Wiro - Memo
AI-generatedOverview
This node integrates with the Wiro API to generate expressive talking videos using memory-guided diffusion. It takes an input image URL and an input audio URL, along with parameters like resolution, frames per second (fps), configuration value (guidance scale), inference steps, and a seed value. The node sends these inputs to the Wiro API, initiates a video generation task, and polls the task status until completion. Upon completion, it outputs the task status and the URL of the generated video. This node is useful for creating talking video content from static images and audio inputs, such as animated avatars or expressive video messages.
Use Case Examples
- Generating a talking video from a portrait image and a voice recording to create an animated avatar.
- Producing expressive video content for marketing or social media by combining a static image with audio narration.
Properties
| Name | Meaning |
|---|---|
| Input Image URL | URL of the input image to be used for video generation. |
| Input Audio URL | URL of the input audio to be used for synchronizing the talking video. |
| Resolution | Resolution setting for the output video. |
| Fps | Frames per second for the output video. |
| Config Value | Guidance scale parameter influencing the video generation process. |
| Inferencesteps | Number of inference steps for the video generation process. |
| Seed | Seed value for randomization control in the video generation. |
Output
JSON
taskid- Identifier of the video generation task.url- URL of the generated talking video.status- Status of the video generation task, e.g., 'completed' or 'failed'.
Dependencies
- Wiro API with API key and secret for authentication
Troubleshooting
- If the node throws an error about missing task ID or socket access token, verify that the Wiro API credentials are correct and the API is responding properly.
- If the task status is 'failed', check the input URLs and parameters for correctness and ensure the Wiro API service is operational.