+ unet

config.json

@@ -1,24 +1,29 @@
 {
-  "architectures": [
-    "CLIPTextModel"
+  "_class_name": "UNetGLIDEModel",
+  "attention_resolutions": [
+    2,
+    4,
+    8
   ],
-  "attention_dropout": 0.0,
-  "bos_token_id": 0,
-  "dropout": 0.0,
-  "eos_token_id": 2,
-  "hidden_act": "quick_gelu",
-  "hidden_size": 512,
-  "initializer_factor": 1.0,
-  "initializer_range": 0.02,
-  "intermediate_size": 2048,
-  "layer_norm_eps": 1e-05,
-  "max_position_embeddings": 128,
-  "model_type": "clip_text_model",
-  "num_attention_heads": 8,
-  "num_hidden_layers": 16,
-  "pad_token_id": 1,
-  "torch_dtype": "float32",
-  "transformers_version": "4.20.0.dev0",
-  "use_padding_embeddings": true,
-  "vocab_size": 49408
+  "channel_mult": [
+    1,
+    2,
+    3,
+    4
+  ],
+  "conv_resample": true,
+  "dims": 2,
+  "dropout": 0.1,
+  "encoder_channels": null,
+  "in_channels": 3,
+  "model_channels": 192,
+  "num_head_channels": 64,
+  "num_heads": 1,
+  "num_heads_upsample": 1,
+  "num_res_blocks": 3,
+  "out_channels": 6,
+  "resblock_updown": true,
+  "use_checkpoint": false,
+  "use_fp16": false,
+  "use_scale_shift_norm": true
 }

diffusion_model.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:716239d332ee5f0d57184cdd46e3ff8f39754db0d38e4a727007705658081b1d
+size 1180750153