Upload folder using huggingface_hub

config-Copy1.txt

@@ -0,0 +1,78 @@
+{
+  "_class_name": "UNet2DConditionModel",
+  "_diffusers_version": "0.36.0",
+  "_name_or_path": "unet",
+  "act_fn": "silu",
+  "addition_embed_type": null,
+  "addition_embed_type_num_heads": 64,
+  "addition_time_embed_dim": null,
+  "attention_head_dim": [
+    10,
+    10,
+    10,
+    12
+  ],
+  "attention_type": "default",
+  "block_out_channels": [
+    320,
+    640,
+    1280,
+    1536
+  ],
+  "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",
+    "CrossAttnDownBlock2D",
+    "DownBlock2D"
+  ],
+  "downsample_padding": 1,
+  "dropout": 0.0,
+  "dual_cross_attention": false,
+  "encoder_hid_dim": null,
+  "encoder_hid_dim_type": null,
+  "flip_sin_to_cos": true,
+  "freq_shift": 0,
+  "in_channels": 32,
+  "layers_per_block": 2,
+  "mid_block_only_cross_attention": null,
+  "mid_block_scale_factor": 1.0,
+  "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": 32,
+  "projection_class_embeddings_input_dim": null,
+  "resnet_out_scale_factor": 1.0,
+  "resnet_skip_time_act": false,
+  "resnet_time_scale_shift": "default",
+  "reverse_transformer_layers_per_block": null,
+  "sample_size": null,
+  "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,
+    3,
+    3,
+    3
+  ],
+  "up_block_types": [
+    "UpBlock2D",
+    "CrossAttnUpBlock2D",
+    "CrossAttnUpBlock2D",
+    "CrossAttnUpBlock2D"
+  ],
+  "upcast_attention": false,
+  "use_linear_projection": false
+}

config.json

@@ -8,26 +8,29 @@
   "addition_time_embed_dim": null,
   "attention_head_dim": [
     10,
-    16,
-    20
+    10,
+    10,
+    12
   ],
   "attention_type": "default",
   "block_out_channels": [
-    1024,
-    1024,
-    1280
+    320,
+    640,
+    1280,
+    1536
   ],
   "center_input_sample": false,
   "class_embed_type": null,
   "class_embeddings_concat": false,
-  "conv_in_kernel": 1,
-  "conv_out_kernel": 1,
+  "conv_in_kernel": 3,
+  "conv_out_kernel": 3,
   "cross_attention_dim": 768,
   "cross_attention_norm": null,
   "down_block_types": [
-    "DownBlock2D",
     "CrossAttnDownBlock2D",
-    "CrossAttnDownBlock2D"
+    "CrossAttnDownBlock2D",
+    "CrossAttnDownBlock2D",
+    "DownBlock2D"
   ],
   "downsample_padding": 1,
   "dropout": 0.0,
@@ -36,8 +39,8 @@
   "encoder_hid_dim_type": null,
   "flip_sin_to_cos": true,
   "freq_shift": 0,
-  "in_channels": 128,
-  "layers_per_block": 1,
+  "in_channels": 32,
+  "layers_per_block": 2,
   "mid_block_only_cross_attention": null,
   "mid_block_scale_factor": 1.0,
   "mid_block_type": "UNetMidBlock2DCrossAttn",
@@ -46,7 +49,7 @@
   "num_attention_heads": null,
   "num_class_embeds": null,
   "only_cross_attention": false,
-  "out_channels": 128,
+  "out_channels": 32,
   "projection_class_embeddings_input_dim": null,
   "resnet_out_scale_factor": 1.0,
   "resnet_skip_time_act": false,
@@ -59,14 +62,15 @@
   "time_embedding_type": "positional",
   "timestep_post_act": null,
   "transformer_layers_per_block": [
-    0,
-    6,
-    6,
-    0
+    1,
+    3,
+    3,
+    3
   ],
   "up_block_types": [
     "UpBlock2D",
     "CrossAttnUpBlock2D",
+    "CrossAttnUpBlock2D",
     "CrossAttnUpBlock2D"
   ],
   "upcast_attention": false,

diffusion_pytorch_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e9925f4a6f34ac7c33c84a4f603469a938abf8e68f24c51fd7e7227248b4d98a
-size 5097769176
+oid sha256:de432df23d19c07ce495bda699a8ba9547c182af1715ee796149287596010497
+size 5935560296