AI Media Generate (Genbo) icon

AI Media Generate (Genbo)

Generate AI media content (images, videos, and audio) using Genbo platform

AI Media Generate (Genbo)

AI-generated

Summary

Generate media using the Genbo platform model selected by model. Consumes a required text prompt and model-specific parameters; output is model-dependent.

Inputs

  • model (required) — Select the Genbo model (e.g., zImageTurbo, flux2Dev, flux2Edit, wan22T2V, wan22I2V, infiniteTalk, indexTTS2Single, etc.). Determines which parameter group is active. Loaded dynamically via getModelOptions.
  • prompt (required) — The text prompt describing the desired media. Required for all model groups. Rows-based input string.

Output shape

Model-dependent generated media output (image, video, or audio). Typically a URL or binary data passed to the next n8n node.

No explicit return shape declared in properties or source; output depends on the active model's implementation.

Examples

Example 1: Image generation with zImageTurbo

Select model 'zImageTurbo', provide a prompt. Optional: set image_size, num_images, num_inference_steps.

Example 2: Text-to-video with wan22T2V

Select model 'wan22T2V', provide a prompt. Optional: set video_url (for image-to-video), aspect_ratio, resolution, num_frames, frames_per_second, guidance_scale, guidance_scale_2, shift, negative_prompt.

Example 3: Speech generation with indexTTS2Single

Select model 'indexTTS2Single', provide a prompt with speaker tags. Optional: set audio_url, temperature, max_length, use_random, unload_model, use_emo_text, emo_alpha.

Links

Discussion