Update unet/config.json

unet/config.json

@@ -1,11 +1,13 @@
 {
   "_class_name": "UNet2DConditionModel",
-  "_diffusers_version": "0.19.0",
+  "_diffusers_version": "0.10.0.dev0",
   "act_fn": "silu",
-  "addition_embed_type": null,
-  "addition_embed_type_num_heads": 64,
-  "addition_time_embed_dim": null,
-  "attention_head_dim": 8,
+  "attention_head_dim": [
+    5,
+    10,
+    20,
+    20
+  ],
   "block_out_channels": [
     320,
     640,
@@ -13,12 +15,7 @@
     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,
+  "cross_attention_dim": 1024,
   "down_block_types": [
     "CrossAttnDownBlock2D",
     "CrossAttnDownBlock2D",
@@ -27,38 +24,23 @@
   ],
   "downsample_padding": 1,
   "dual_cross_attention": false,
-  "encoder_hid_dim": null,
-  "encoder_hid_dim_type": null,
   "flip_sin_to_cos": true,
   "freq_shift": 0,
   "in_channels": 4,
   "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_attention_heads": null,
   "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,
-  "transformer_layers_per_block": 1,
+  "sample_size": 96,
   "up_block_types": [
     "UpBlock2D",
     "CrossAttnUpBlock2D",
     "CrossAttnUpBlock2D",
     "CrossAttnUpBlock2D"
   ],
-  "upcast_attention": null,
-  "use_linear_projection": false
-}
+  "use_linear_projection": true,
+  "upcast_attention": true
+}