Memes
Let's start review of KREA 2 Turbo with memes.
hoho meme
or Woman yelling at a cat type of meme generated by KREA 2 Turbo:
What is so special about it? this part:
It is exact image used as meme template. Not something like scene recreated from prompt. The models know the meme. Like Nano Banana 1/2 or ChatGPT Image 1.5/2, grok do. Other models will create something based on text prompt. but these are same faces same place.
Three Spidermen Pointing Meme
Generated by KREA2 Turbo:
you may ask "So what?", Emm again... it is exactly the meme. Not another version drawn using model than unaware of it. Like see spider-man-triple-meme-template and spiderman-pointing-at-spiderman-template the original meme series templates are:
so model know this meme too. Impressive.
Now when I share what impressed me the most for the first day of use, we can proceed with Intro and all the usual article things. Should we?
Intro
KREA 2 Turbo and KREA 2 Raw is open (not very, but still... will check license later) models from KREA. It is available (since Jun 22, 22026) as download for local generation on Huggingface. Raw version is supposed to be used for training mostly and Turbo for generations.
KREA 2 Turbo (8 steps)
KREA 2 Raw (52 steps)
CivitAi official KREA 2
Those are available for generation onsite. Were published on May 28, 2026:
KREA 2 Medium - ⚡39 BUZZ (+tips)
KREA 2 Large - ⚡78 BUZZ (+tips)
Added month later
Krea 2 Raw - ⚡45 BUZZ (+tips) for 30 step
KREA 2 Turbo - ⚡20 BUZZ (+tips) for 8 step
Unofficial checkpoints
Used in SD.Next are
CalamitousFelicitousness/Krea-2-Turbo-Diffusers - that was actually used for test
CalamitousFelicitousness/Krea-2-Base-Diffusers (it is Raw)
Some unofficial models on CivitAi are
Model was released with LORAs from KREA on huggingface
https://huggingface.co/collections/krea/krea-2-loras
Image Quality
I got some list of prompts that executed on every new model, so I can compare it to previous. It is three sets for now. I would post links to the prompts and full results in the article end. Let's see some images from those test sets.
test v1 2048px
Photorealistic
Taxi window portrait
Hand details
Oslo Opera House (it is correct image, most of the models do not know it)
model also know Obama, Arnold Schwarzenegger in Terminator 2 (will not post here since civitAi not happy with celebrity images so..) You can check it on test v1 2048px page.
Abstract Art
abstract art
gold and sepia
city theme abstract art
should I say it is nice? or it is obvious?
Art styles
ok with abstract art but other art styles are not that good. Not only ASCII art not known by the model. Compare KREA 2:
with Nano Banana 2 (I know it is SOTA and GOAT, but anyway)
or with ERNIE Image Turbo
I would give "less than expected" for paint styles.
But it will be LORAs someday... right?
I did also some photo and illustrative Styles test (click the link to see all).
The results are not bad. Its able synthwave, pixel art, polaroid and other. Not produce expected result on papier-mache art or cast paper art style. So not all, but still not bad. some examples:
funko pop art style.
or caricature style
synthwave style.
Minimalist abstract art.
returning to my general-purpose tests...
test v2 1024 samples
photorealistic
hand and key - good.
hands under the glasses - ok, it is also good
broken mirror - and this one also good
Illustrative
sociotype (far from ChatGPT 2.0 illustrative quality, but still not bad)
braking the paper wall (it is ok)
gangster duck (I like it)
solar system (again not GPT level, but not bad)
test v3 1024px and 2048px
this one done in both resolution already so we can compare output of 1024px ws 2048 px
photorealistic
2048px
1024px
fairy
2048px
1024px
surreal 2048px
complex concept
Compare with Medium and Large
KREA 2 Turbo
pareidolia effect (looks like not able), but at least not put plain faces over the glass.
BTW, I have got this also generated with commercial variants
KREA 2 Medium
KREA 2 Large
I do not know.. ok. let see another
Turbo
Medium
Large
I do not know. like it is different for sure. but the examples aren't justified the cost of Large, but it might be wrong examples. And Large is recommended for photorealistic. So it might need another test for those commercial versions to see what is really going on there.
Resources needed
For local generations I got Intel iGPUs on Intel core ultra 9 185H and 285H with 64 GB and 128 GB of RAM. Both are able to generate with KREA 2. It consumes about 46 GB of "unified" (v)RAM in bfloat16. Just to compare with similar models Z Image Turbo 6B (Total parameters: 10.2B), FLUX.2 Klein 9B (Total parameters: 17.3B), ERNIE Image Turbo 8B (Total parameters: 15.3B), KREA 2 Turbo 13B (Total parameters: 17.1B)
Generation time on Intel core ultra 9 285H iGPU
KREA 2 Turbo (8 step 128x128) generation time is 19 seconds
KREA 2 Turbo (8 step 256x256) generation time is 20 seconds
KREA 2 Turbo (8 step 512x512) generation time is 38 seconds
KREA 2 Turbo (8 step 1024x1024) generation time is 154 seconds
KREA 2 Turbo (8 step 2048x2048) generation time is 738 seconds
ERNIE Image Turbo (8 step 1024x1024) generation time is 95 seconds
Z Image Turbo (9 step 1024x1024) generation time is 85 seconds
FLUX.2 Klein 9B (4 step 1024x1024) generation time is 37 seconds
On real GPUs it will be faster, but the relative speed should remain the same.
Resolution range
1024px and 2048px is definitely work, lets check some other.
128px
256px
512px
1024px
that is good.
Other
Quick compare to ERNIE Image Turbo.
Will generate the illustrations from article https://civitai.red/articles/31633/ernie-image-turbo with KREA2.
Woman subway portrait (not defaulting to Asian)
Chinese prompt generated by ERNIE Built-In prompt enhancer (Asian, that is ok there)
same prompt translated back to English (Caucasian, and that is what you expect), Like you expect wall tiles and station name actually on a station not a subway car.
Fingers. Same two Seeds. Seed 20260619 and Seed 21
both OK.
1920x1200 image is ok it should be negative space on a border and so on.
but some gradients and "stains" are on a background.
1600x400.. Emm ERNIE is kind of better there
Will check if 12 steps will somehow help with that. not much actually
Lighthouse (still a bit better on ERNIE but not by far)
Artifacts check images
there are some patchy/stains/noise... hmm
omg, on ribbon it is takes its extreme.
License
https://www.krea.ai/krea-2-licensing you can read all that, but I just asked Claude to compare with Apache 2.0 (ERNIE Image Turbo) license and get:
Apache 2.0 is a permissive, business-friendly, irrevocable open-source license with virtually no strings attached. Krea 2's license is much more restrictive — it blocks serious commercial players (>$1M revenue), can be revoked at will, requires content policing on your end, and puts all legal risk squarely on you. It's closer in spirit to a "community/non-commercial" license than true open source.
Issues
So let us summarize the problems:
License is not an Apache 2.0, not critical for personal use, but anyway...
Some patchy-stains-kind-of-artifacts on dark colors.
Seems it is not good with a lot of text. Some text is ok.
Most emotions filtered. Only neutral and smile remain.
Need LORAs for real Art style uses.
Links
test v1
https://wiki.liutyi.info/display/AI/KREA+2+Turbo+2048px
compare to
test v2
https://wiki.liutyi.info/display/AI/KREA+2+Turbo+test+v2
compare to
https://wiki.liutyi.info/display/AI/ERNIE+Image+test+v2+with+Prompt+Enhancer
https://wiki.liutyi.info/display/AI/ERNIE+Image+Turbo+test+v2
https://wiki.liutyi.info/display/AI/ERNIE+Image+Turbo+test+v2+with+Prompt+Enhancer
https://wiki.liutyi.info/display/AI/GPT-Image+1.5+medium+test+v2
https://wiki.liutyi.info/display/AI/GPT+Image+2.0+high+test+v2
https://wiki.liutyi.info/display/AI/HiDream+O1+Image+test+v2+with+Prompt+Enhancer
https://wiki.liutyi.info/display/AI/Seedream+5.0+Lite+test+v2
test v3
https://wiki.liutyi.info/display/AI/KREA+2+Turbo+test+v3
https://wiki.liutyi.info/display/AI/KREA+2+Turbo+2048px+test+v3
compare to
https://wiki.liutyi.info/display/AI/ERNIE+Image+Turbo+test+v3
https://wiki.liutyi.info/display/AI/FLUX.2+Klein+base+9B+test+v3
https://wiki.liutyi.info/display/AI/HiDream+O1+Image+test+v3
https://wiki.liutyi.info/display/AI/Microsoft+Lens+base+test+v3
https://wiki.liutyi.info/display/AI/Microsoft+Lens+Turbo+test+v3
All prompts can be found at
https://wiki.liutyi.info/display/AI/liutyi+text2image+test+v1
https://wiki.liutyi.info/display/AI/liutyi+text2image+test+v2
https://wiki.liutyi.info/display/AI/liutyi+text2image+test+v3
Ai Art test series
https://wiki.liutyi.info/display/AI/KREA+2+Turbo+-+Ai+Art+1+images (artistic)
https://wiki.liutyi.info/display/AI/KREA+2+Turbo+-+Ai+Art+2+images (noir surreal)
https://wiki.liutyi.info/display/AI/KREA+2+Turbo+-+Ai+Art+3+images (silhouttes)
https://wiki.liutyi.info/display/AI/KREA+2+Turbo+-+Ai+Art+4+images (foreshortening)
https://wiki.liutyi.info/display/AI/KREA+2+Turbo+-+Ai+Art+5+images (minimalist flowers)
https://wiki.liutyi.info/display/AI/KREA+2+Turbo+-+Ai+Art+6+images (liminal spaces)
https://wiki.liutyi.info/display/AI/KREA+2+Turbo+-+Ai+Art+7+images (5 tags prompts)
https://wiki.liutyi.info/display/AI/KREA+2+Turbo+-+Ai+Art+8+images (black and amber noir)
https://wiki.liutyi.info/display/AI/KREA+2+Turbo+-+Ai+Art+9+images (amber and navy noir)
https://wiki.liutyi.info/display/AI/KREA+2+Turbo+-+Ai+Art+10+images (red and gold noir)
https://wiki.liutyi.info/display/AI/KREA+2+Turbo+-+Ai+Art+11+images (Mixed media streets)
https://wiki.liutyi.info/display/AI/KREA+2+Turbo+-+Ai+Art+12+images (tiny creatures)
https://wiki.liutyi.info/display/AI/KREA+2+Turbo+-+Ai+Art+13+images (double exposure)
https://wiki.liutyi.info/display/AI/KREA+2+Turbo+-+Ai+Art+14+images (female portraits)
https://wiki.liutyi.info/display/AI/KREA+2+Turbo+-+Ai+Art+15+images (pipelines)
https://wiki.liutyi.info/display/AI/KREA+2+Turbo+-+Ai+Art+16+images (legs and books)
https://wiki.liutyi.info/display/AI/KREA+2+Turbo+-+Ai+Art+17+images (flower faces)
https://wiki.liutyi.info/display/AI/KREA+2+Turbo+-+Ai+Art+18+images (biting lips)
https://wiki.liutyi.info/display/AI/KREA+2+Turbo+-+Ai+Art+19+images (street photo)
https://wiki.liutyi.info/display/AI/KREA+2+Turbo+-+Ai+Art+20+images (drone photo)
https://wiki.liutyi.info/display/AI/KREA+2+Turbo+-+Ai+Art+21+images (fog)
https://wiki.liutyi.info/display/AI/KREA+2+Turbo+-+Ai+Art+22+images (LLM humor)
https://wiki.liutyi.info/display/AI/KREA+2+Turbo+-+Ai+Art+23+images (sunset)
https://wiki.liutyi.info/display/AI/KREA+2+Turbo+-+Ai+Art+24+images (office)
https://wiki.liutyi.info/display/AI/KREA+2+Turbo+-+Ai+Art+25+images (original illustrative)
https://wiki.liutyi.info/display/AI/KREA+2+Turbo+-+Ai+Art+26+images (3 words story)
https://wiki.liutyi.info/display/AI/KREA+2+Turbo+-+Ai+Art+27+images (minimalist portraits)
https://wiki.liutyi.info/display/AI/KREA+2+Turbo+-+Ai+Art+28+images (urban oil paintings)
https://wiki.liutyi.info/display/AI/KREA+2+Turbo+-+Ai+Art+29+images (reflections)
https://wiki.liutyi.info/display/AI/KREA+2+Turbo+-+Ai+Art+30+images (couples)
https://wiki.liutyi.info/display/AI/KREA+2+Turbo+-+Ai+Art+31+images (papercut)
https://wiki.liutyi.info/display/AI/KREA+2+Turbo+-+Ai+Art+32+images (popotillo)
https://wiki.liutyi.info/display/AI/KREA+2+Turbo+-+Ai+Art+33+images (art->reality)