{ "architectures": [ "PixelDiTModel" ], "dtype": "float32", "hidden_size": 1536, "in_channels": 3, "model_type": "pixeldit", "num_groups": 24, "num_text_blocks": 4, "patch_depth": 14, "patch_size": 16, "pixel_attn_hidden_size": 1152, "pixel_depth": 2, "pixel_hidden_size": 16, "pixel_num_groups": 16, "repa_encoder_index": -1, "text_rope_theta": 10000.0, "transformers_version": "5.9.0", "txt_embed_dim": 2304, "txt_max_length": 300, "use_pixel_abs_pos": true, "use_text_rope": true }