xiaomi-research/OneVL_visual_decoder_pt_ar1

1{2  "auto_map": {3    "AutoProcessor": "processing_qwen3vl_visual.Qwen3VLVisualProcessor"4  },5  "crop_size": null,6  "data_format": "channels_first",7  "default_to_square": true,8  "device": null,9  "do_center_crop": null,10  "do_convert_rgb": true,11  "do_normalize": true,12  "do_rescale": true,13  "do_resize": true,14  "do_sample_frames": true,15  "fps": 2,16  "image_mean": [17    0.5,18    0.5,19    0.520  ],21  "image_std": [22    0.5,23    0.5,24    0.525  ],26  "input_data_format": null,27  "max_frames": 768,28  "merge_size": 2,29  "min_frames": 4,30  "num_frames": null,31  "pad_size": null,32  "patch_size": 16,33  "processor_class": "Qwen3VLVisualProcessor",34  "resample": 3,35  "rescale_factor": 0.00392156862745098,36  "return_metadata": false,37  "size": {38    "longest_edge": 25165824,39    "shortest_edge": 409640  },41  "temporal_patch_size": 2,42  "video_metadata": null,43  "video_processor_type": "Qwen3VLVideoProcessor"44}45