✏️ Prompt (— Step 1)
✨ Rewrite Prompt (— Step 2)
📝 Rewritten Prompt (click Rewrite to generate, or use raw input)
-> Speech Tag Check
🖼️ Image Input (optional — enables I2V mode)
▼
🎤 Speaker Reference (optional, max 2)
▼
⚙️ Generation Settings (Recommended)
Inference Steps
More steps = better quality, slower generation
↺
10
100
Duration (seconds) — 6s = 37 frames
Video length in seconds
↺
2
10
Aspect Ratio
🚀 Generate (— Step 3)
Generated Video (with Audio)(approx.300s)