Adobe Firefly Beta : Abstract Painting

 I would think in the areas of abstract painting the AI generate decent images. Unless you are a painter and you see areas where that paint strokes does not relate to the paint strokes form in reality. 

 PROMPT :  ink painting abstract with rhythm.

PROMPT : rainbow ink painting abstract strokes and watery splashes.
 

PROMPT :  ink painting abstract strokes with rhythm and architectural structure.

 

PROMPT : botanical ink painting abstract with rhythm.

 

 

PROMPT : botanical ink painting abstract with fiery rhythm batik style.

 

 

PROMPT : botanical ink painting abstract with fiery rhythm batik style pattern.

PROMPT : ink painting abstract geometric shapes of town surrounded by natural vast landscape cubism. (After some edits)

 

Adobe Firefly Beta : Ideas about the Muse

 I have this vision of the Muse the Goddess of Ideas , she came to me when I crawl in the endless desert heat thirsting for a sip of water , if she is generous , she pour water from her pitcher to quench my thirst , she is sometimes cruel by pouring water an inch away from me into the sand ....

 PROMPT : In a desert landscape, a goddess holding a pitcher, pouring water into the mouth of a man.

This one is very close without any edits. I prefer the man on his knees or crawling. But this is amazing.

 

This is when the goddess is cruel. ( Edited wavy hair , mouth of man , water , correct pitcher , hand , added sun )

 

Interesting generation , that the goddess  sat on the sand. ( Edited , milk spilling to the ground , hand )

This is the closest representation of the goddess wearing white roman dress. Pitcher could be improved to white porcelain.  ( Edited , face and body of man , hand of goddess )

This is interesting , I have not have thought of the Muse being an Indian goddess. This works too. ( Edited , mouth , handle , hand , water )

A goddess giant submerge in its own water from a small pitcher . ( Edited man face, body ,  goddess arm in water. )

 

Adobe FireFly : Scene Creation

I am practicing scene creation using Adobe FireFly. A scene of a man and his environment.

Touch up with generative fill : Mouth with fang and tongue , man face and hands.

 

PROMPT: Evil black mamba serpent in horror landscape creeping behind a man.

Touch up with generative fill , man , hands , planet. The hands are generated separately, the reason for different hand poses.

 
Mark the shape of the man with open arms.

 

 
PROMPT : Space City.

Adobe Firefly Beta : Character Design : TV Crab

 

 I have done an old design of TV crab in YouTube. I seem to have many ideas when it comes to crab design. I would like to see how the AI would generate the image of TV crab.

 PROMPT : Character design of an old television crab. 

Use a steampunk style. the lower bottom image is very nice.

 I use the Generative Fill and change the opacity to 40% because I want some of the screen texture to be on the TV screen . 

PROMPT : Kid

PROMPT : golden stars

 

Adobe Firefly Beta : Character Design : Vadai Boy

 There is a side kick Indian food character named Vadai Boy who is small and feel small and follow the stronger character named Origami Paper Thosai Girl.

 

Vadai Boy 

PROMPT : Character design of a bread donut that can walk and talk.

I need to clean up the donut and I prefer the hole of the donut being the mouth so I need to move the position of the eyes upward.

There is another donut generated that has an interesting shy pose.

Adobe FireFly Beta : Character Design : Origami Paper Thosai Girl

 I have this character design for Indian food . That is why the name of the blog is Prataverse , in a metaverse world where Indian food characters exist. 

The motivation is to create a character in my story named origami paper thosai girl who has supper power to transform or fold into any origami shape.

 

Origami Paper Thosai Girl 

 

 

PROMPT: Character design of a crepe girl that can walk and talk.

That does not work very well. It looks more like a girl than a crepe.

PROMPT: Character design of a crepe that can walk and talk. 

Much better . I use Origami Style , there are some 3D folds that looked 3D , I like the look.

I tried the same prompt with a different Layered paper style. It gave the crepe more texture and I like the 2nd image.

I changed the background , eye color , hands and shoes with Generative Fill. I like the final image even though it is not the Origami Paper Thosai Girl that I wanted, but it give me a lot more ideas ...

 

Adobe Firefly Beta : New Asian + Italian Fusion Spaghetti

There is no Asian fusion in regards to spaghetti. Lets see if AI can create the look of the non-existent dish.

• Paleak Paneer Spaghetti
• Ayam Buah Keuak Spaghetti
• Petai Cincalok Spaghetti
• Frog Leg Spaghetti
• Chicken Feet Spaghetti
• Natto Bean Spaghetti

 

 Paleak Paneer Spaghetti

PROMPT: Aglio olio spaghetti with green curry sauce and feta cheese cubes.

 Natto Bean Spaghetti

PROMPT : Spaghetti soak in sticky liquid 100 natto pick up with chopstick.

Somehow the stickiness of Japanese natto beans are not yet learned by AI.

More human prompting could be required to add the stickiness. 

 PROMPT: Person pick up natto on chopstick.

 Use Generative fill for 5 columns with the following prompt

PROMPT : Thick white sticky liquid.

Even though I mention thick , I have selected the thin ones that looks better.

I bought natto beans in a box ( picture below ) and compare it to the edited generated image ( picture above ) .

 

Chicken Feet Spaghetti

 

PROMPT : Braised chicken feet spaghetti.

 

Sambal Petai and Prawn Spaghetti

This strange Asian fusion dish actually existed in a KL restaurant at the price of RM$25.

 

 

Adobe FireFly Beta : Praying Mantis

 I finally have some time to test Adobe Firefly Beta. In this exercise, I hope to understand the process of Adobe Firefly workflow as well as to learn how to communicate with AI using prompts that AI can understand.

Lets starts simple . I was thinking of combining two ideas , praying mantis and martial arts. 

I must have confused the AI , "two hands" is treated as a separate object and not the hands of the praying mantis. The image generated on the top left is an interesting perspective.

 I am unsure if the hands are actually legs of of the praying mantis . I join the two sentence in the previous prompt choosing to use the verb "wielding" and not mentioning hands or legs.

PROMPT :  " Praying mantis in a big white room practicing martial arts wielding a long sword "

The one pose that I like is the mantis holding a long stick instead of a sword. I use it as a reference image and adjust the bar more towards the meaning of the prompt to regenerate till I found the image I like on the lower bottom right.

There are quite a bit of things to correct in the picture which I use generative fill to do it.

PROMPT : " Remove feeler "  apparently the AI understood this works better than "remove line".

PROMPT : "  "  for sword handle , neck area , shadow for it to regenerate alternatives images.

PROMPT " Join to body "  

Use the word body rather than the word leg.

To add extension of the leg use the following prompt

PROMPT " Add body "

PROMPT " add broken wing "

The prompt does not work it is against user agreement , no generation of blood or violent images. 

PROMPT: "Splatter liquid on the floor"

Final collaborative human + AI image