Wiro - Wan 2.6 Video Generation Model icon

Wiro - Wan 2.6 Video Generation Model

Create AI-generated videos with Wan 2.6. Transform text or images into dynamic video content. P

Wiro - Wan 2.6 Video Generation Model

AI-generated

Overview

This node integrates with the Wiro Wan 2.6 video generation model to create AI-generated videos from text prompts, images, or audio inputs. It supports various modes, resolutions, aspect ratios, and additional options like multi-shot video generation, audio inclusion, and watermarking. The node is useful for generating dynamic video content based on user-defined prompts and media inputs, suitable for creative projects, marketing videos, or content generation workflows.

Use Case Examples

  1. Generating a video from a text prompt with a specified duration and resolution.
  2. Creating a video from an input image URL with audio enabled and a watermark added.
  3. Using reference images to extract character appearance and voice for video generation.

Properties

Name Meaning
Mode Selects the generation mode, either 'pro' or 'std'. The 't2v' model only supports 'pro' mode.
Image URL Optional URL of an input image; if provided, the model determines the video ratio automatically.
Prompt The text prompt used to generate the video content.
Negative Prompt Text specifying elements to exclude from the generated video.
Audio URL Optional URL of an audio file; if provided, audioEnabled is set to true by default. Not accepted by the 'r2v' model.
References URL Optional URLs of reference images (0-5) for the 'r2v' model to extract character appearance and voice. Each image should contain only one main character.
Enabled Audio Option to enable or disable audio in the generated video. Defaults to true in 'pro' mode and only allowed for image-to-video generation.
Duration Total duration of the generated video in seconds.
Resolution Quality tier of the generated video, either 1080P or 720P.
Ratio Aspect ratio of the video. Required for text-to-video and reference-to-video generation. Ignored if an image is provided.
Shot Type Enables multi-shot or single-shot video generation.
Prompt Extend Required to be true if multi-shot is enabled for image-to-video or text-to-video generation; not used for reference-to-video.
Watermark Option to add an 'AI Generated' watermark in the lower-right corner of the video.
Seed Random seed for reproducibility of the generated video, ranging from 0 to 21474836.

Output

JSON

  • taskid - The unique identifier of the video generation task.
  • url - The URL of the generated video if the task completed successfully.
  • status - The status of the video generation task, e.g., 'completed' or 'failed'.

Dependencies

  • Wiro API with API key and secret for authentication

Troubleshooting

  • If the API response does not include a valid task ID or socket access token, the node throws an error indicating an invalid response from the Wiro API. Verify API credentials and request parameters.
  • Task status codes '-1', '-2', '-3', and '-4' indicate failure states; check the input parameters and API limits.
  • Ensure that the 'mode' parameter is set correctly, especially since the 't2v' model only supports 'pro' mode.
  • If audio is provided for the 'r2v' model, it will automatically enable audio, but the model does not accept audio files; verify compatibility.

Discussion