All models
BytePlus · Video
Omnihuman 1.5
ByteDance's OmniHuman 1.5 animates a person from a single photo, driven by an audio track: talking heads, singing, gestures. A specialist for avatars and dubbing, not a general text-to-video model. Pricier per second than most mid-range video models. For scenes without a speaking person, pick Kling 3.0 or Wan 2.7.
OpenAlso works from chat: ask any chat model to use Omnihuman 1.5 for you.
The facts
Model type
Video
Made by
BytePlus
Content tier
OpenOpen-weight models with lighter filters. Discuss more, refuse less.
Intelligence
Smart & Cheap
Price per use
91 credits/clip≈ $0.91
Reads
Text, Images
Writes
Video
Served via
ModelsLab, Unbottled AI
Status
Current
Price is per unit - image, clip, second or character - and shifts with size, length and options. 1 credit = $0.01.
Try Omnihuman 1.5 now.
No subscription. Free credits to start. The tool opens ready to run.