounds they hear and so on.

I myself try to focus on the things I am doing now - just like writing this blogpost. In the past multitasking has been a goal for many - doing several things at the same time. I learnt that the human brain is not made for multitasking, and whenever we do it, we cause stress for our brain and for our body, 

Spartacus

What comes to your mind when you hear the name "Spartacus"? Well, I bet that you will be thinking of the film "Spartacus" with Kirk Douglas playing the leader of the slaves who could escape the gladiator school. 

I also know this film, and I was curious to see what AI would make out of the following prompt:

comic drawing of Spartacus | fighting,| front view, monochromatic blue and black | minimalistic simple shapes | smoke ink art 

Here is the interpretation of Leonardo AI:

Well, you cannot see him fighting because of the half body format; but he looks like he's going to fight!

Now I went over to Openart AI and changed the prompt quite a lot. It now reads: 

illustration portrait of Spartacus | expressive color palette; light blue and dark orange  | flat perspective | translucent planes | bone; dignified pose; kingcore

The Spartacus I got now looks very different (apart from the different style, of course)

I may be totally wong, but to me he looks like he knows that he and his comrades will not will the war but still keeps on fighting.

And none of them looks like Kirk Douglas, by the way! 

Ideogram AI

 When I look back one year, there were not many AI Art Generators in November 2022. I learnt about Midjourney, but it was not free, and I did not like the fact that it runs on Discord. I learnt about Nightcafe Studio and I immediately loved it and got addicted to the whole field of generating images with this Art Generator. 

Now, one year later, the number of AI Art Generators is still growing. A few days ago I watched a video in which Ideogram AI was given a try, and of course I had to try it, too.

I used the following prompt:
black cat in a colorful garden, folk art style, intricate

And here is the result:

You get four images with one prompt. The images can be saved on your profile page. Ideogram is free. You are offered a variety of styles,

I used this image as "a parent" and added a style to it.

Now the prompt is:

black cat in a colorful garden, folk art style, intricate, painting.

I can only invite you to visit Ideogram and play with it!

X and the Sharing of Prompts

For a long time I haven't used Twitter - sorry: X. I now and then tweeted a blogpost or one of my Zazzle Products. I presented my AI Art pieces on Facebook on my wall and in various groups. But a few days ago i found out that there is a very active AI community on X. Often users share their prompts either in the post itself or in the ALT field of the image they uploaded.

Another way to find prompts is by using the hashtag "#promptshare". 

One example: This is a prompt I found.

the neon pink and yellow pilcrow macpie caduceus by botticelli, minimal figures --ar 4:5 --v 5.2 --s 250

Now I like to take a prompt and tweak it a bit and then see what I can get. The prompt now reads:

the neon yellow and dark blue pilcrow macpie caduceus by botticelli, minimal figures And here comes the image:

Having fun with rubberducks

 

Everybody has a certain image in his or her mind when somebody says "rubberduck". So why not create images which show those critters in a strange surrounding?

This image was created with Nightcafe Studio and the following prompt:

a portrait of a rubberduck swimming in the bathtub, cubism, insanely detailed

The surroundings have changed quite a lot in this image.

And here is the prompt I used with Nightcafe Studio:

a rubberduck swimming in the bathtub, cubism style, insanely detailed

As you can see, I left out "portrait" in the prompt.

Halloween

 

I must admit that I do not celebrate Halloween. I am far too old for that. Halloween does not have a tradition in Germany - however why should kids not have fun with dressing up as witches, vampyres or skeletons? 

But I could not resist creating an image for Halloween - this time with Stablecog AI.

Have fun everyone!

Traditional Art vs AI Art?

 Many traditional artists reject AI Art. I consider myself a traditional artist also - having painted with acrylics, alcoholbased markers, gouache and other watermedia. In November 2022 I got in contact with Nightcafe Studio, and since then have created a lot of AI Art pieces. I must admit that for some time (actually some months) I did not touch a brush, opened a paint tube or painted with markers. 

But then I felt a rather heavy urge to do traditional art again, first with inktense pencils and then with acrylic inks. However I still continued creating art pieces with Artificial Intelligence Art Generators. For me it is not either that or this, it is both.

I like how I can apply acrylic ink on a surface (mostly watercolor paper) and how I can get various shades and hues by mixing those inks.

But I also like how to create images with words, to experiment with various art generators and the order of the words in a prompt. 

I am grateful that I have both ways to be creative!

The last days of October

 October is the month where days get shorter and colder; actually we here in Germany had some very warm and nice days - almost summer like. We also had some very wet and stormy days. Most of the leaves had been green for quite a long time, and then they turned brown and the wind swept them off the trees. 

However with AI Art Generators you can have your special collection of autumn images.

This image was created with Limewire AI and it reminds me of the region I come from, the South of Germany.  We have a lot of beech trees there on the Swabian Alb. 

You do not always see leaves as colorful as those on the image on the right are; as I mentioned in the beginning of this post this year the leaves stayed green for a long time and then turned yellow-brownish. 

However October is not over yet, maybe I will be able to see those colors in real nature and not only on an image! By the way, this image was created with picFinder AI.

Cute kitten Christmas ornament

 Are you a kitten lover and looking for cute kitten Christmas ornaments? Then this ornament may be the perfect thing for you! 

Cute Cat with Christmas Hat and red Christmas Ball
by ullahennig

Abstract Acrylic painting

It seems that Acrylic inks are one of my favorite mediums. I love the bold colors you can get with them, especially with the black lines between. 

I use empty yoghurt containers for mixing the colors in. I am eating a yoghurt almost every day, so I got stacks of these empty containers. 

I am still spending more time with creating images with AI Art Generators than with painting abstract pieces. However it is a nice change to sit down and apply paint on the surface!
 

Fuitbowl puzzle

 The days are getting shorter and colder. So why not spend your free time working on this puzzle? I don't think this puzzle is an easy one - there are a lot of details. In the end you will have a beautiful image of a fruitbowl with some juicy apples and grapes!

I've got other puzzles as well in my Zazzle shop. So come and have a look!

Colorful fruitbowl with apples and grapes
by ullahennig

Uncropping and cleaning up in Clipdrop

I love the quality of the images created with Bing Image Creator. However, the big disadvantage in my opinion is that you only get images in a square format. Now I want to decorate my home with my images, and that means that I have to put them into frames. Frames come in rectangular format like 15x10 cm. 

So I am very glad that Clipdrop offers the uncropping of images, which means that you upload your square images and Clipdrop converts it into a rectangular format, adding content.

This is the image created with Bing Image creator. I want to have it framed, that means printed it out in a rectangular format.

So I used the Uncop tool on Clipdrop.

I quite liked the result, but I was not so pleased with the yellow.white sphere on the left. 

So I clicked on "Edit" and chose the "cleaning up" tool. You now have a brush with which you can remove the parts you do not like.

Voilà, this is the "cleaned up" image!

Painting with acrylics again

 Now and then I like to take a break with AI Art and do some "traditional" painting. After a period of painting with my inktense pencils I now decided to grab my acrylics. I've got acrylic paint in tubes, in bottles and some acrylic markers. 

This one I did with some student acrylic paints - the yellow even is a no-name brand, I got the tube in a 1 Euro shop. 

It may sound funny but the fact that I can always use my paintings as starter images with AI Art Generators encourages me to paint. Even if the painting as such is not very good it still can be used to create something. 

(I actually used this painting as a starter image but that is a post on its own.)

New AI Generator: Full Journey

There are lots of AI Image Generators on the web, and there are a lot of changes going on. I once used Lexica, which now seems to be almost dead. I used Clipdrop for quite some time, and since last weekend their website seems to undergo a lot of changes and /or bugs.

On the other hand, there is always something new to try out and explore. For example there is Full Journey AI. It is a bit similar to Midjourney because it only runs on discord, but the commands are different. There is a free plan which gives you 50 tokens / credits every month. 

I quite like the quality of the images. You get four images with each prompt, like with Midjourney AI.

The prompt for this image was:

still life with crystal glasses, in the style of Rubens -43

The second thing which I was very pleased with was the quality of the service; I asked a question regarding how I could get the info about my remaining tokens, and it did not take more than 5 minutes untill I got the answer. 

Bing Image Creator and Dall-E-3

Among the many AI-Image Creators I have been using Bing Image Creator is the only one which has been using Dall-E. A few days ago Bing upgraded Dall-E to Dall-E-3. I have noticed quite a few very positive reactions to that and so I had to try it myself.

I used the prompt: 

still life with a glass vase and a glass pitcher, cinematic photography, intricate

And look what I've got! It is an image in the style of a still life, with one glass vase and a glass pitcher. 

Now I like to change my prompts a bit and see what happens. So I removed "cinematic photography" and added "in the style of Rubens".

Okay, there is more than one vase and one pitcher. 
However we have some beautiful juicy looking fruits and a beautifully painted background. As far as I can see, it looks like a painting Rubens could have done. 

Abstract Inktense pencil artwork

Today I finished this abstract piece done with inktense pencils. I used a colorless blender alcoholbased marker and a light grey alcoholbased marker to blend the pigments of the inktense pencils. 

The advantage of using alcoholbased markers to blend the pigments of the inktense pencils is that you can use cardboard as surface. 

Uncrop tool in Clipdrop

If you are using Bing Image Creator you will have noticed that it only offers the square format for the rendered images. The quality of the images is quite good. However I like to put my photo prints into frames, and the standard frame for photos are 4:3 or 3:4 sizes. 

Lately I watched a video about Clipdrop and I learnt that Clipdrop has a tool which makes it possible to change the format on a rectangle image. It is called the "Uncrop" Tool. I had to try it and was very pleased with the result. 

This image was created with Bing's Image Creator. I love the colors, and the flowing shapes. I'd like to use it for a selfmade card or frame it and hang it on my wall. 

But, as I said above, I could not find any frames for the square format.

So I had a go with this image and the Uncrop Tool on Clipdrop's website.

This is the 4:3 version. Yes, the image is smaller than the square one: I have a free account and that means that the image is downsized when using the tool. 

However, Clipdrop itself offers a tool with which you can enlarge your image, so that will be no problem. 

Styles in Clipdrop

During the last days I have focussed on Nightcafe Studio and ClipDrop AI. Nightcafe Studio offers SDXL 0.9 and ClipDrop offers SDXL. Whereas in Nightcafe you pay with credits, in ClipDrop AI you get 100 images per day in the free Account. 

You can choose between various styles in ClipDrop (and various aspect ratios as well). I used the following prompt:

 PROMPT: Beautiful glass sculpture of a dove, intricate, realistic

I chose Photography as style for the first image, and Fantasy Art as style for the second image.