AI Models

Generate 8-second videos with native dialogue, sound effects, and ambient audio in one pass.

Create up to 15-second multi-shot videos with character consistency, 4K 60fps support, and bilingual audio.

Turn images into 10-second 1080p videos with 48fps motion control and native speaking, singing, or rapping audio.

Generate up to 30-second videos with strong physics, long scene continuity, and precise style control.

ByteDance's most capable video model — accepts up to 12 reference files simultaneously with native 2K output and director-level camera control.

Generate 12-second videos with native audio, multilingual speech, and fast turnaround from 45 seconds to 3 minutes.

Generate 15-second videos with audio, strong character consistency, and a free tier on Flashloop.

Generate 30-second videos with native audio, 4 instant variations, and fast renders in about 17 seconds.

Generate 4K images, edit with plain English, and blend up to 4 references in one pass.

Create fast, flexible images with up to 10 references, LoRA tuning, and four speed-to-quality tiers.

Generate 4K images in 2–3 seconds with web-aware prompts, strong reasoning, and near-perfect EN/CN text.