Veo 3.1
Veo 3.1 video generation with visual anchors and generated audio.
Veo 3.1 video generation with visual anchors and generated audio.
Veo 3.1 is the fuller Veo option in this batch: it can start from text, an image, a last frame, or reference images, and it can generate audio. Use it when a short scene needs both prompt direction and visual anchors.
The node exposes duration, resolution, aspect ratio, negative prompt, generated audio, and seed. Use reference images sparingly and describe their role, such as subject, location, palette, or framing.
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.
Reference Images
String1 to 3 reference images for subject-consistent generation (reference-to-video, or R2V). Reference images only work with 16:9 aspect ratio and 8-second duration. Last frame is ignored if reference images are provided.
Seed
NumberRandom seed. Omit for random generations
Prompt
StringText prompt for video generation
Duration
NumberVideo duration in seconds
8Resolution
StringResolution of the generated video
720pAspect 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
Nodespell Team
Type
Node
Status
Official
Package
Nodespell AI
Category
AI / Video / GoogleInput
Output