Krea 2 gets an API, playground and docs, wired into fal, ComfyUI and agents
- Source
- x.com
- Date
today, we're releasing the API for Krea 2. now available in platforms like @fal or @ComfyUI, through agents like Hermes from @NousResearch, and with full support for Claude, Codex, or OpenClaw. learn how you can set it up 👇
here's how you can find our new API platform from https://t.co/V31Uw5b10E there you can find a Playground to test all the features that come with Krea 2 and detailed Documentation.
we also prepared this blogpost with examples and more details about the features available through the API. https://t.co/dktS9F8zkF
more updates coming soon 👀
Context
Krea's Krea 2 API lets software generate images with the same kinds of visual direction users supply in its creative tools. The May 27 launch guide describes requests containing a text prompt, reference images or a saved moodboard, with strength values controlling how much those references influence the result. This makes a chosen visual direction usable inside an automated image workflow.
Generation runs as a job: an application submits the request, then polls for the finished result or receives a completion notification through a webhook. Both Medium and Large models accept the documented parameters. The guide listed trained styles as coming soon, so the separate availability of LoRAs in the web app should not be read as launch-day API support. The full guide includes request examples.
Checking sign-in…
Loading comments…





