Side by side
See the difference.
Scores, capabilities and costs for the models you’re considering.
Scroll to compare models →
| 3 models | bytedanceBytedance Omnihuman V2Remove × | googleembeddinggemma-2Remove × | CreatifyBorealRemove × |
|---|---|---|---|
| What’s different | Animates a person from one image and supplied audio, with optional text guidance for the performance. | EmbeddingGemma 2 is a 740M parameter multimodal embedding model from Google DeepMind that maps text (incl. code), images, video and audio, alone or interleaved, into a single 768-dimensional vector space,… | |
| Date | Oct 15, 2026Listed | Oct 8, 2026Listed | Sep 15, 2026Released |
API prices USD · provider configuration shown below | |||
| Listed rate | $0.105/ secondfal · all routes ↗ | See provider quotes | See provider quotes |
| Provider endpoints | 1 endpoint → | 0 endpoints → | 0 endpoints → |
Benchmarks Each result retains its evaluation configuration | |||
| AA Video + Audio ↗2.1 | Not reported | Not reported | 829.6 ↗Text-to-video · audio evaluated · all categoriesIndependent result95% CI 810.6–848.6 · n=3,332 |
| AA Video Silent ↗2.1 | Not reported | Not reported | 820.63 ↗Text-to-video · silent evaluation · all categoriesIndependent result95% CI 801.63–839.63 · n=3,109 |
Specifications | |||
| Context window | — | 8.2K | — |
| Max output | — | — | — |
| Parameters | — | — | — |