Upgrade to SD2

feature_extractor/preprocessor_config.json

@@ -1,20 +0,0 @@
-{
-  "crop_size": 224,
-  "do_center_crop": true,
-  "do_convert_rgb": true,
-  "do_normalize": true,
-  "do_resize": true,
-  "feature_extractor_type": "CLIPFeatureExtractor",
-  "image_mean": [
-    0.48145466,
-    0.4578275,
-    0.40821073
-  ],
-  "image_std": [
-    0.26862954,
-    0.26130258,
-    0.27577711
-  ],
-  "resample": 3,
-  "size": 224
-}

logs/dreambooth/1669598855.001458/events.out.tfevents.1669598855.instance-4.5954.1

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:24cf85eb46a8790c3a8364f90cde2c364ec5c73c1e1f0ae96225c112f5d81fa3
-size 1923

logs/dreambooth/1669598855.018298/hparams.yml

@@ -1,37 +0,0 @@
-adam_beta1: 0.9
-adam_beta2: 0.999
-adam_epsilon: 1.0e-08
-adam_weight_decay: 0.01
-center_crop: false
-class_data_dir: null
-class_prompt: null
-gradient_accumulation_steps: 1
-gradient_checkpointing: true
-hub_model_id: null
-hub_token: null
-instance_data_dir: /home/diffusers/examples/dreambooth/datasets/3-lowpoly/living_room/class
-instance_prompt: a photo of lowpoly_living_room
-learning_rate: 2.0e-06
-local_rank: -1
-logging_dir: logs
-lr_scheduler: constant
-lr_warmup_steps: 0
-max_grad_norm: 1.0
-max_train_steps: 2000
-mixed_precision: null
-num_class_images: 100
-num_train_epochs: 223
-output_dir: /home/diffusers/examples/dreambooth/datasets/3-lowpoly/living_room/model
-pretrained_model_name_or_path: runwayml/stable-diffusion-v1-5
-prior_loss_weight: 1.0
-push_to_hub: false
-resolution: 512
-revision: null
-sample_batch_size: 4
-scale_lr: false
-seed: null
-tokenizer_name: null
-train_batch_size: 1
-train_text_encoder: true
-use_8bit_adam: true
-with_prior_preservation: false

logs/dreambooth/events.out.tfevents.1669598854.instance-4.5954.0

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:a4b465676c57c03d4c6bbc45ea82ee5a840c95e7b8acf588adeab50e29f7b1d6
-size 167786

model_index.json

@@ -2,13 +2,13 @@
   "_class_name": "StableDiffusionPipeline",
   "_diffusers_version": "0.9.0",
   "feature_extractor": [
-    "transformers",
-    "CLIPFeatureExtractor"
+    null,
+    null
   ],
-  "requires_safety_checker": true,
+  "requires_safety_checker": false,
   "safety_checker": [
-    "stable_diffusion",
-    "StableDiffusionSafetyChecker"
+    null,
+    null
   ],
   "scheduler": [
     "diffusers",

safety_checker/config.json

@@ -1,179 +0,0 @@
-{
-  "_commit_hash": "63534535d4730d5976c5c647a7f2adaea1102f5b",
-  "_name_or_path": "/root/.cache/huggingface/diffusers/models--runwayml--stable-diffusion-v1-5/snapshots/63534535d4730d5976c5c647a7f2adaea1102f5b/safety_checker",
-  "architectures": [
-    "StableDiffusionSafetyChecker"
-  ],
-  "initializer_factor": 1.0,
-  "logit_scale_init_value": 2.6592,
-  "model_type": "clip",
-  "projection_dim": 768,
-  "text_config": {
-    "_name_or_path": "",
-    "add_cross_attention": false,
-    "architectures": null,
-    "attention_dropout": 0.0,
-    "bad_words_ids": null,
-    "begin_suppress_tokens": null,
-    "bos_token_id": 0,
-    "chunk_size_feed_forward": 0,
-    "cross_attention_hidden_size": null,
-    "decoder_start_token_id": null,
-    "diversity_penalty": 0.0,
-    "do_sample": false,
-    "dropout": 0.0,
-    "early_stopping": false,
-    "encoder_no_repeat_ngram_size": 0,
-    "eos_token_id": 2,
-    "exponential_decay_length_penalty": null,
-    "finetuning_task": null,
-    "forced_bos_token_id": null,
-    "forced_eos_token_id": null,
-    "hidden_act": "quick_gelu",
-    "hidden_size": 768,
-    "id2label": {
-      "0": "LABEL_0",
-      "1": "LABEL_1"
-    },
-    "initializer_factor": 1.0,
-    "initializer_range": 0.02,
-    "intermediate_size": 3072,
-    "is_decoder": false,
-    "is_encoder_decoder": false,
-    "label2id": {
-      "LABEL_0": 0,
-      "LABEL_1": 1
-    },
-    "layer_norm_eps": 1e-05,
-    "length_penalty": 1.0,
-    "max_length": 20,
-    "max_position_embeddings": 77,
-    "min_length": 0,
-    "model_type": "clip_text_model",
-    "no_repeat_ngram_size": 0,
-    "num_attention_heads": 12,
-    "num_beam_groups": 1,
-    "num_beams": 1,
-    "num_hidden_layers": 12,
-    "num_return_sequences": 1,
-    "output_attentions": false,
-    "output_hidden_states": false,
-    "output_scores": false,
-    "pad_token_id": 1,
-    "prefix": null,
-    "problem_type": null,
-    "pruned_heads": {},
-    "remove_invalid_values": false,
-    "repetition_penalty": 1.0,
-    "return_dict": true,
-    "return_dict_in_generate": false,
-    "sep_token_id": null,
-    "suppress_tokens": null,
-    "task_specific_params": null,
-    "temperature": 1.0,
-    "tf_legacy_loss": false,
-    "tie_encoder_decoder": false,
-    "tie_word_embeddings": true,
-    "tokenizer_class": null,
-    "top_k": 50,
-    "top_p": 1.0,
-    "torch_dtype": null,
-    "torchscript": false,
-    "transformers_version": "4.24.0",
-    "typical_p": 1.0,
-    "use_bfloat16": false,
-    "vocab_size": 49408
-  },
-  "text_config_dict": {
-    "hidden_size": 768,
-    "intermediate_size": 3072,
-    "num_attention_heads": 12,
-    "num_hidden_layers": 12
-  },
-  "torch_dtype": "float32",
-  "transformers_version": null,
-  "vision_config": {
-    "_name_or_path": "",
-    "add_cross_attention": false,
-    "architectures": null,
-    "attention_dropout": 0.0,
-    "bad_words_ids": null,
-    "begin_suppress_tokens": null,
-    "bos_token_id": null,
-    "chunk_size_feed_forward": 0,
-    "cross_attention_hidden_size": null,
-    "decoder_start_token_id": null,
-    "diversity_penalty": 0.0,
-    "do_sample": false,
-    "dropout": 0.0,
-    "early_stopping": false,
-    "encoder_no_repeat_ngram_size": 0,
-    "eos_token_id": null,
-    "exponential_decay_length_penalty": null,
-    "finetuning_task": null,
-    "forced_bos_token_id": null,
-    "forced_eos_token_id": null,
-    "hidden_act": "quick_gelu",
-    "hidden_size": 1024,
-    "id2label": {
-      "0": "LABEL_0",
-      "1": "LABEL_1"
-    },
-    "image_size": 224,
-    "initializer_factor": 1.0,
-    "initializer_range": 0.02,
-    "intermediate_size": 4096,
-    "is_decoder": false,
-    "is_encoder_decoder": false,
-    "label2id": {
-      "LABEL_0": 0,
-      "LABEL_1": 1
-    },
-    "layer_norm_eps": 1e-05,
-    "length_penalty": 1.0,
-    "max_length": 20,
-    "min_length": 0,
-    "model_type": "clip_vision_model",
-    "no_repeat_ngram_size": 0,
-    "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,
-    "output_hidden_states": false,
-    "output_scores": false,
-    "pad_token_id": null,
-    "patch_size": 14,
-    "prefix": null,
-    "problem_type": null,
-    "pruned_heads": {},
-    "remove_invalid_values": false,
-    "repetition_penalty": 1.0,
-    "return_dict": true,
-    "return_dict_in_generate": false,
-    "sep_token_id": null,
-    "suppress_tokens": null,
-    "task_specific_params": null,
-    "temperature": 1.0,
-    "tf_legacy_loss": false,
-    "tie_encoder_decoder": false,
-    "tie_word_embeddings": true,
-    "tokenizer_class": null,
-    "top_k": 50,
-    "top_p": 1.0,
-    "torch_dtype": null,
-    "torchscript": false,
-    "transformers_version": "4.24.0",
-    "typical_p": 1.0,
-    "use_bfloat16": false
-  },
-  "vision_config_dict": {
-    "hidden_size": 1024,
-    "intermediate_size": 4096,
-    "num_attention_heads": 16,
-    "num_hidden_layers": 24,
-    "patch_size": 14
-  }
-}

safety_checker/pytorch_model.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:16d28f2b37109f222cdc33620fdd262102ac32112be0352a7f77e9614b35a394
-size 1216064769

text_encoder/config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "runwayml/stable-diffusion-v1-5",
+  "_name_or_path": "stabilityai/stable-diffusion-2-base",
   "architectures": [
     "CLIPTextModel"
   ],
@@ -7,18 +7,18 @@
   "bos_token_id": 0,
   "dropout": 0.0,
   "eos_token_id": 2,
-  "hidden_act": "quick_gelu",
-  "hidden_size": 768,
+  "hidden_act": "gelu",
+  "hidden_size": 1024,
   "initializer_factor": 1.0,
   "initializer_range": 0.02,
-  "intermediate_size": 3072,
+  "intermediate_size": 4096,
   "layer_norm_eps": 1e-05,
   "max_position_embeddings": 77,
   "model_type": "clip_text_model",
-  "num_attention_heads": 12,
-  "num_hidden_layers": 12,
+  "num_attention_heads": 16,
+  "num_hidden_layers": 23,
   "pad_token_id": 1,
-  "projection_dim": 768,
+  "projection_dim": 512,
   "torch_dtype": "float32",
   "transformers_version": "4.24.0",
   "vocab_size": 49408

text_encoder/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9697d910de3a19d60c2b8ba27a600443177edb43abf3d513f7638b8facf93640
-size 492309793
+oid sha256:5d61d4f33f3c90c3b96c477aaa4f3cb2c767809f18f27d29e52c471275e59bfa
+size 1361679905

tokenizer/special_tokens_map.json

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

tokenizer/tokenizer_config.json

@@ -19,7 +19,7 @@
   },
   "errors": "replace",
   "model_max_length": 77,
-  "name_or_path": "/root/.cache/huggingface/diffusers/models--runwayml--stable-diffusion-v1-5/snapshots/63534535d4730d5976c5c647a7f2adaea1102f5b/tokenizer",
+  "name_or_path": "/root/.cache/huggingface/diffusers/models--stabilityai--stable-diffusion-2-base/snapshots/abda38f7c548237cae935d6182ae56acd5a02ed8/tokenizer",
   "pad_token": "<|endoftext|>",
   "special_tokens_map_file": "./special_tokens_map.json",
   "tokenizer_class": "CLIPTokenizer",

unet/config.json

@@ -1,9 +1,14 @@
 {
   "_class_name": "UNet2DConditionModel",
   "_diffusers_version": "0.9.0",
-  "_name_or_path": "runwayml/stable-diffusion-v1-5",
+  "_name_or_path": "stabilityai/stable-diffusion-2-base",
   "act_fn": "silu",
-  "attention_head_dim": 8,
+  "attention_head_dim": [
+    5,
+    10,
+    20,
+    20
+  ],
   "block_out_channels": [
     320,
     640,
@@ -11,7 +16,7 @@
     1280
   ],
   "center_input_sample": false,
-  "cross_attention_dim": 768,
+  "cross_attention_dim": 1024,
   "down_block_types": [
     "CrossAttnDownBlock2D",
     "CrossAttnDownBlock2D",
@@ -37,5 +42,5 @@
     "CrossAttnUpBlock2D",
     "CrossAttnUpBlock2D"
   ],
-  "use_linear_projection": false
+  "use_linear_projection": true
 }

unet/diffusion_pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c91d52946c3b2ea6110748fdb02f076768f7fce419377cab010b99469dc5f38
-size 3438375973
+oid sha256:bb1c00b93b60561e392b4bca9af675ed296ef86a741693d5f9e812ecf78cccf9
+size 3463934693

vae/config.json

@@ -1,7 +1,7 @@
 {
   "_class_name": "AutoencoderKL",
   "_diffusers_version": "0.9.0",
-  "_name_or_path": "/root/.cache/huggingface/diffusers/models--runwayml--stable-diffusion-v1-5/snapshots/63534535d4730d5976c5c647a7f2adaea1102f5b/vae",
+  "_name_or_path": "/root/.cache/huggingface/diffusers/models--stabilityai--stable-diffusion-2-base/snapshots/abda38f7c548237cae935d6182ae56acd5a02ed8/vae",
   "act_fn": "silu",
   "block_out_channels": [
     128,

vae/diffusion_pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:af27ea858349760ebe3311953e0bfe8d6fd257dc9537ae0b2b938c262132a2c6
+oid sha256:36bb8e1b54aba3a0914eb35fba13dcb107e9f18d379d1df2158732cd4bf56a94
 size 334711857