Foxy lets you create AI videos in three flows. Pick the one that fits what you're trying to do.
The three video flows
1. Image-to-Video (I2V) — animate an existing image
Open any image in your gallery, tap the play (Make video) icon, and write a prompt describing what you want to happen.
The character, outfit, and setting are inherited from the source image
You write the action — "smiling and waving," "walking through a city," "blowing a kiss"
Best when you have an image you love and want to bring it to life
2. Text-to-Video (T2V) — start from a prompt
Tap Create → Custom prompt to write a video prompt from scratch. Pick the character, then describe the scene, the action, the setting — anything you want.
Most creative flexibility — you control everything via prompt
Best when you have a specific scene in mind
3. Templates — pick a ready-made scene
Tap Create → Video and browse the template grid. Each template is a pre-built scene with a fixed prompt — you just pick one and run it.
Fastest way to get started
You can't edit a template's prompt — if you want to tweak it, start from Custom prompt instead
Video lengths and pricing
Videos come in 5, 10, 15, 20, 25 and 30 seconds. Which lengths you can pick depends on the video model you choose — some models offer the full range, others are limited to the shorter options.
Credits are spent per generation, and the cost depends on what you're making:
Videos are priced by length, so a longer clip costs more than a shorter one
Foxy has several video models, and the more advanced ones cost more per second
You always see the exact cost before you generate. The credit cost is shown on the create screen once you've picked your model and length, so nothing is charged until you confirm.
If a generation fails, your credits are returned automatically.
Audio is automatic
Every Foxy video automatically includes AI-generated audio that fits the scene — contextual music, ambient sound (footsteps when walking, city sounds in a city, etc.), and lip-sync where the moment calls for it. You don't need to add audio yourself; Foxy picks what fits.
Tips for great videos
Be specific — "turning her head to smile at the camera" beats "happy"
Keep it visual — describe what we'd see, not what the character is feeling
One main action per prompt — pick the moment you want to capture
Use Image-to-Video when you want the exact look of an existing image
Aspect ratios
Portrait (4:5) — great for Instagram feed
Story/Reel (9:16) — vertical, full-screen mobile
Landscape (16:9) — horizontal, YouTube and traditional video format
Image-to-Video inherits the aspect ratio from the source image — pick a source image in the ratio you want.
Questions about a specific video? Open chat with us via the Profile menu → Support.