KREA 2

KREA trained their own AI ART models from scratch -- KREA 2, both "Large" and "Medium" -- and let all paid subscribers use it for free for one week (May 18 - 24, 2026).

KREA

"Only this week: UNLIMITED Krea 2 generations for all paid plans."

FRAGMENTED STRUCTURAL PAPERCRAFT

My best success was with the Moodboard -- FRAGMENTED STRUCTURAL PAPERCRAFT -- of my Paper Figure Sculptures (which I've been generating since February 2026) because I like that aesthetic:

FRAGMENTED STRUCTURAL PAPERCRAFT

Moodboard made from 24 images of my Paper Figure sculptures

 -- which I made public

My Paper Figure Sculptures

described in words

•  I also made this Moodboard public, so that anyone on KREA could use it

GENERATIONS

My best results were from using JUST USING TEXT PROMPTS -- and not from uploading and image

KREA

KREA

Midjourney

EzGIF

KREA

KREA

KREA

KREA

KREA

KREA

KREA

MONOCHROMATIC BIOMECHANICAL STATUARY

I made another Moodboard -- MONOCHROMATIC BIOMECHANICAL STATUARY -- with images that were based on Bernini sculptures and my drawings, which I started generating in Leonardo.AI back in 2023.  However the results were not always that exciting:

MONOCHROMATIC BIOMECHANICAL STATUARY

Moodboard based on 10 of my drawings

in the style of Bernini

FRAGMENTED GESTURAL MINIMALISM

I made a Moodboard based on my raw figure drawings -- FRAGMENTED GESTURAL MINIMALISM -- but I did not like the generated results:

FRAGMENTED GESTURAL MINIMALISM

DECONSTRUCTED GEOMETRIC FUTURISM

I made a Moodboard based on my drawings -- DECONSTRUCTED GEOMETRIC FUTURISM -- but I did not like the generated results:

DECONSTRUCTED GEOMETRIC FUTURISM

based on 

---

 KRRRL STYLE FAILS

I cannot get Midjourney or the new KREA "K2" models (designed to compete with Midjourney) to generate anything in my KRRRL drawing style. Moreover Google never gives me anything like my drawings when I do a reverse search with Google Lens. The premiere AI ART programs do not work well generating organic forms, perhaps they are even censored. Or maybe I'm on to something new?

I uploaded the first drawing in this blog

and altered it with the K2 AI model

using my "Fragmented Structural Papercraft" Moodboard

However the results did not look like either my drawing or the images in my Moodboard -- not for the "K2 Large" nor "K2 Medium" AI models:

"K2 Large" model result

"K2 Medium" model result

hubg

May 19, 2026

Drawn at Art Buddies in Albuquerque:

KREA

KREA Realtime prompt:

"paper sculpture of a woman"

KREA

KREA Realtime prompt:

"paper sculpture of a woman"

KREA

KREA Realtime prompt:

"paper sculpture of a woman"

KREA

KREA Realtime prompt:

"paper sculpture"

KREA

Midjourney

EzGIF

(YouTube): Google Omni Is Nano Banana for Video

May 18, 2026

Drawn at Art Buddies in Albuquerque:

KREA

EzGIF

KREA Realtime prompt:

"black and white only dotted lines"

On May 19, 2026 EzGIF came out with an animated GIF to animated SVG conversion:

KREA

EzGIF

Download: animated "290518.SVG" (920.39 KB)

KREA

KREA Realtime prompt:

"black and white only dotted lines"

KREA

KREA Realtime prompt:

"black and white only dotted lines"

KREA

KREA Realtime prompt:

"black and white only dotted lines"

KREA

KREA Realtime prompt:

"black and white only dotted lines"

KREA

KREA Realtime prompt:

"black and white only dotted lines"

KREA

KREA Realtime prompt:

"black and white only dotted lines"

KREA

FLOW

EzGIF

FLOW prompt: "swimming"

KREA

KREA

KREA Realtime prompt:

"black and white only dotted lines"

KREA

KREA

KREA Realtime prompt:

"black and white only dotted lines"

KREA

KREA Realtime prompt:

"black and white only dotted lines"

KREA

KREA Realtime prompt:

"black and white only dotted lines"

KREA

Add Lines

KREA

KREA Realtime prompt:

"black and white only dotted lines"

KREA

KREA Realtime prompt:

"black and white only dotted lines"

KREA

KREA Realtime prompt:

"black and white only dotted lines"

KREA

KREA Realtime prompt:

"black and white only dotted lines"

KREA

KREA Realtime prompt:

"black and white only dotted lines"

KREA

KREA Realtime prompt:

"black and white only dotted lines"

KREA

KREA Realtime prompt:

"black and white only dotted lines"

 

KREA

Midjourney

EzGIF

---

 KRRRL STYLE FAILS

I cannot get Midjourney or the new KREA "K2" models (designed to compete with Midjourney) to generate anything in my KRRRL drawing style. Moreover Google never gives me anything like my drawings when I do a reverse search with Google Lens.  The premiere AI ART programs do not work well generating organic forms, perhaps they are even censored. Or maybe I'm on to something new?

KREA is offering unlimited generations this week for all plans with their new AI model "K2" -- however I am not getting anything good from it:

KREA

"Only this week: UNLIMITED Krea 2 generations for all paid plans."

KREA 2 allows you to make "Moodboards," which it will reference for AI image generation.  So I made a couple of Moodboards and tried it:

"Fragmented Structural Papercraft" Moodboard

"Fragmented Structural Papercraft" Moodboard

made with 24 paper sculpture images

I uploaded the first drawing in this blog

and altered it with the K2 AI model

using my "Fragmented Structural Papercraft" Moodboard

However the results did not look like either my drawing or the images in my Moodboard -- not for the "K2 Large" nor "K2 Medium" AI models:

"K2 Large" model result

"K2 Medium" model result

"Deconstructed Geometric Futurism" Moodboard

"Deconstructed Geometric Futurism" Moodboard

made with 10 images from my "Dotted Lines" blog post

I uploaded the first drawing in this blog
and altered it with the K2 AI model
using my "Deconstructed Geometric Futurism" Moodboard

Again,  the results did not look like either my drawing or the images in my Moodboard -- not for the "K2 Medium" nor "K2 Large" AI models:

K2 Medium model result

K2 Large model result

Also the GOOGLE LENS reverse image search always gives me images that I don't think look like my figure drawings:

I don't think the GOOGLE LENS results

look like my drawings

UNFAIL

So I added "structured figure drawing" to the GOOGLE LENS image upload and got a descent description or my drawing approach:

HOW to PRACTIC THIS STYLE

1.  Start with Gestures:  Capture the flow and tilt of the spine and hips using simple stick lines first

2.  Box the Torso:  Treat the chest and pelvis as two solid bricks or wedges that can twist independently

3. Carve the Planes: Instead of drawing smooth outer outlines, connect points using straight, deliberate lines to "carve" out the muscles

4. Wrap the Surface: Draw light horizontal and vertical bands around the arms and legs like bandages to force yourself to see their thickness

I might add that I like to drag lines through the image to "translate the force" that act on the figure.

I went to the UNM student Film showing

at the Rodey Theatre on May 17, 2026