Upload with huggingface_hub

logs/dreambooth/1681476308.1182032/events.out.tfevents.1681476308.s-iriscope-dreambooth-training-c7fc8-69459f4fbf-5cn5c.1.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17b434a58b58155ab5ceb9defa178db7e8405d90f458792bb31e4e055edfd58d
+size 2476

logs/dreambooth/events.out.tfevents.1681476308.s-iriscope-dreambooth-training-c7fc8-69459f4fbf-5cn5c.1.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4055bf852e91d8e742a270446efcb70c572096451a2ea6d84fb6bf7f9cbaf98f
+size 957434

model_index.json

@@ -1,6 +1,6 @@
 {
   "_class_name": "StableDiffusionPipeline",
-  "_diffusers_version": "0.9.0.dev0",
+  "_diffusers_version": "0.6.0",
   "feature_extractor": [
     "transformers",
     "CLIPFeatureExtractor"

safety_checker/config.json

@@ -1,6 +1,5 @@
 {
-  "_commit_hash": "4bb648a606ef040e7685bde262611766a5fdd67b",
-  "_name_or_path": "CompVis/stable-diffusion-safety-checker",
+  "_name_or_path": "./safety_module",
   "architectures": [
     "StableDiffusionSafetyChecker"
   ],
@@ -69,7 +68,6 @@
     "sep_token_id": null,
     "task_specific_params": null,
     "temperature": 1.0,
-    "tf_legacy_loss": false,
     "tie_encoder_decoder": false,
     "tie_word_embeddings": true,
     "tokenizer_class": null,
@@ -77,7 +75,7 @@
     "top_p": 1.0,
     "torch_dtype": null,
     "torchscript": false,
-    "transformers_version": "4.22.0.dev0",
+    "transformers_version": "4.21.0.dev0",
     "typical_p": 1.0,
     "use_bfloat16": false,
     "vocab_size": 49408
@@ -135,7 +133,6 @@
     "num_attention_heads": 16,
     "num_beam_groups": 1,
     "num_beams": 1,
-    "num_channels": 3,
     "num_hidden_layers": 24,
     "num_return_sequences": 1,
     "output_attentions": false,
@@ -153,7 +150,6 @@
     "sep_token_id": null,
     "task_specific_params": null,
     "temperature": 1.0,
-    "tf_legacy_loss": false,
     "tie_encoder_decoder": false,
     "tie_word_embeddings": true,
     "tokenizer_class": null,
@@ -161,7 +157,7 @@
     "top_p": 1.0,
     "torch_dtype": null,
     "torchscript": false,
-    "transformers_version": "4.22.0.dev0",
+    "transformers_version": "4.21.0.dev0",
     "typical_p": 1.0,
     "use_bfloat16": false
   },

scheduler/scheduler_config.json

@@ -1,10 +1,9 @@
 {
-  "_class_name": "DDIMScheduler",
-  "_diffusers_version": "0.9.0.dev0",
+  "_class_name": "PNDMScheduler",
+  "_diffusers_version": "0.11.1",
   "beta_end": 0.012,
   "beta_schedule": "scaled_linear",
   "beta_start": 0.00085,
-  "clip_sample": false,
   "num_train_timesteps": 1000,
   "prediction_type": "epsilon",
   "set_alpha_to_one": false,

text_encoder/config.json

@@ -1,4 +1,5 @@
 {
+  "_name_or_path": "/home/user/.cache/huggingface/hub/models--multimodalart--sd-fine-tunable/snapshots/9dabd4dbbdd4c72e2ffbc8fb4e28debef0254949",
   "architectures": [
     "CLIPTextModel"
   ],
@@ -6,19 +7,19 @@
   "bos_token_id": 0,
   "dropout": 0.0,
   "eos_token_id": 2,
-  "hidden_act": "gelu",
-  "hidden_size": 1024,
+  "hidden_act": "quick_gelu",
+  "hidden_size": 768,
   "initializer_factor": 1.0,
   "initializer_range": 0.02,
-  "intermediate_size": 4096,
+  "intermediate_size": 3072,
   "layer_norm_eps": 1e-05,
   "max_position_embeddings": 77,
   "model_type": "clip_text_model",
-  "num_attention_heads": 16,
-  "num_hidden_layers": 23,
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
   "pad_token_id": 1,
-  "projection_dim": 512,
+  "projection_dim": 768,
   "torch_dtype": "float32",
-  "transformers_version": "4.21.1",
+  "transformers_version": "4.25.1",
   "vocab_size": 49408
 }

text_encoder/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f0b6635b44bbfc50a61f74468ea18314e7bf3387db059390df4f30811b053849
-size 1361674657
+oid sha256:5f9a1e23fb9cc35a64fd89783b7a0bc89a9f399dcd05a1f12a7d5cc74738e5b9
+size 492308087

tokenizer/special_tokens_map.json

@@ -13,7 +13,7 @@
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": "!",
+  "pad_token": "<|endoftext|>",
   "unk_token": {
     "content": "<|endoftext|>",
     "lstrip": false,

tokenizer/tokenizer_config.json

@@ -19,7 +19,7 @@
   },
   "errors": "replace",
   "model_max_length": 77,
-  "name_or_path": "stabilityai/stable-diffusion-2-1-base",
+  "name_or_path": "/home/user/.cache/huggingface/hub/models--multimodalart--sd-fine-tunable/snapshots/9dabd4dbbdd4c72e2ffbc8fb4e28debef0254949/tokenizer",
   "pad_token": "<|endoftext|>",
   "special_tokens_map_file": "./special_tokens_map.json",
   "tokenizer_class": "CLIPTokenizer",

unet/config.json

@@ -1,13 +1,9 @@
 {
   "_class_name": "UNet2DConditionModel",
-  "_diffusers_version": "0.9.0.dev0",
+  "_diffusers_version": "0.11.1",
+  "_name_or_path": "/home/user/.cache/huggingface/hub/models--multimodalart--sd-fine-tunable/snapshots/9dabd4dbbdd4c72e2ffbc8fb4e28debef0254949",
   "act_fn": "silu",
-  "attention_head_dim": [
-    5,
-    10,
-    20,
-    20
-  ],
+  "attention_head_dim": 8,
   "block_out_channels": [
     320,
     640,
@@ -15,7 +11,8 @@
     1280
   ],
   "center_input_sample": false,
-  "cross_attention_dim": 1024,
+  "class_embed_type": null,
+  "cross_attention_dim": 768,
   "down_block_types": [
     "CrossAttnDownBlock2D",
     "CrossAttnDownBlock2D",
@@ -29,17 +26,20 @@
   "in_channels": 4,
   "layers_per_block": 2,
   "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": 32,
+  "resnet_time_scale_shift": "default",
+  "sample_size": 64,
   "up_block_types": [
     "UpBlock2D",
     "CrossAttnUpBlock2D",
     "CrossAttnUpBlock2D",
     "CrossAttnUpBlock2D"
   ],
+  "upcast_attention": false,
   "use_linear_projection": false
 }

unet/diffusion_pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8fa89c9915435c4ca57fa131cd965923eb856c5f2d9b2f4d0b30009006a3dbe7
-size 3463925413
+oid sha256:57b51f2826055124fb4bbc709eda825e77d6fed2748eeb65954c506dd818f56b
+size 3438364325

vae/config.json

@@ -1,6 +1,7 @@
 {
   "_class_name": "AutoencoderKL",
-  "_diffusers_version": "0.9.0.dev0",
+  "_diffusers_version": "0.11.1",
+  "_name_or_path": "/home/user/.cache/huggingface/hub/models--multimodalart--sd-fine-tunable/snapshots/9dabd4dbbdd4c72e2ffbc8fb4e28debef0254949/vae",
   "act_fn": "silu",
   "block_out_channels": [
     128,
@@ -19,7 +20,7 @@
   "layers_per_block": 2,
   "norm_num_groups": 32,
   "out_channels": 3,
-  "sample_size": 256,
+  "sample_size": 512,
   "up_block_types": [
     "UpDecoderBlock2D",
     "UpDecoderBlock2D",