Models
Every model behind Likna, compared
Likna doesn't make you pick a model soup — it names the outcome and picks the right engine underneath. Here's what's actually running: three still models and two video models, each with a dedicated page covering speed, cost, and sample output.
Z-Image Turbo
A 6B local model tuned for fast, natural everyday shots — Likna's default for most stills, rendered entirely on Likna's own GPU. See sample output, pricing, and how it compares below.
FLUX.1 dev
The high-detail image model in Likna's lineup — the same FLUX.1 dev weights whether Likna renders on fal.ai's cloud (fal-ai/flux-lora) or on its own GPU. Samples below are plain FLUX.1 dev output; identity conditioning is a separate feature, on its own page. See sample output, pricing, and how it compares below.
Face Lock
PuLID identity conditioning on the FLUX family — lock one reference face and it holds across every scene, outfit and lighting setup, instead of drifting into a different person shot to shot. See sample output, pricing, and how it compares below.
Wan 2.2
Likna's standard video model — a 14B image-to-video and 5B text+image-to-video pair, rendered on Likna's own GPU capacity at half the credit rate of cloud video. See sample output, pricing, and how it compares below.
Kling v3 Pro
Likna's premium motion tier — Kling 3.0 Pro, rendered on fal.ai's cloud at double the credit rate of standard Wan 2.2 video. The upgrade you pick when a clip has to look cinematic. See sample output, pricing, and how it compares below.