Models on cv.cm

ByteDance's cinematic multimodal video model with native synced audio

Cost-effective video generation — half the price, built for batch drafts

ByteDance Doubao fast, cost-efficient image model with 2K/4K output

OpenAI's image model — sharp in-image text, precise prompt-following and editing

Turn text or lyrics into a full song with vocals

Fast, low-cost text model for writing, rewriting, and orchestration

Zhipu's multimodal vision model that reads images and outputs text