unet/config.json

 {
   "_class_name": "UNet2DConditionModel",
   "_diffusers_version": "0.17.0.dev0",
   "model_channels": 384,
   "num_channels": 4,
   "init_channels": 192,
   "time_embed_dim": 1536,
   "context_dim": 4096,
   "model_dim": 4096,
   "groups": 32,
   "head_dim": 64,
   "expansion_ratio": 4,
   "compression_ratio": 2,
   "dim_mult": [1, 2, 4, 8],
   "num_blocks": [3, 3, 3, 3],
   "add_cross_attention": [false, true, true, true],
   "add_self_attention": [false, true, true, true]
}