Epoch 0

logs/train_unet/events.out.tfevents.1694194250.d6466ec610d1.128260.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:15cd596455b3cb83b13e9ca3a35decaf3445f71347b308a5a22b946c12a8df83
-size 27023395
+oid sha256:93b6b41ce0d38694a55fababb725913a184fc11c00bc003c4c2744fb33bdbbac
+size 28360560

logs/train_unet/events.out.tfevents.1694199536.d6466ec610d1.156816.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d9ea1eeead060b999080b828057fb9eb12352d58b83e18b148305151a4ef69d
+size 80430

model_index.json

@@ -11,7 +11,7 @@
   ],
   "unet": [
     "diffusers",
-    "UNet2DConditionModel"
+    "UNet2DModel"
   ],
   "vqvae": [
     "diffusers",

unet/config.json

@@ -1,68 +1,51 @@
 {
-  "_class_name": "UNet2DConditionModel",
+  "_class_name": "UNet2DModel",
   "_diffusers_version": "0.20.2",
   "act_fn": "silu",
-  "addition_embed_type": null,
-  "addition_embed_type_num_heads": 64,
-  "addition_time_embed_dim": null,
+  "add_attention": true,
   "attention_head_dim": 8,
-  "attention_type": "default",
   "block_out_channels": [
     128,
+    128,
+    256,
     256,
     512,
     512
   ],
   "center_input_sample": false,
   "class_embed_type": null,
-  "class_embeddings_concat": false,
-  "conv_in_kernel": 3,
-  "conv_out_kernel": 3,
-  "cross_attention_dim": 256,
-  "cross_attention_norm": null,
   "down_block_types": [
-    "CrossAttnDownBlock2D",
-    "CrossAttnDownBlock2D",
-    "CrossAttnDownBlock2D",
+    "DownBlock2D",
+    "DownBlock2D",
+    "DownBlock2D",
+    "DownBlock2D",
+    "AttnDownBlock2D",
     "DownBlock2D"
   ],
   "downsample_padding": 1,
-  "dual_cross_attention": false,
-  "encoder_hid_dim": null,
-  "encoder_hid_dim_type": null,
+  "downsample_type": "conv",
   "flip_sin_to_cos": true,
   "freq_shift": 0,
   "in_channels": 1,
   "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": 1,
-  "projection_class_embeddings_input_dim": null,
-  "resnet_out_scale_factor": 1.0,
-  "resnet_skip_time_act": false,
   "resnet_time_scale_shift": "default",
   "sample_size": [
     32,
     32
   ],
-  "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,
   "up_block_types": [
     "UpBlock2D",
-    "CrossAttnUpBlock2D",
-    "CrossAttnUpBlock2D",
-    "CrossAttnUpBlock2D"
+    "AttnUpBlock2D",
+    "UpBlock2D",
+    "UpBlock2D",
+    "UpBlock2D",
+    "UpBlock2D"
   ],
-  "upcast_attention": false,
-  "use_linear_projection": false
+  "upsample_type": "conv"
 }

unet/diffusion_pytorch_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d85981ca6faf9ee5bb49625edb0d5bd77fa5c21932aae8c9d88d12972d2ff798
-size 548551292
+oid sha256:6a1bc7b786dcb9087f194d52fb6e6bbfe44b30413f05eb9eef29d12623f9fb91
+size 454722660