docs/finetrainers/examples_training_wan_image_conditioning__ttraining.json

{
  "datasets": [
    {
      "data_root": "recoilme/aesthetic_photos_xs",
      "dataset_type": "image",
      "image_resolution_buckets": [
        [1024, 1024]
      ],
      "reshape_mode": "bicubic",
      "remove_common_llm_caption_prefixes": true
    },
    {
      "data_root": "finetrainers/OpenVid-1k-split",
      "dataset_type": "video",
      "video_resolution_buckets": [
        [49, 512, 512],
        [49, 768, 768],
        [49, 1024, 1024],
        [49, 480, 704],
        [49, 704, 480]
      ],
      "reshape_mode": "bicubic",
      "remove_common_llm_caption_prefixes": true
    }
  ]
}