First model version

ema_unet/config.json

@@ -1,61 +0,0 @@
-{
-  "_class_name": "UNet2DConditionModel",
-  "_diffusers_version": "0.16.1",
-  "_name_or_path": "/workspace/stable-diffusion-webui/models/dreambooth/test/working",
-  "act_fn": "silu",
-  "addition_embed_type": null,
-  "addition_embed_type_num_heads": 64,
-  "attention_head_dim": 8,
-  "block_out_channels": [
-    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": 768,
-  "cross_attention_norm": null,
-  "down_block_types": [
-    "CrossAttnDownBlock2D",
-    "CrossAttnDownBlock2D",
-    "CrossAttnDownBlock2D",
-    "DownBlock2D"
-  ],
-  "downsample_padding": 1,
-  "dual_cross_attention": false,
-  "encoder_hid_dim": 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_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": 96,
-  "time_cond_proj_dim": null,
-  "time_embedding_act_fn": null,
-  "time_embedding_dim": null,
-  "time_embedding_type": "positional",
-  "timestep_post_act": null,
-  "up_block_types": [
-    "UpBlock2D",
-    "CrossAttnUpBlock2D",
-    "CrossAttnUpBlock2D",
-    "CrossAttnUpBlock2D"
-  ],
-  "upcast_attention": false,
-  "use_linear_projection": false
-}

ema_unet/diffusion_pytorch_model.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:dc827caae77ad16410c1d5d4d378a25cf889409be4996ed32b1654b43e050a07
-size 1719125992

model_index.json

@@ -1,33 +1,33 @@
 {
-  "_class_name": "StableDiffusionPipeline",
-  "_diffusers_version": "0.16.1",
-  "feature_extractor": [
-    null,
-    null
-  ],
-  "requires_safety_checker": null,
-  "safety_checker": [
-    null,
-    null
-  ],
-  "scheduler": [
-    "diffusers",
-    "DEISMultistepScheduler"
-  ],
-  "text_encoder": [
-    "transformers",
-    "CLIPTextModel"
-  ],
-  "tokenizer": [
-    "transformers",
-    "CLIPTokenizer"
-  ],
-  "unet": [
-    "diffusers",
-    "UNet2DConditionModel"
-  ],
-  "vae": [
-    "diffusers",
-    "AutoencoderKL"
-  ]
-}
+    "_class_name": "StableDiffusionPipeline",
+    "_diffusers_version": "0.16.1",
+    "feature_extractor": [
+        null,
+        null
+    ],
+    "requires_safety_checker": null,
+    "safety_checker": [
+        null,
+        null
+    ],
+    "scheduler": [
+        "diffusers",
+        "DEISMultistepScheduler"
+    ],
+    "text_encoder": [
+        "transformers",
+        "CLIPTextModel"
+    ],
+    "tokenizer": [
+        "transformers",
+        "CLIPTokenizer"
+    ],
+    "unet": [
+        "diffusers",
+        "UNet2DConditionModel"
+    ],
+    "vae": [
+        "diffusers",
+        "AutoencoderKL"
+    ]
+}

text_encoder/config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "/workspace/stable-diffusion-webui/models/dreambooth/test/working",
+  "_name_or_path": "openai/clip-vit-large-patch14",
   "architectures": [
     "CLIPTextModel"
   ],

text_encoder/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4319e140d9462670beb1281c7b04809d411aa155109b93c88655f2da6a5e8d3c
+oid sha256:c4177831acff528ef37a27adfccf378830cdf4a5429905c80ba8fb1dec4d0b61
 size 492265880

unet/config.json

@@ -1,7 +1,6 @@
 {
   "_class_name": "UNet2DConditionModel",
   "_diffusers_version": "0.16.1",
-  "_name_or_path": "/workspace/stable-diffusion-webui/models/dreambooth/test/working",
   "act_fn": "silu",
   "addition_embed_type": null,
   "addition_embed_type_num_heads": 64,
@@ -44,7 +43,7 @@
   "resnet_out_scale_factor": 1.0,
   "resnet_skip_time_act": false,
   "resnet_time_scale_shift": "default",
-  "sample_size": 96,
+  "sample_size": 64,
   "time_cond_proj_dim": null,
   "time_embedding_act_fn": null,
   "time_embedding_dim": null,

unet/diffusion_pytorch_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49165cecd6fa1a88870c686748563aaa25c99adc06aae89d90487fbd598a3a1a
+oid sha256:6348f9bc7fafde33208c9f1f63b0fc9a04d8e635e18cbcc0ba78888b8069d85b
 size 3438167536

vae/config.json

@@ -1,7 +1,6 @@
 {
   "_class_name": "AutoencoderKL",
   "_diffusers_version": "0.16.1",
-  "_name_or_path": "/workspace/stable-diffusion-webui/models/dreambooth/test/working",
   "act_fn": "silu",
   "block_out_channels": [
     128,
@@ -20,7 +19,7 @@
   "layers_per_block": 2,
   "norm_num_groups": 32,
   "out_channels": 3,
-  "sample_size": 768,
+  "sample_size": 512,
   "scaling_factor": 0.18215,
   "up_block_types": [
     "UpDecoderBlock2D",

vae/diffusion_pytorch_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:794220001bb42c5e3a9ea21062abdc9772f3a1050a326ce7a88eba920f0736a4
-size 167335598
+oid sha256:9cef71588194e1fdeaf373c5c1268b97a11d00699e61e17c658283c5889a6ab6
+size 334643276