⚡ LongCat-Video-Avatar 1.5 TURBO

Enter a scene prompt for a generated avatar, or provide your own reference image and driving audio. Generates a ~5-second lip-synced video using Meituan's LongCat-Video-Avatar 1.5 (INT8 DiT + DMD2 8-step distilled + DBCache).

Prompt

Resolution

480p 720p

Seed

Acceleration

Exact 8-step DBCache fast DBCache faster

Output

Generated reference

Generated speech

Image prompt

Video prompt