{
 "model_type": "seedvr2",
 "architectures": [
  "NaDiT"
 ],
 "vid_dim": 2560,
 "num_layers": 32,
 "mm_layers": 10,
 "heads": 20,
 "head_dim": 128,
 "vid_in_channels": 33,
 "vid_out_channels": 16,
 "patch_size": [
  1,
  2,
  2
 ],
 "rope_dim": 128,
 "window": [
  4,
  3,
  3
 ],
 "vae": {
  "latent_channels": 16,
  "spatial_downsample_factor": 8,
  "temporal_downsample_factor": 4,
  "scaling_factor": 0.9152
 },
 "_converted_by": "tests/convert_seedvr2_weights.py"
}