{ "_class_name": "UNet2DConditionModel", "_diffusers_version": "0.22.0.dev0", "_name_or_path": "stabilityai/stable-diffusion-2-1-base", "act_fn": "silu", "addition_embed_type": null, "addition_embed_type_num_heads": 64, "addition_time_embed_dim": null, "attention_head_dim": [ 5, 10, 20, 20 ], "attention_type": "default", "block_out_channels": [ 320, 640, 1280, 1280 ], "center_input_sample": false, "class_embed_type": null, "class_embeddings_concat": false, "conv_in_kernel": 3, "conv_out_kernel": 3, "cross_attention_dim": 1024, "cross_attention_norm": null, "decay": 0.9999, "down_block_types": [ "CrossAttnDownBlock2D", "CrossAttnDownBlock2D", "CrossAttnDownBlock2D", "DownBlock2D" ], "downsample_padding": 1, "dropout": 0.0, "dual_cross_attention": false, "encoder_hid_dim": null, "encoder_hid_dim_type": null, "flip_sin_to_cos": true, "freq_shift": 0, "in_channels": 4, "inv_gamma": 1.0, "layers_per_block": 2, "mid_block_only_cross_attention": null, "mid_block_scale_factor": 1, "mid_block_type": "UNetMidBlock2DCrossAttn", "min_decay": 0.0, "norm_eps": 1e-05, "norm_num_groups": 32, "num_attention_heads": null, "num_class_embeds": null, "only_cross_attention": false, "optimization_step": 12500, "out_channels": 4, "power": 0.6666666666666666, "projection_class_embeddings_input_dim": null, "resnet_out_scale_factor": 1.0, "resnet_skip_time_act": false, "resnet_time_scale_shift": "default", "reverse_transformer_layers_per_block": null, "sample_size": 64, "time_cond_proj_dim": null, "time_embedding_act_fn": null, "time_embedding_dim": null, "time_embedding_type": "positional", "timestep_post_act": null, "transformer_layers_per_block": 1, "up_block_types": [ "UpBlock2D", "CrossAttnUpBlock2D", "CrossAttnUpBlock2D", "CrossAttnUpBlock2D" ], "upcast_attention": false, "update_after_step": 0, "use_ema_warmup": false, "use_linear_projection": true }