Setting things up…
AI video model
Veo 3.1 Fast (Image to Video)
Google Veo 3.1 Fast is an Image-to-Video model with native 1080p output for high-detail videos from images and fast performance. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
video outputfrom 60 creditsrefunded on failure
What you'll need
- Image — The image to use for the generation.
- Prompt — The positive prompt for the generation.
About Veo 3.1 Fast (Image to Video)
Veo 3.1 Fast (Image to Video) is an AI video model you can run directly in the Percify playground — fill in the inputs and generate right in your browser, or call it programmatically through the Percify API. Each run returns a ready-to-download video hosted on our CDN, and credits are only charged for successful results.
More AI video models
View the full catalogInfiniteTalk FastFast lip-sync — animate a portrait to speak any audio in seconds.InfiniteTalkLip-sync any portrait to any audio for a natural talking-avatar video.P-VideoP-Video — fast, efficient image-to-video generation.Seedance V1.5 Pro I2VSeedance 1.5 Pro — high-fidelity image-to-video.Sora 2 I2VSora 2 — turn an image into a coherent, high-quality video.Sora 2 Pro I2VSora 2 Pro — premium image-to-video with longer, sharper results.Kling v2.6 Standard Motion ControlKling 2.6 — animate a subject with motion control for cinematic video.Kling v3 Motion ControlKling 3.0 motion control: transfer motion from a reference video to any character image with improved consistency and quality.Grok Imagine Video EditGenerate videos using xAI's Grok Imagine Video modelWan 2.2 Animate ReplaceUse Wan 2.2 Animate to replace a character in a video sceneSeedance 2.0 Image-to-VideoSeedance 2 — image-to-video with smooth, dynamic motion.Seedance 2.0 Text-to-VideoSeedance 2 — generate video from a text prompt.