π¨ Krea 2 | ARShumov - Turbo
Small-Tune ver.
π About the Model
Base model: Krea 2 Turbo
Precision: Full Precision BF16
Model size: 25 GB
Prompting: Natural Captions & Booru Tags
Full BF16 precision means full compatibility with LoRA. The model works best with them: styles, characters, and more.
π― No baked-in styles. The model doesn't have any particularly mixed-in styles.
πΌοΈ Small Tune. The dataset was expanded with a tuned set of 1,000 high-quality images. It's a tiny tune that barely affects overall quality.
π·οΈ Flexible prompting. Works with both Captions and Booru Tags.
π A good replacement for Illustrious or Anima models.
This is the first release, so I haven't run any big experiments with the model yet.
βοΈ Recommended Settings
My settings for Krea 2 Turbo
CLIP Skip: None (or 1)
CFG Scale: 1 β 1.5 (max)
Sampler: Euler (custom preset)
Scheduler: SGM_Uniform, Beta, or Simple β best way!
Steps: 8 β 10 (max)
Hi-Res Fix: β None
ADetailer: β None
π¬ Feedback and example images are very welcome. Please leave a review and share your results!
π License
The model follows the official license from the creators, without violating its copyright.
You can review the official license here:
Description
FAQ
Comments (7)
looks great, but my 8gb vram crying in the corner haha, fp8!
I'll later release smaller models and other quantization versions FP8-INT8 that will suit you, but for now, if you want, you can find it on other platforms and try it online.
or use it here on civit online, I wouldn't say Civit's online generator is great, but you can try the model to see what it's capable of.
FP8 Version on Testing now
Looks promising. waiting for lower quants.










