Krea image models are available through fal in OpenClaw's image generation stack, so you can wire them into the same `image_generate` workflow. https://t.co/lDk20WEZmc
Krea is now built in to Hermes Agent as an image generation API provider, allowing your agent to use Krea 2: a new foundation model trained from scratch to balance aesthetic quality and fine control, with style transfer, moodboard input, and adjustable creativity settings.
KREA 2 Image is now a Partner Node in ComfyUI
KREA's first foundation image model — trained from scratch — with tunable creativity, style references, and moodboard conditioning.
Krea 2 Large is two different models.
>27% win rate when the style is described in words.
>51% when the style is a reference image.
A 24-point swing based on whether the brief is text or image.
On reference-image prompts, @krea_ai jumps to second place
>beating Gemini 3 Pro 🤯
>Seedream 5.0 Lite 🔥
>within 19 points of ChatGPT Images 2.0 👀
Model rankings without prompt-type context are misleading
Very impressive from the Krea team given how early it is @viccpoes@asciidiego
K2 is the only model i've tried that understands and can reproduce artistic and visual language (outperforms lora trainings).
look at the outcomes with the same prompt and original watercolor painting as a reference:
this is Krea 2.
our first foundation model, built completely from scratch for aesthetic diversity and stylistic control.
learn more and get early access 👇
today, Krea 2 goes live to everyone.
to celebrate, we're offering unlimited Krea 2 generations to all our subscribers for the entire week.
try it for free 👇