| from transformers import PretrainedConfig | |
| class PixelDiTConfig(PretrainedConfig): | |
| model_type = "pixeldit" | |
| def __init__( | |
| self, | |
| in_channels=3, | |
| num_groups=24, | |
| hidden_size=1536, | |
| pixel_hidden_size=16, | |
| pixel_attn_hidden_size=1152, | |
| pixel_num_groups=16, | |
| patch_depth=14, | |
| pixel_depth=2, | |
| num_text_blocks=4, | |
| patch_size=16, | |
| txt_embed_dim=2304, | |
| txt_max_length=300, | |
| use_text_rope=True, | |
| text_rope_theta=10000.0, | |
| repa_encoder_index=-1, | |
| use_pixel_abs_pos=True, | |
| **kwargs, | |
| ): | |
| super().__init__(**kwargs) | |
| self.in_channels = in_channels | |
| self.num_groups = num_groups | |
| self.hidden_size = hidden_size | |
| self.pixel_hidden_size = pixel_hidden_size | |
| self.pixel_attn_hidden_size = pixel_attn_hidden_size | |
| self.pixel_num_groups = pixel_num_groups | |
| self.patch_depth = patch_depth | |
| self.pixel_depth = pixel_depth | |
| self.num_text_blocks = num_text_blocks | |
| self.patch_size = patch_size | |
| self.txt_embed_dim = txt_embed_dim | |
| self.txt_max_length = txt_max_length | |
| self.use_text_rope = use_text_rope | |
| self.text_rope_theta = text_rope_theta | |
| self.repa_encoder_index = repa_encoder_index | |
| self.use_pixel_abs_pos = use_pixel_abs_pos | |