Ovi
Ovi text-to-video with built-in audio prompting controls.
Ovi text-to-video with built-in audio prompting controls.
Ovi is a text-to-video node that includes negative prompt and audio-negative-prompt controls alongside resolution, steps, and seed. It is useful when video and sound direction should be considered together from a prompt.
Use Ovi Image To Video when an initial image should anchor the visual result.
Prompt
StringThe text prompt to guide video generation.
Prompt
StringThe text prompt to guide video generation.
Resolution
StringResolution of the generated video in W:H format. One of (512x992, 992x512, 960x512, 512x960, 720x720, or 448x1120).
992x512Num Inference Steps
NumberThe number of inference steps.
30Audio Negative Prompt
StringNegative prompt for audio generation.
robotic, muffled, echo, distortedNegative Prompt
StringNegative prompt for video generation.
jitter, bad hands, blur, distortionSeed
NumberRandom seed for reproducibility. If None, a random seed is chosen.
Output
InferredOutput
Nodespell Team
Type
Node
Status
Official
Package
Nodespell AI
Category
AI / Video / Character AiInput
Output