The models behind the characters
InfluAI Labs is a layer over the best generative models available, not a model of its own. Each one below was verified against our own provider key — if a page says a model is not currently routed, that is because it is not, and the page says so.
Video
Veo 3 Fast
in useGoogle DeepMind
Google's fast video tier, wired to a character whose face does not change between clips.
Kling 2.1 Master
availableKuaishou
Kuaishou's video model. Reachable on this key, held as an alternative to Veo.
Sora 2
availableOpenAI
OpenAI's video model, reachable through the same provider.
Image
Grok Imagine
in usexAI
xAI's image generation model. Photorealistic, professional, and built for consistent character generation.
Seedream v4
availableByteDance
Fast, cheap image model. Available as a fallback alternative.
Seedream v4 Edit
availableByteDance
The same model, but it takes input images. This is what makes a face stay a face.
Nano Banana
availableGoogle's image editing model, reachable on this key and kept as a second engine.
The model is the easy part. Keeping one face identical across three hundred posts is not — that is what this product does.
Get started