Every model Hermoso renders with

Video models all 39 →

Seedance 2.5default Up to 30s in ONE unbroken take · synced audio · keeps a person’s face from a saved creator or a photo you have the rights to Gemini Omni Fast and cheapest with sound. Start from text, an image or a video Veo 3.1 Top quality with sound, cinematic Veo 3.1 Fast Faster · has audio Kling 3.0 Latest Kling: sound, several shots in one clip, up to 15s Seedance 2.0 Fast Cheaper, faster Seedance · sound included · up to 15s

Image models all 42 →

Nano Banana 2.1default Newest Nano Banana: sharp text, true-to-life products, up to 4K Nano Banana Pro Top quality, best at text, packaging and true-to-life products GPT Image Great at in-image text & instructions FLUX1.1 Pro Versatile, lifelike product & lifestyle Seedream 4.0 ByteDance flagship, up to 4K with sharp text FLUX.2 [pro] Newest FLUX: photoreal detail and cleaner text

Text models all 23 →

Claude Fable 5 Previous Fable Claude Opus 5.5 Complex, analytical work Claude Sonnet 5.5 Responsive everyday work Claude Haiku 5.5 Fastest, lowest cost Claude Sonnet 4.6 Previous generation GPT-6 Astra OpenAI’s most capable, for long-horizon work with a 1M context

Voice models all 14 →

Seed Audio Eleven v3 Speech 2.6 HD Speech 2.8 HD Speech 2.8 Turbo I Inworld TTS

Every render is priced in credits before it runs and settled at its exact cost, so a model you have never used costs you nothing to have available. Models are added and retired as the field moves; these pages are generated from the live catalog rather than written by hand, which is how a model we no longer offer stops being advertised the day it goes.

Frequently asked questions

Can I choose which model renders my ad?

Yes. Every surface takes a model name, and leaving it out picks a sound default for the job.

Does using a premium model cost more?

Yes. A render is priced before it runs and settled at its exact cost; the current price per model is shown in the app, beside the button that spends it, rather than on a page that can go stale.