preprocessor_config.json

{
  "processor_class": "MiniMaxVLProcessor",
  "auto_map": {
    "AutoImageProcessor": "image_processor.MiniMaxM3VLImageProcessor",
    "AutoProcessor": "processing_minimax.MiniMaxVLProcessor",
    "AutoVideoProcessor": "video_processor.MiniMaxM3VLVideoProcessor"
  },
  "process_image_mode": "dynamic_res",
  "image_mean": [
    0.48145466,
    0.4578275,
    0.40821073
  ],
  "image_std": [
    0.26862954,
    0.26130258,
    0.27577711
  ],
  "size": [
    672,
    672
  ],
  "patch_size": 14,
  "img_token_compression_config": {
    "image_token_compression_threshold": 1.1,
    "image_token_compression_method": "patch_merge",
    "max_image_resolution": 1008,
    "spatial_merge_size": 2,
    "temporal_patch_size": 2
  },
  "add_start_end_special_tokens": true
}