Text to Video
Text-to-Video Guide
The Text-to-Video (T2V) tab lets you turn plain-language prompts into AI-generated video clips—no uploads required.
1. Mode Selector
At the top, choose your generation mode:
T2V (Text → Video)
I2V (Image → Video)
SR (Super-Resolution / Upscale)
EXT (Extend Clip)
F-L (First Frame → Last Frame)
Tip: Choose T2V
2. Settings Panel
Adjust these four parameters—or leave them on default for an optimized experience:
Model
Select from available video engines (e.g. Hailuo Base, Hailuo Director, WAN 2.1, Kling, etc.). Each entry shows an estimated generation time and credit cost.
Aspect Ratio
Pick your framing: • 16:9 (widescreen) • 9:16 (vertical) • 1:1 (square)
Number of Videos
Queue up to 5 clips in one batch. (Default = 1)
Generate Sound
Toggle on to auto-add sound effects (5 extra credits)
3. Prompt Box
At the bottom:
Type your description (e.g. “A Boba cup does a happy dance in slow motion”).
Credit Counter displays the credits your prompt will consume.
Optimize Button if clicked it will show "Optimized" which will automatically improve your prompt using our systems.
Send (↑) Button kicks off the generation.
Clear (🗑️) Icon resets the prompt field.
4. Monitoring Your Job
Once you hit Send, your request appears in the Generation Feed on the right:
Progress Bar & Percentage
Mode Tag & Aspect Ratio
Timestamp
Hover for a quick preview or click to open the full player.
With these simple controls, you’re ready to go from text → high-quality video in minutes. Enjoy!
Last updated