Models / FLUX.1 dev
Generate photorealistic avatars with FLUX.1 dev
The high-detail image model in Likna's lineup — rendered on fal.ai's cloud (fal-ai/flux-lora). 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.
Try FLUX.1 dev — freeSpeed
30 steps
Cost
2 credits / image
Best for
Detail and realism
Sample output
How it compares
Model
Speed
Best for
Z-Image Turbo
8 steps
Everyday shots
FLUX.1 dev
30 steps
Detail and realism
NoobAI XL
30 steps
Anime and illustration
Face Lock
Runs with FLUX sampling
One identity, every scene
MiniMax H3
Cloud, i2v
Highest-fidelity video with audio
FAQ
What is FLUX.1 dev used for?
It's the model behind fal.ai's fal-ai/flux-lora endpoint, which Likna uses to render your trained avatars.
Does it support Face Lock?
Yes — Face Lock (PuLID) runs on the FLUX family, so you can layer a locked reference face on top of FLUX.1 dev's output. It has its own page.
How many steps does it sample at?
30 by default, versus Z-Image Turbo's 8 — the extra steps are what buy the higher identity precision.
How much does an image cost?
2 credits per image.