DropAi · Video effects
Turn a photo into a short film
Bring a portrait to life with a short AI film. Turn your chosen scene into a moving keepsake that guests can watch and download on their phones.
Compare AI models
Explore the models, their suggested uses and credit prices. Processing time and result quality depend on the model, photo and settings.
Video models
| Model | Type | Cost | Processing profile | Description and suggested use |
|---|---|---|---|---|
| Alibaba | ||||
| wan-3 | Video | 0.25 credits / second | Depends on duration and queue | A video model for animating one photo into a short scene with described subject motion and camera movement. DropAi uses 720p with automatic prompt expansion disabled, so specify one clear action, the camera movement, and the intended scene atmosphere. |
| ByteDance | ||||
| seedance-1-pro | Video | 0.15 credits / second | Depends on duration and queue | A video model for photo-based scenes with character gestures, moving surroundings, and camera directions specified in the description. DropAi offers two to twelve seconds at resolutions up to 1080p and a fixed-camera option when the scene should avoid camera movement. |
| seedance-1-pro-fast | Video | 0.0625 credits / second | Depends on duration and queue | The Fast variant of Seedance 1 Pro animates input photos into short clips with a described action and camera movement. DropAi offers the same two-to-twelve-second range and resolutions up to 1080p as Seedance 1 Pro, including the fixed-camera control. |
| seedance-1.5-pro | Video | 0.13 credits / second | Depends on duration and queue | A video model for turning an event photo into a short scene with described character motion and camera movement. DropAi offers two to twelve seconds at twenty-four frames per second, with optional fixed-camera control and audio generation for the scene. |
| seedance-2.0 | Video | 0.45 credits / second | Depends on duration and queue | A video model for animating an input photo with character movement, environmental motion, and camera directions described in the prompt. DropAi offers four to fifteen seconds at 480p or 720p, with optional audio; the selected duration applies to one continuous clip. |
| seedance-2.0-fast | Video | 0.375 credits / second | Depends on duration and queue | The Fast variant of Seedance 2 supports photo animation and short event clips using motion and camera instructions. DropAi exposes the same four-to-fifteen-second range and 480p or 720p options as Seedance 2, including the choice to generate audio. |
| seedance-2.0-mini | Video | 0.225 credits / second | Depends on duration and queue | The Mini variant of Seedance 2 supports compact photo-animation workflows and short scenes based on a starting image. DropAi retains the four-to-fifteen-second range and optional audio, but output is limited to 480p or 720p rather than 1080p. |
| seedance-2.5 | Video | 0.578 credits / second | Depends on duration and queue | A video model for turning one starting photo into an animated event scene with subject movement and generated audio. DropAi uses a 720p MP4 profile with audio enabled and framing adapted to the input photo; video files cannot be supplied as input. |
| gemini-omni-1.1 | Video | 3.75 credits / generation | Depends on duration and queue | A video model for animating one photo with generated audio, using the configured 720p landscape profile in DropAi. The provider chooses the clip duration, while DropAi charges a fixed number of credits per generation rather than billing each output second. |
| veo-3.1 | Video | 1 credits / second | Depends on duration and queue | A video model for cinematic photo animations, with scene instructions covering action, camera movement, and optional generated audio. DropAi offers four, six or eight seconds in portrait or landscape at up to 1080p, with the option to generate audio. |
| veo-3.1-fast | Video | 0.375 credits / second | Depends on duration and queue | The Fast variant of Veo 3.1 turns starting photos into short scenes with described motion and optional generated audio. DropAi retains four, six or eight seconds, output up to 1080p and optional audio, matching the controls available for standard Veo 3.1. |
| veo-3.1-lite | Video | 0.125 credits / second | Depends on duration and queue | The Lite variant of Veo 3.1 supports photo animation and short clips with defined subject and camera movement. DropAi offers four, six or eight seconds at 720p or 1080p, but does not expose the optional audio control available in other Veo variants. |
| Kuaishou | ||||
| kling-v3-video | Video | 0.42 credits / second | Depends on duration and queue | A Kling video model for animating a starting photo with staged action, camera movement, and optional generated sound. DropAi offers three to fifteen seconds and a choice between 720p Standard and 1080p Pro, with optional generated audio for either mode. |
| Pruna | ||||
| p-video | Video | 0.05 credits / second | Depends on duration and queue | A video model for animating event photos into short scenes with character actions, moving backgrounds, and camera movement. DropAi offers one to twenty seconds at 720p or 1080p, plus a choice of twenty-four or forty-eight frames per second. |
| p-video-2 | Video | 0.075 credits / second | Depends on duration and queue | A video model for animating one photo into an event clip with subject motion, camera movement, and sound. DropAi uses 720p at twenty-four frames per second with audio enabled; describe one clear action and the intended movement of the camera. |
| p-video-2-pro | Video | 0.0875 credits / second | Depends on duration and queue | The Pro variant of P-Video 2 supports photo animation with movement instructions for the subject, background, and camera. DropAi uses the 768p speed profile with automatic prompt expansion disabled, so the requested action should be stated clearly in the description. |
| Vidu | ||||
| q3-turbo | Video | 0.15 credits / second | Depends on duration and queue | A video model for animating a starting photo into a short scene, with generated sound and a described action. DropAi offers one to sixteen seconds with optional audio, but output is fixed at 720p, so this integration does not provide 1080p. |
| xAI | ||||
| grok-imagine-video | Video | 0.125 credits / second | Depends on duration and queue | A video model for turning an event photo into a short promotional scene with motion and generated sound. DropAi offers one to fifteen seconds and output at 480p or 720p, with selectable portrait, square or landscape framing for the clip. |
Add movement to your theme
A portrait can become the starting point for a moving scene. Choose from the durations, formats and options available for your video model.
Share a film guests can keep
The result page brings playback and download together. Review the full clip before sharing, including faces, movement and the final frame.
You can use an AI image as the starting point for a video. Creating the image and the video are separate paid generations.
Frequently asked questions
Can I choose any video length?
Choose from the durations and formats offered for your selected model and configuration. Duration and settings can affect the credit price. Image and video generation are charged separately.