MiniMax-H3

by rioshiinaco.huggingface.rioshiina/minimax-h3

  • Remote endpoint
  • 3 tools

Tools

  • MiniMax_H3_get_task_list [Recommended Flow Step 1] Get a list of supported video generation task types (t2va, i2va, flf2va, ref2va) along with their required/optional parameters and paste-and-run example_json_params.
  • MiniMax_H3_get_task_status Query the progress, status, and final generated results of an async video generation task.
  • MiniMax_H3_run [Recommended Flow Step 2] Unified video generation task execution interface (t2va, i2va, flf2va, ref2va). Accepts a JSON string or dict of parameters. REQUIRED PARAMETERS PER TASK TYPE: - t2va: task_type, prompt, width, height, duration - i2va: task_type, prompt, width, height, duration, first_frame_image - flf2va: task_type, prompt, width, height, duration, first_frame_image, last_frame_image - ref2va: task_type, prompt, width, height, duration GLOBAL OPTIONAL CONTROL PARAMETERS: - seed (int): Random seed (-1 for random, >=0 for deterministic reproducibility). Default: -1. - zero_gpu_duration (int): GPU quota allocation in seconds on HuggingFace ZeroGPU spaces (default: 120). REF2VA OPTIONAL MEDIA REFERENCES: - ref_image1..9: Image file path or URL - ref_video1..3: Video file path - ref_audio1..3: Audio file path

As the server's own listing gives them. We never call a tool.