Back to Nodes
Ovi Image To Video

Ovi Image To Video

Official

Ovi generates videos with audio from both image and text inputs, providing a unique multimodal creation experience.

Nodespell AI
AI / Video / Character Ai

Ovi generates videos with audio from both image and text inputs, providing a unique multimodal creation experience.

Model Overview

Ovi is an image-to-video generation model that creates videos with audio based on an input image and a descriptive text prompt. It's designed to bring still images to life with motion and sound.

Best At

  • Generating short, engaging videos from a single image and a text prompt.
  • Creating videos with synchronized audio based on detailed text descriptions.

Limitations / Not Good At

  • May struggle with complex scenes or nuanced audio descriptions.
  • Video quality and coherence depend heavily on the quality of the input image and prompt.

Ideal Use Cases

  • Social media content creation.
  • Visual storytelling and concept showcasing.
  • Generating dynamic content for presentations.

Input & Output Format

  • Input: Image URL and Text Prompt.
  • Output: Video file (mp4).

Performance Notes

  • Generation speed depends on the complexity of the prompt and the number of inference steps specified.
Inputs (2)

Prompt

String

The text prompt to guide video generation.

Multi InputMin: 0Max: 100

Image

String

The image to guide video generation.

Multi InputMin: 0Max: 100
Parameters (6)

Prompt

String

The text prompt to guide video generation.

Default:

Seed

Number

Random seed for reproducibility. If None, a random seed is chosen.

Default: -1

Num Inference Steps

Number

The number of inference steps.

Default: 30

Audio Negative Prompt

String

Negative prompt for audio generation.

Default: robotic, muffled, echo, distorted

Negative Prompt

String

Negative prompt for video generation.

Default: jitter, bad hands, blur, distortion

Image Url

String

The image URL to guide video generation.

Default:
Outputs (1)

Output

Inferred

Output

Nodespell

Nodespell

📍 London

Building the future. Join us!

Type

Node

Status

Official

Package

Nodespell AI

Category

AI / Video / Character Ai

Input

TextImage

Output

Video

Keywords

Video GenerationAudio EnhancementConditional Generation
Use in Workflow