AI Dungeon : Adventures of Zondar the Wizard

 After creating a team of motley crew level 1 adventurers see https://prataverse.blogspot.com/2023/07/dezgo-bad-drawings-of-motley-crew-of.html , I was thinking of a dungeon game and I chance upon the website for AI Dungeon https://aidungeon.io/

It is powered by ChatGPT model and I dive right into creating a character , I chose a wizard and named him Zondar. 

It has the old school feel of Zork (1977), a text based adventure game. Another dungeon game Wizardry (1987 ) had minimal graphical lines to give some spacial representation to walls, corridors and doors when the party decent into the dungeon depths. 

As for AI dungeon , there is the Continue button and if you click it brings you to the next segment of the story. If you click the Take A Turn button, you can choose Do , Say , Story and See.

Example if you are in the marketplace and you click see and type marketplace you get a pixelated image of the marketplace.

At the start of the game , I entered the dungeon and I clicked continue most of the time and found the adventure a little too boring until I started using the do and say button. The story started to change according to my input interaction.

 

 

 

Image of Zondar the wizard with his goblin buddy generated using Degzo and  Adobe Photoshop beta.

 

 

Image of cooked spider generated using Degzo and  Adobe Photoshop beta.

 

 

 Image of shaman with goblins generated using Degzo.

The story does not just end, Zondar and goblin continued their journey to seek more dungeons and with each fight gain in experience and magic. He visited towns to chill out and on one occasion, the town was attacked by zombies. Exterminating them was too easy for him, he crave for a tougher challenge. He decided to change the script to change his destiny. 

 

  

My next blog I create a hospital game https://prataverse.blogspot.com/2023/09/ai-dungeon-creating-hospital-drama-game.html

How to find your Metaphor

Previous blog  https://prataverse.blogspot.com/2023/08/dezgo-set-up-lora1-from-civitai-dark.html

There are so many faces of water that cannot be describe by the word "water" that Roni Horn creates a lexicon of water through photographs instead in the book titled Dictionary of Water.

Taoist masters made reference to water as the natural flow to life. Be like water. Flow like water. 

Ask yourself what are your thoughts about water ? 

Is water a good metaphor to the concept of flow ? 

Is water a meaningful analogy or metaphor for you ? 

Roni Horn photographs documents the changing textures of waves. I would approach the water subject differently here, I would doodle and bad draw the site of water or a water situation as it comes to my mind.

Close your eyes and imagine you are water in the following site and situation. 

I would put side by side my image with AI text to image generation to compare which one is a better representation.

There is the ocean water at the night of the full moon , the waves crest glittered by the moon light. The Degzo AI did a much better representation than my bad drawing.

The sound of the gentle waves on the sandy beach. It is difficult to compare as it is a subject preference in styles here.

 The clear sound of water inside the cave without other noises. I think my doodling is too abstract for this one the Degzo AI image representation is better.

 

Water from many points flowing down a cliff wall forming a pool. Adobe Firefly beta did a great job in the representation that is better. It is able to understand my text prompt instead of creating a single waterfall. 

 A river runs through two mountains. Adobe Firefly beta generates a better representation.

 

The destructive power of flood waters . I do like my abstract doodling better but the generation of realistic photo image by Adobe Firefly beta supplements my abstraction to give an extra dimension and contextualization to the gravity of the climate change situation happening in the world today.

 

Balancing on top of the water ... The Adobe Firefly beta generative image is supplementary here providing realism.

 

 

Water can come from slowly melting ice. The Dezgo AI provides the supplementary realistic image.  

 

Sometimes it need not be human or AI , there are cases where both images can compliment one another. 

Have you found what kind of water are you ? and at what speed you flow ?

 

Dezgo : Set up LoRA1 from CivitAI Dark Elf performing a ballet pose

My previous blog are all male character designs https://prataverse.blogspot.com/2023/07/dezgo-bad-drawings-of-motley-crew-of.html

 This blog I'll be creating female characters and at the same time testing the new LoRA feature for Dezgo. It can import the LoRA from CivitAI just by copying the SHA256 hash and pasting it in Dezgo.

In CivitAI, I came across a Drow Concept LoRA by Lykon that I like to use for Dezgo.

I used the trigger words in the prompt eg Dark elf , Dark skin , Pointy Ears

The following pictures are Text to Image and Controlled Text to Image for the Dark elf performing a ballet pose. 

 

See the next blog https://prataverse.blogspot.com/2023/08/how-to-find-your-metaphor.html

Dezgo : Detail Instructional Doodling Process Korean Pop Dancers

Finally I see sun light , out from the caves of mental block. See previous blog https://prataverse.blogspot.com/2023/08/dezgo-sculptural-doodle-class.html 

This blog gives a peek into the details of my Instructional Doodling process. It can be an assemblage of my doodling and my bad drawing processes.

 These three personal lexicons that are important :

• Doodle : Subconsciously creating line work with my fingers until I arrive at a satisfied image. The line work usually flows in a continuous manner.
  
  
• Bad Drawing : once I know what the doodle image is going to be means that I am conscious and have a purpose in creating line work to complete the image. However, it is bad because I am not trying to draw the image in correct proportion or to draw a beautiful composition.
  
  
• Drawing : normally a process to correct the image, to redraw for the AI to generate better.

  

K-pop Dancer #1

 

STEP 1 : For this particular drawing , I doodle the eyes, nose and lips , bad drawing the head and the hair.

 

STEP 2 : Title it as Korean Pop Dancer

STEP 3 : I scaled the head smaller and bad drawing the rest of the body in a dance pose. 

STEP 4 : First image completed.  I start the process again to process the next Korean Dancer Image.... until I stop doodling or bad drawing.

 

STEP 5 : Decide what I want for the AI generation to get it accurate. For this case I want the AI to :

• follow the body pose of the input image.
• follow the pointing fingers of the input image
• follow the boots of the input image
  
• follow the text prompt a realistic image of a K PoP dancer
  

 

Control Model : Scribble

Model : AbsoluteReality 1.6 

 

PROMPT : Realistic Rendering Korean male dancer

Control Scale : 69%

Guidance : 14

 

The hands did not turn up well and the clothing looked old school. I would preferred it is modern Korean pop style.

 PROMPT : Realistic Rendering Korean pop male dancer
Control Scale : 85%
Guidance : 14

STEP 6 : Generate image with DEZGO AI . Choosing the best overall generation.

 

Prompt :Pointing white glove hand

 STEP 7 : Correct hands Adobe Photoshop beta AI Generative Fill. White glove is a good idea because it is difficult to match skin tone.

K-pop Dancer#2

 

STEP 1 : For this 2nd drawing , I doodle the eyes, nose and lips , bad drawing the head and the hair.

STEP 2 : Scale the head down. Bad drawing the body but realized that I have no space.

STEP 3 : Scale the half body and rotate to the landscape to have more space to bad drawing complete the whole image.

STEP 4 : Decide what I want for the AI generation to get it accurate. For this case I want the AI to :

•     follow the body pose of the input image.
•     follow the text prompt a realistic image of a K PoP dancer

STEP 5 : Generate the initial Control Text to Image using Dezgo. The hand is not placed on the floor as I have loosen the control setting. The other hand is inward could be due to the Resolution Landscape.

PROMPT : Realistic rendering of Korean pop male dancer doing breakdancing

 

STEP 6 : Regenerate by increasing the height of the image by moving the resolution a notch from extreme landscape.

I prefer the 2nd image so I take it to Adobe Photoshop beta to AI edit.

 

STEP 7 : Extend the image using Adobe Photoshop beta generative AI.

 

 

STEP 8 : The hand is not generated well probably due to beta but more or less the same color tone. Select and regenerate the hand.

 

 

K-pop Dancer #3

STEP 1 : For this 3nd drawing , I doodle the eyes, nose and lips , bad drawing the head and the hair.

 

STEP 2 : I scaled the head smaller and bad drawing the rest of the body in a dance pose. 

STEP 3 : Decide what I want for the AI generation to get it accurate. For this case I want the AI to :

•         follow the body pose of the input image.
•         follow the text prompt a realistic image of a K PoP dancer

STEP 4 : Generate the initial Control Text to Image using Dezgo. There are lines on the extending out from the shoes due to the doodle image. The other hand is not clenched. I forgot to put the "fists" or "hands"  in the prompt.

PROMPT : Realistic rendering of Korean pop male dancer with clenched

 

STEP 5 : I update the doodle again using the drawing process to correct for AI. 

 

• redraw the end of the pants
• redraw the hands.

STEP 6 : Generate the image using the updated drawing. There are lines on the extending out from the shoes due to the doodle image. The other hand is not clenched. I forgot to put the "fists" or "hands"  in the prompt.

 

 PROMPT : Realistic rendering of Korean pop male dancer with clenched fists

Seed : 3169676413

 

I do like the 2nd image generation better so I take down the Seed number.

STEP 7 : Regenerate images using the seed number.

STEP 8 : After evaluating the generated images in Step 6 and 7. I have figured out the bug is actually due to my bad drawing. The negative spaces ( see red arrows ) are interpreted as fists by the AI.  

 

• Redraw the left side negative space. 
• Scale down the head.
  

 

 

 

STEP 9 : Regenerate image using updated drawing. I like that the dancer pose like a puppet. I can add the thumbs in Adobe Photoshop beta but it looks good for me.

 

K-pop Guitarist #4

STEP 1 : For this particular drawing , I doodle the head, the face as well as the body. I realized later that the hands are circular and part of the circular hole of the guitar where the strings are connected to. The other hand seems to hold a pick that I do not remember during doodling. 

STEP 2 : Decide what I want for the AI generation to get it accurate. For this case I want the AI to :

•  follow the hair style from the initial image and prompt 
  
•  follow the text prompt a realistic image of a K PoP guitar
•  produce a decent electric guitar
  

STEP 3 : Generate the image. The hands did not generate properly.

PROMPT : Realistic rendering of Korean pop male guitarist with large hair

STEP 4 : Use Adobe Photoshop beta to edit the hands.

See the next blog : https://prataverse.blogspot.com/2023/08/dezgo-set-up-lora1-from-civitai-dark.html