AI On My Mind #3: World Art Nouveau Day

Today, June 10th, is World Art Nouveau Day. My recent photo of statues in a Laotian Buddhist temple is about as far as you can get from the Art Nouveau movement. So it is a perfect image to play with in AI image generation software. I have used three online sites, two of which I discussed in previous posts: ImgCreator.AI, Dream by WOMBO, and Night Cafe (https://nightcafe.studio/). Using the image above as a visual and short text prompts, with or without the addition of styles, AI came up with some interesting images. I am amazed at the variations and perplexed by some of the cultural missteps, and amused by the mishmash of body parts.

Art Nouveau – maybe

Night Cafe: Using a Start Image In Night Cafe requires at least a one word text prompt, which can be selected from the Advanced Prompt Editor or provided by user. I think the first image is my favorite. Art Nouveau as a text prompt produced mostly female subjects.

Dream by WOMBO: Dream allows an optional Input Image but the image shape is limited to 9:6 online; the image must be cropped to fit the dimensions. Only the left side of the original image was used. At least one text prompt is required with an image. A small selection of Art Styles are available.

ImgCreator.AI: Allows only Text Input or Image Input, with the addition of a category and a style for each create command. I was not able to apply an Art Nouveau prompt to the original image. The category and style menus are limited under Image Input.

Image Input Only

Text Input Only: Art Nouveau

Note: This post is one of a series in my attempt to forestall becoming a uninformed Luddite with regard to artificial intelligence (AI) and its positives and negatives when using existing images instead of just text to generate new images. I’ve decide to explore some of the current software options. Many free programs are available, though free is a fluid term. To produce higher quality, higher resolution, and sharper images, many programs charge credit based “fees” or require subscriptions.

AI On My Mind #2: Dream by WOMBO (https://dream.ai)

This is my attempt to forestall becoming a uninformed Luddite with regard to artificial intelligence (AI) and its positives and negatives when using existing images instead of text to generate new images. I’ve decide to explore some of the software options. Many free programs are available, though free is a fluid term. To produce higher quality, higher resolution, and sharper images, many programs charge credit based “fees” or require subscriptions. I plan on using the same image of my nephew and grandniece as the starting image, if possible. If only text to image generation is available, I will use this prompt: Young bearded man wearing a blue shirt sitting outside on a porch holding his baby daughter. 

Dream by WOMBO uses text and image prompts in it AI image generation. With the optional image prompts, though, there must be at least one descriptive word in the text prompt box. I used all three prompt options to produce the results below. Dream has a free level which provided one image for each image generation request and has ads. Monthly, annual or lifetime premium plans are ad free.

Image and One Word Text Prompt

The optional Input Image is used as a reference for the final output. I was surprised at the diverse images generated. The only difference was the text prompt word. The colors reflect, though don’t necessarily duplicate, the original photo

Groovy Times. Not sure what the baby is holding in the generated image. It looks like a small fence post.

Image and Full Text Prompt

Text prompt “Young bearded man wearing a blue shirt sitting outside on a porch holding his baby daughter” and the original input image. I picked a style for each new image created. Some “create” actions produced a mishmash of strange lines, colors and body parts. One action produced an NSFW Content warning, but I don’t know why because only the style selected had changed, not the text prompt.

Anime. Notice the lack of distinction between the arm of the father and the child. This happened in several images and in other AI generation programs. Body parts can come and go or be missing all together. Try different styles. The baby in the Analogue image below is scary with a touch of a beard and crazy eyes.

Text Prompt

Text prompt Young bearded man wearing a blue shirt sitting outside on a porch holding his baby daughter. I selected different styles with the text. I was surprised that in some images, the child was missing. I love the details, such as the earring in the first image. The baby looks a bit possessed because the light reflections are in the whites of the eyes. And the father’s hand on the child’s back is child-sized.

Realistic

Edit Image (BETA): Edit with Text

You can describe a change you would like to see in an image you upload. I am not sure which image formats it will accept. It felt strange to use words to tell a program home to modify a face. In the Edit with Text box, I entered “make beard on chin longer.” A thick dark beard was added. To me, Jeff’s entire face now looks more AI generated than realistic. It doesn’t feel real to me.

I learned a hard lesson about using a program I don’t know well. While I generated lots of images, I didn’t save them as finalized. So, when I closed the program and went back to review the styles I had used, the images were no longer there. Luckily I had downloaded the ones I wanted to used. Some of the style captions may be incorrect. New images are saved and downloaded as .jpg files. If there are any any FAQs, guidelines, or manuals, they are well hidden. Maybe you need to be a premium member to access. The free version is basic and generally intuitive.

AI On My Mind #1: ImgCreator.AI

This is my attempt to forestall becoming a uninformed Luddite with regard to artificial intelligence (AI) and its positives and negatives when using existing images instead of text to generate new images. I’ve decide to explore some of the software options. Many free programs are available, though free is a fluid term. To produce higher quality, higher resolution, and sharper images, many programs charge credit based “fees.” I plan on using the same image of my nephew and grandniece as the starting image, if possible. If only text to image generation is available, I will use this prompt: Young bearded man wearing a blue shirt sitting outside on a porch holding his baby daughter. 

ImgCreator.AI (https://imgcreator.zmo.ai/)

I generated five different image styles using the base image and one based on the text prompt. Each try produced two images, one of each is below. I was charged 10 of my free 60 credits, but I am not sure for which image.

“Oil painting” Because the image does not clearly show the my niece is female, the child appears to be a boy in all but one instance.

“Illustration variation”

“Anime to photo” This is the most photo realistic but I think it is because I selected Anime as the category when the original is not.

“Anime Art” Most of the Anime options when using an image as the prompt are “girl” styles. Both figures are feminine.

“Anime Colorful” For the most part, the new images have a blue or dark shirt, a short beard, wavy hair and a lovely sunny background.

Text: Young bearded man wearing a blue shirt sitting outside on a porch holding his baby daughter. The two text based images. They are very different from the original. The second image added a woman and a pet.

Generally, I am pleased with the quality of the new images. The one negative for me is that without being able to specify that the child in the photo was a girl, the child generally appears to be a boy. There may be ways to edit the details of new images but that is still beyond me.

Lights in Alaska Land, Fairbanks, Alaska

4:30 pm stroll to see lights at Alaska Land (now Pioneer Park). A mere – 4F.


 Excrescence: Is it a Tree or an Elephant

For Ragtag’s Friday Prompt: Excrescence

Sequenced and Arranged

For Lost In Translations Thursday’s Special Pick A Word November 2022: Sequential. The Hassan II Mosque in Casablanca, Morocco. Opened in 1993, it is the largest functioning mosque in Africa and the 7th largest in the world. It was paid for with mandatory donations by all citizens of Morocco. It is the only mosque in Morocco open to non Muslims. Interestingly, this is not a religious proscription as many assume. When the French established a “protectorate” over Morocco (1912–1956), they passed a law forbidding Muslims from entering Christian churches and forbidding Christians from entering Muslim religious buildings. The French felt this would prevent religious disputes and attempts at conversion. The law is still on the books .

%d bloggers like this: