text_encoder_i2v/preprocessor_config.json

{
  "_valid_processor_keys": [
    "images",
    "do_resize",
    "size",
    "resample",
    "do_center_crop",
    "crop_size",
    "do_rescale",
    "rescale_factor",
    "do_normalize",
    "image_mean",
    "image_std",
    "do_convert_rgb",
    "return_tensors",
    "data_format",
    "input_data_format"
  ],
  "crop_size": {
    "height": 336,
    "width": 336
  },
  "do_center_crop": 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": "CLIPImageProcessor",
  "image_std": [
    0.26862954,
    0.26130258,
    0.27577711
  ],
  "processor_class": "LlavaProcessor",
  "resample": 3,
  "rescale_factor": 0.00392156862745098,
  "size": {
    "shortest_edge": 336
  }
}