transformer/config.json

{
  "_class_name": "SAPIImageGenTransformer2DModel",
  "_diffusers_version": "0.31.0.dev0",
  "dual_attention_layers": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12],
  "attention_head_dim": 64,
  "caption_projection_dim": 1536,
  "in_channels": 16,
  "joint_attention_dim": 4096,
  "num_attention_heads": 24,
  "num_layers": 24,
  "out_channels": 16,
  "patch_size": 2,
  "pooled_projection_dim": 2048,
  "pos_embed_max_size": 384,
  "qk_norm": "rms_norm",
  "sample_size": 128
}