Upload config.json with huggingface_hub

config.json

@@ -1,30 +1,77 @@
 {
-  "_class_name": "AutoencoderKL",
+  "_class_name": "UNet2DConditionModel",
   "_commit_hash": null,
   "_diffusers_version": "0.21.0.dev0",
-  "_name_or_path": "/home/ubuntu/.cache/huggingface/hub/models--stabilityai--stable-diffusion-2-1-base/snapshots/5ede9e4bf3e3fd1cb0ef2f7a3fff13ee514fdf06/vae",
+  "_name_or_path": "/home/ubuntu/.cache/huggingface/hub/models--stabilityai--stable-diffusion-2-1-base/snapshots/5ede9e4bf3e3fd1cb0ef2f7a3fff13ee514fdf06/unet",
   "_use_default_values": [
-    "scaling_factor",
-    "force_upcast"
+    "conv_in_kernel",
+    "mid_block_type",
+    "projection_class_embeddings_input_dim",
+    "cross_attention_norm",
+    "addition_time_embed_dim",
+    "addition_embed_type_num_heads",
+    "class_embed_type",
+    "mid_block_only_cross_attention",
+    "encoder_hid_dim",
+    "resnet_out_scale_factor",
+    "time_cond_proj_dim",
+    "conv_out_kernel",
+    "attention_type",
+    "resnet_skip_time_act",
+    "transformer_layers_per_block",
+    "time_embedding_type",
+    "time_embedding_act_fn",
+    "addition_embed_type",
+    "encoder_hid_dim_type",
+    "class_embeddings_concat",
+    "upcast_attention",
+    "num_attention_heads",
+    "resnet_time_scale_shift",
+    "timestep_post_act",
+    "time_embedding_dim"
   ],
   "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": [
-    128,
-    256,
-    512,
-    512
+    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,
   "down_block_types": [
-    "DownEncoderBlock2D",
-    "DownEncoderBlock2D",
-    "DownEncoderBlock2D",
-    "DownEncoderBlock2D"
+    "CrossAttnDownBlock2D",
+    "CrossAttnDownBlock2D",
+    "CrossAttnDownBlock2D",
+    "DownBlock2D"
   ],
-  "force_upcast": true,
-  "in_channels": 3,
-  "latent_channels": 4,
+  "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,
-  "model_type": "vae-decoder",
+  "mid_block_only_cross_attention": null,
+  "mid_block_scale_factor": 1,
+  "mid_block_type": "UNetMidBlock2DCrossAttn",
+  "model_type": "unet",
   "neuron": {
     "auto_cast": null,
     "auto_cast_type": null,
@@ -32,7 +79,9 @@
     "compiler_version": "2.8.0.25+a3ad0f342",
     "dynamic_batch_size": false,
     "input_names": [
-      "latent_sample"
+      "sample",
+      "timestep",
+      "encoder_hidden_states"
     ],
     "output_names": [
       "sample"
@@ -40,17 +89,33 @@
     "static_batch_size": 1,
     "static_height": 64,
     "static_num_channels": 4,
+    "static_sequence_length": 77,
     "static_width": 64
   },
+  "norm_eps": 1e-05,
   "norm_num_groups": 32,
-  "out_channels": 3,
-  "sample_size": 768,
-  "scaling_factor": 0.18215,
+  "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,
   "transformers_version": null,
   "up_block_types": [
-    "UpDecoderBlock2D",
-    "UpDecoderBlock2D",
-    "UpDecoderBlock2D",
-    "UpDecoderBlock2D"
-  ]
+    "UpBlock2D",
+    "CrossAttnUpBlock2D",
+    "CrossAttnUpBlock2D",
+    "CrossAttnUpBlock2D"
+  ],
+  "upcast_attention": false,
+  "use_linear_projection": true
 }