Veo 3.1 Fast
Text-to-video generator with higher-fidelity output and support for contextual audio and frame-based transitions.
Text-to-video generator with higher-fidelity output and support for contextual audio and frame-based transitions.
Model Overview
The new Veo 3.1 Fast model creates high-quality video from text prompts, adding features like context-aware audio and the ability to transition between two images. 🎬✨
Best At 🚀
- Generating polished video clips from simple text descriptions.
- Creating smooth transitions between two images using last frame support.
- Adding context-responsive audio to the generated videos.
Ideal Use Cases 🎯
- Product Demos: Generate a short demo video from a product image and a descriptive prompt.
- Storyboard Animations: Bring storyboards to life by transitioning between key frames.
- Promotional Videos: Quickly create engaging trailer-like videos for marketing.
Input & Output Format 📥📤
- Input:
- Text Prompt (required): Describe what you want in the video.
- Optional Video Settings:
- Aspect Ratio (e.g., "16:9")
- Duration (in seconds)
- Resolution (e.g., "720p")
- Audio Generation (toggle)
- Optional Images:
- Starting Image (for generating from a base frame)
- Ending Image (for creating a transition between two frames)
- Output:
- A URL (URI) pointing to the generated MP4 video file.
Prompt
StringText prompt for video generation
Image
StringInput image to start generating from. Ideal images are 16:9 or 9:16 and 1280x720 or 720x1280, depending on the aspect ratio you choose.
Last Frame
StringEnding image for interpolation. When provided with an input image, creates a transition between the two images.
Seed
NumberRandom seed. Omit for random generations
-1Prompt
StringText prompt for video generation
Duration
NumberVideo duration in seconds
8Resolution
StringResolution of the generated video
1080pAspect Ratio
StringVideo aspect ratio
16:9Generate Audio
BooleanGenerate audio with the video
trueNegative Prompt
StringDescription of what to exclude from the generated video
Output
InferredOutput
Type
Node
Status
Official
Package
Nodespell AI
Category
AI / Video / GoogleInput
Output