unet improve

unet/config.json

@@ -1,7 +1,9 @@
 {
   "_class_name": "UNet2DConditionModel",
-  "_diffusers_version": "0.6.0.dev0",
+  "_diffusers_version": "0.16.1",
   "act_fn": "silu",
+  "addition_embed_type": null,
+  "addition_embed_type_num_heads": 64,
   "attention_head_dim": 8,
   "block_out_channels": [
     320,
@@ -10,7 +12,12 @@
     1280
   ],
   "center_input_sample": false,
+  "class_embed_type": null,
+  "class_embeddings_concat": false,
+  "conv_in_kernel": 3,
+  "conv_out_kernel": 3,
   "cross_attention_dim": 768,
+  "cross_attention_norm": null,
   "down_block_types": [
     "CrossAttnDownBlock2D",
     "CrossAttnDownBlock2D",
@@ -18,19 +25,36 @@
     "DownBlock2D"
   ],
   "downsample_padding": 1,
+  "dual_cross_attention": false,
+  "encoder_hid_dim": null,
   "flip_sin_to_cos": true,
   "freq_shift": 0,
   "in_channels": 9,
   "layers_per_block": 2,
+  "mid_block_only_cross_attention": null,
   "mid_block_scale_factor": 1,
+  "mid_block_type": "UNetMidBlock2DCrossAttn",
   "norm_eps": 1e-05,
   "norm_num_groups": 32,
+  "num_class_embeds": null,
+  "only_cross_attention": false,
   "out_channels": 4,
+  "projection_class_embeddings_input_dim": null,
+  "resnet_out_scale_factor": 1.0,
+  "resnet_skip_time_act": false,
+  "resnet_time_scale_shift": "default",
   "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,
   "up_block_types": [
     "UpBlock2D",
     "CrossAttnUpBlock2D",
     "CrossAttnUpBlock2D",
     "CrossAttnUpBlock2D"
-  ]
+  ],
+  "upcast_attention": false,
+  "use_linear_projection": false
 }

unet/diffusion_pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63692153675d112389b4ad7adc3b8cebab20902dfaa942bc3eef16a6489bab0f
+size 1719353253