Skip to main content
Video models generate short video clips, with or without sound. You describe the scene in a text prompt, or provide an image for the model to bring to life. Use them for product teasers, animated social posts, background loops, and storyboard previews. One model improves video you already have instead of generating a new clip. Ask Lovable to:
  • Generate a video clip from a text description.
  • Animate an uploaded image into a short clip.
  • Produce a vertical clip for social media.
  • Feature a specific product, person, or character in a new scene by supplying reference photos of the subject.
  • Turn two images into a clip that starts on one and ends on the other.
  • Change what an existing video shows by describing the edit, whether the clip was generated earlier or uploaded by your app’s users.
  • Extend an existing video to build a longer one.
  • Restore and upscale an existing video to 1080p or 4K, keeping its original frame rate.
Ask for any of these in the project chat, and Lovable writes the feature and the backend call behind it. See Add an AI feature to your app for the whole flow, including publishing. On Enterprise workspaces, Gemini Omni 1.1 Flash, Seedance 2.5, and Topaz Starlight Fast 2 are available only after workspace admins and owners enable Extended-retention models and accept the terms shown there. Until then, Veo 3.1 is the default, and your app cannot restore a clip.

​
Compare the video models

A clip from Gemini Omni 1.1 Flash or a Veo model arrives as an MP4 file, in landscape (16:9) or portrait (9:16). Gemini Omni 1.1 Flash always generates a soundtrack, and on the Veo models you ask for sound when you want it. Gemini Omni 1.1 Flash and the Veo models differ in clip length, resolutions, and what they can do with existing footage: On Gemini Omni 1.1 Flash, a 360p clip costs about a third of the same clip at 720p, which makes 360p a low-cost way to draft a clip before regenerating it at full quality.

​
Start from your own images

Instead of describing everything in text, you can start from your own images:
  • Animate an uploaded image. The clip starts from your exact photo and sets it in motion, so the photo’s scene and framing stay.
  • Supply two images as the first and last frame. The model generates the motion between them, which is a simple way to make a transition between two visuals. This works on Gemini Omni 1.1 Flash, Veo 3.1, and Veo 3.1 Fast.
  • Supply reference photos of a subject. Provide photos of the same product, person, or character, and the model places that subject into a freshly generated scene described by your prompt. Unlike animating a photo, nothing from the photos appears directly in the clip: the photos only fix what the subject looks like, and the scene around it is newly generated. Several angles of the same subject improve fidelity.

​
Edit and extend a video

Gemini Omni 1.1 Flash also works with existing footage, whether Lovable generated it earlier or your app’s users uploaded it. To edit a video, describe one change, such as swapping the background or replacing an object, and Lovable regenerates the clip with that change applied at the same length. To build a longer video, ask Lovable to extend a clip: each extension continues the same scene and produces a single merged video, which you can extend again. The Veo models can also extend clips they generated. Either way, only the new seconds are billed.

​
Generation time, storage, and cost

Generating a clip usually takes 1 to 3 minutes, so video works differently from chat or images: the clip is generated in the background, and your app checks on it until it is done. Write the prompt in English. Google recommends it for these models. The Veo models also rewrite the prompt before generating, so the finished clip follows the intent of your prompt rather than its exact wording. A finished clip stays available to your app for 48 hours. If your app should show a video again later, or keep it permanently, ask Lovable to save it to your app’s own storage. Generating video uses credits. The model, the resolution, and the length decide what a clip costs, and a single clip costs far more than a typical chat response. You are charged when a generation completes, even if your app stops waiting or never shows the clip. Failed generations are not charged. Each project also generates a limited number of clips at the same time: 1 on Free plans, and up to 10 on paid plans. See Usage and pricing and Workspace rate limits.

​
Restore and upscale an existing video

Your app can rebuild the detail in a blurry, noisy, or low-resolution clip with Topaz Starlight Fast 2 and output it at 1080p or 4K. The restored clip keeps the original frame rate. Use the model for older recordings, or for video your app’s users upload. The clip you start from can be up to 10 minutes long. Workspace admins and owners open Connectors, select AI, enable TopazLabs, and accept the terms shown there. On Enterprise workspaces, they also enable Extended-retention models. Until then, Lovable cannot add the feature and your app cannot use the model. Restoring a clip takes much longer than generating one, and a long clip can run for hours. Your app can cancel the job while Lovable prepares the clip, but not after the restoration itself starts. From that point the job runs to the end and is charged. Your credit balance drops when the job starts, not when it finishes. If the job fails, the credits come back. A longer clip costs more than a shorter one, and 4K costs more than 1080p. The restored clip stays available to your app for 48 hours, the same as a generated clip. The 48 hours are counted from when your app starts the job, not from when it finishes. A long job leaves less time to save the result.