BLIP3o/BLIP3o-Model-4B
14604
1{2 "_class_name": "UNet2DConditionModel",3 "_diffusers_version": "0.21.2",4 "_name_or_path": "/share/project/quansun/release_hf/Emu2-VisualGeneration/unet",5 "act_fn": "silu",6 "addition_embed_type": "text_time",7 "addition_embed_type_num_heads": 64,8 "addition_time_embed_dim": 256,9 "attention_head_dim": [10 5,11 10,12 2013 ],14 "attention_type": "default",15 "block_out_channels": [16 320,17 640,18 128019 ],20 "center_input_sample": false,21 "class_embed_type": null,22 "class_embeddings_concat": false,23 "conv_in_kernel": 3,24 "conv_out_kernel": 3,25 "cross_attention_dim": 1792,26 "cross_attention_norm": null,27 "down_block_types": [28 "DownBlock2D",29 "CrossAttnDownBlock2D",30 "CrossAttnDownBlock2D"31 ],32 "downsample_padding": 1,33 "dropout": 0.0,34 "dual_cross_attention": false,35 "encoder_hid_dim": null,36 "encoder_hid_dim_type": null,37 "flip_sin_to_cos": true,38 "freq_shift": 0,39 "in_channels": 4,40 "layers_per_block": 2,41 "mid_block_only_cross_attention": null,42 "mid_block_scale_factor": 1,43 "mid_block_type": "UNetMidBlock2DCrossAttn",44 "norm_eps": 1e-05,45 "norm_num_groups": 32,46 "num_attention_heads": null,47 "num_class_embeds": null,48 "only_cross_attention": false,49 "out_channels": 4,50 "projection_class_embeddings_input_dim": 3328,51 "resnet_out_scale_factor": 1.0,52 "resnet_skip_time_act": false,53 "resnet_time_scale_shift": "default",54 "sample_size": 128,55 "time_cond_proj_dim": null,56 "time_embedding_act_fn": null,57 "time_embedding_dim": null,58 "time_embedding_type": "positional",59 "timestep_post_act": null,60 "transformer_layers_per_block": [61 1,62 2,63 1064 ],65 "up_block_types": [66 "CrossAttnUpBlock2D",67 "CrossAttnUpBlock2D",68 "UpBlock2D"69 ],70 "upcast_attention": null,71 "use_linear_projection": true72}73 