preprocessor_config.json

{
  "data_format": "channels_first",
  "default_to_square": true,
  "do_convert_rgb": true,
  "do_normalize": true,
  "do_rescale": true,
  "do_resize": true,
  "image_mean": [
    0.48145466,
    0.4578275,
    0.40821073
  ],
  "image_processor_type": "Qwen2VLImageProcessor",
  "image_std": [
    0.26862954,
    0.26130258,
    0.27577711
  ],
  "max_pixels": 4000000,
  "merge_size": 2,
  "min_pixels": 3136,
  "patch_size": 14,
  "processor_class": "LlavaOnevision2Processor",
  "auto_map": {
    "AutoProcessor": "processing_llava_onevision2.LlavaOnevision2Processor",
    "AutoVideoProcessor": "video_processing_llava_onevision2.LlavaOnevision2VideoProcessor"
  },
  "codec": {
    "target_canvas": 32,
    "group_size": 32,
    "images_per_group": 4,
    "patch": 14,
    "min_group_frames": 8,
    "max_group_frames": 64,
    "spatial_mask_mode": "off"
  },
  "resample": 3,
  "rescale_factor": 0.00392156862745098,
  "size": {
    "longest_edge": 4000000,
    "shortest_edge": 3136
  },
  "temporal_patch_size": 1
}