unet/config.json
| 1 | { |
| 2 | "_class_name": "UNet2DConditionModel", |
| 3 | "_diffusers_version": "0.17.1", |
| 4 | "act_fn": "silu", |
| 5 | "addition_embed_type": null, |
| 6 | "addition_embed_type_num_heads": 64, |
| 7 | "attention_head_dim": 8, |
| 8 | "block_out_channels": [ |
| 9 | 320, |
| 10 | 640, |
| 11 | 1280, |
| 12 | 1280 |
| 13 | ], |
| 14 | "center_input_sample": false, |
| 15 | "class_embed_type": null, |
| 16 | "class_embeddings_concat": false, |
| 17 | "conv_in_kernel": 3, |
| 18 | "conv_out_kernel": 3, |
| 19 | "cross_attention_dim": 768, |
| 20 | "cross_attention_norm": null, |
| 21 | "down_block_types": [ |
| 22 | "CrossAttnDownBlock2D", |
| 23 | "CrossAttnDownBlock2D", |
| 24 | "CrossAttnDownBlock2D", |
| 25 | "DownBlock2D" |
| 26 | ], |
| 27 | "downsample_padding": 1, |
| 28 | "dual_cross_attention": false, |
| 29 | "encoder_hid_dim": null, |
| 30 | "encoder_hid_dim_type": null, |
| 31 | "flip_sin_to_cos": true, |
| 32 | "freq_shift": 0, |
| 33 | "in_channels": 4, |
| 34 | "layers_per_block": 2, |
| 35 | "mid_block_only_cross_attention": null, |
| 36 | "mid_block_scale_factor": 1, |
| 37 | "mid_block_type": "UNetMidBlock2DCrossAttn", |
| 38 | "norm_eps": 1e-05, |
| 39 | "norm_num_groups": 32, |
| 40 | "num_class_embeds": null, |
| 41 | "only_cross_attention": false, |
| 42 | "out_channels": 4, |
| 43 | "projection_class_embeddings_input_dim": null, |
| 44 | "resnet_out_scale_factor": 1.0, |
| 45 | "resnet_skip_time_act": false, |
| 46 | "resnet_time_scale_shift": "default", |
| 47 | "sample_size": 64, |
| 48 | "time_cond_proj_dim": null, |
| 49 | "time_embedding_act_fn": null, |
| 50 | "time_embedding_dim": null, |
| 51 | "time_embedding_type": "positional", |
| 52 | "timestep_post_act": null, |
| 53 | "up_block_types": [ |
| 54 | "UpBlock2D", |
| 55 | "CrossAttnUpBlock2D", |
| 56 | "CrossAttnUpBlock2D", |
| 57 | "CrossAttnUpBlock2D" |
| 58 | ], |
| 59 | "upcast_attention": null, |
| 60 | "use_linear_projection": false |
| 61 | } |
| 62 | |