unet/config.json

{
    "_class_name": "Transformer3DModel",
    "_diffusers_version": "0.25.1",
    "_name_or_path": "PixArt-alpha/PixArt-XL-2-256x256",
    "activation_fn": "gelu-approximate",
    "attention_bias": true,
    "attention_head_dim": 64,
    "attention_type": "default",
    "caption_channels": 4096,
    "cross_attention_dim": 2048,
    "double_self_attention": false,
    "dropout": 0.0,
    "in_channels": 128,
    "norm_elementwise_affine": false,
    "norm_eps": 1e-06,
    "norm_num_groups": 32,
    "num_attention_heads": 32,
    "num_embeds_ada_norm": 1000,
    "num_layers": 28,
    "num_vector_embeds": null,
    "only_cross_attention": false,
    "out_channels": 128,
    "project_to_2d_pos": true,
    "upcast_attention": false,
    "use_linear_projection": false,
    "qk_norm": "rms_norm",
    "standardization_norm": "rms_norm",
    "positional_embedding_type": "rope",
    "positional_embedding_theta": 10000.0,
    "positional_embedding_max_pos": [20, 2048, 2048],
    "timestep_scale_multiplier": 1000
}