First model version

ema_unet/config.json

@@ -0,0 +1,61 @@
+{
+  "_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

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

model_index.json

@@ -1,6 +1,6 @@
 {
   "_class_name": "StableDiffusionPipeline",
-  "_diffusers_version": "0.10.2",
+  "_diffusers_version": "0.16.1",
   "feature_extractor": [
     null,
     null
@@ -12,7 +12,7 @@
   ],
   "scheduler": [
     "diffusers",
-    "DDIMScheduler"
+    "DEISMultistepScheduler"
   ],
   "text_encoder": [
     "transformers",

scheduler/scheduler_config.json

@@ -1,14 +1,21 @@
 {
-  "_class_name": "DDIMScheduler",
-  "_diffusers_version": "0.10.2",
+  "_class_name": "DEISMultistepScheduler",
+  "_diffusers_version": "0.16.1",
+  "algorithm_type": "deis",
   "beta_end": 0.012,
   "beta_schedule": "scaled_linear",
   "beta_start": 0.00085,
   "clip_sample": false,
+  "clip_sample_range": 1.0,
+  "dynamic_thresholding_ratio": 0.995,
+  "lower_order_final": true,
   "num_train_timesteps": 1000,
   "prediction_type": "epsilon",
+  "sample_max_value": 1.0,
   "set_alpha_to_one": false,
-  "skip_prk_steps": true,
+  "solver_order": 2,
+  "solver_type": "logrho",
   "steps_offset": 1,
+  "thresholding": false,
   "trained_betas": null
 }

text_encoder/config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "openai/clip-vit-large-patch14",
+  "_name_or_path": "/workspace/stable-diffusion-webui/models/dreambooth/test/working",
   "architectures": [
     "CLIPTextModel"
   ],
@@ -20,6 +20,6 @@
   "pad_token_id": 1,
   "projection_dim": 768,
   "torch_dtype": "float32",
-  "transformers_version": "4.26.0",
+  "transformers_version": "4.29.2",
   "vocab_size": 49408
 }

vae/diffusion_pytorch_model.bin → text_encoder/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:354e94ceb8cebe720c40510b94599b388a8eda407e7694a4db1ed8dc4f678538
-size 167404145
+oid sha256:4319e140d9462670beb1281c7b04809d411aa155109b93c88655f2da6a5e8d3c
+size 492265880

tokenizer/tokenizer_config.json

@@ -8,6 +8,7 @@
     "rstrip": false,
     "single_word": false
   },
+  "clean_up_tokenization_spaces": true,
   "do_lower_case": true,
   "eos_token": {
     "__type": "AddedToken",
@@ -19,9 +20,7 @@
   },
   "errors": "replace",
   "model_max_length": 77,
-  "name_or_path": "runwayml/stable-diffusion-v1-5",
   "pad_token": "<|endoftext|>",
-  "special_tokens_map_file": "./special_tokens_map.json",
   "tokenizer_class": "CLIPTokenizer",
   "unk_token": {
     "__type": "AddedToken",

unet/config.json

@@ -1,7 +1,10 @@
 {
   "_class_name": "UNet2DConditionModel",
-  "_diffusers_version": "0.10.2",
+  "_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,
@@ -10,7 +13,12 @@
     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",
@@ -19,17 +27,29 @@
   ],
   "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,
-  "sample_size": 64,
+  "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",

unet/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49165cecd6fa1a88870c686748563aaa25c99adc06aae89d90487fbd598a3a1a
+size 3438167536

vae/config.json

@@ -1,6 +1,7 @@
 {
   "_class_name": "AutoencoderKL",
-  "_diffusers_version": "0.10.2",
+  "_diffusers_version": "0.16.1",
+  "_name_or_path": "/workspace/stable-diffusion-webui/models/dreambooth/test/working",
   "act_fn": "silu",
   "block_out_channels": [
     128,
@@ -19,7 +20,8 @@
   "layers_per_block": 2,
   "norm_num_groups": 32,
   "out_channels": 3,
-  "sample_size": 256,
+  "sample_size": 768,
+  "scaling_factor": 0.18215,
   "up_block_types": [
     "UpDecoderBlock2D",
     "UpDecoderBlock2D",

vae/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:794220001bb42c5e3a9ea21062abdc9772f3a1050a326ce7a88eba920f0736a4
+size 167335598