updated ckpts - ema weights

feature_extractor/preprocessor_config.json

@@ -0,0 +1,20 @@
+{
+  "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
+}

model_index.json

@@ -1,10 +1,11 @@
 {
-  "_class_name": "StableDiffusionUpscalePipeline",
+  "_class_name": "StableDiffusionUpscaleLDM3DPipeline",
   "_diffusers_version": "0.9.0.dev0",
   "low_res_scheduler": [
     "diffusers",
     "DDPMScheduler"
   ],
+
   "max_noise_level": 350,
   "scheduler": [
     "diffusers",

safety_checker/config.json

@@ -0,0 +1,171 @@
+{
+  "_name_or_path": "./safety_module",
+  "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,
+    "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,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "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": "4.21.0.dev0",
+    "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,
+    "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_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,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "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": "4.21.0.dev0",
+    "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
+  }
+}

unet/diffusion_pytorch_model.bin → safety_checker/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd94f081b9077d017ed99d0b96c0b8b5a38742cdcb61302e4472a6f9d98ad6b4
-size 3443497527
+oid sha256:9d6a233ff6fd5ccb9f76fd99618d73369c52dd3d8222376384d0e601911089e8
+size 1215981830

unet/diffusion_pytorch_model_ema.bin → safety_checker/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:063889377720289a5f8b9cdb8c31cdd18b29c2e9b98186ff849e6b54101d4b0e
-size 3443500283
+oid sha256:770a47a9ffdcfda0b05506a7888ed714d06131d60267e6cf52765d61cf59fd67
+size 492305335

unet/.ipynb_checkpoints/config-checkpoint.json

@@ -1,46 +0,0 @@
-{
-  "_class_name": "UNet2DConditionModel",
-  "_diffusers_version": "0.8.0",
-  "_name_or_path": "hf-models/stable-diffusion-x4-upscaler/unet",
-  "act_fn": "silu",
-  "attention_head_dim": 8,
-  "block_out_channels": [
-    256,
-    512,
-    512,
-    1024
-  ],
-  "center_input_sample": false,
-  "cross_attention_dim": 1024,
-  "down_block_types": [
-    "DownBlock2D",
-    "CrossAttnDownBlock2D",
-    "CrossAttnDownBlock2D",
-    "CrossAttnDownBlock2D"
-  ],
-  "downsample_padding": 1,
-  "dual_cross_attention": false,
-  "flip_sin_to_cos": true,
-  "freq_shift": 0,
-  "in_channels": 7,
-  "layers_per_block": 2,
-  "mid_block_scale_factor": 1,
-  "norm_eps": 1e-05,
-  "norm_num_groups": 32,
-  "num_class_embeds": 1000,
-  "only_cross_attention": [
-    true,
-    true,
-    true,
-    false
-  ],
-  "out_channels": 4,
-  "sample_size": 128,
-  "up_block_types": [
-    "CrossAttnUpBlock2D",
-    "CrossAttnUpBlock2D",
-    "CrossAttnUpBlock2D",
-    "UpBlock2D"
-  ],
-  "use_linear_projection": true
-}

unet/config.json

@@ -1,46 +1,37 @@
 {
   "_class_name": "UNet2DConditionModel",
-  "_diffusers_version": "0.9.0.dev0",
-  "_name_or_path": "hf-models/stable-diffusion-x4-upscaler/unet",
+  "_diffusers_version": "0.2.2",
   "act_fn": "silu",
   "attention_head_dim": 8,
   "block_out_channels": [
-    256,
-    512,
-    512,
-    1024
+    320,
+    640,
+    1280,
+    1280
   ],
   "center_input_sample": false,
-  "cross_attention_dim": 1024,
+  "cross_attention_dim": 768,
   "down_block_types": [
-    "DownBlock2D",
     "CrossAttnDownBlock2D",
     "CrossAttnDownBlock2D",
-    "CrossAttnDownBlock2D"
+    "CrossAttnDownBlock2D",
+    "DownBlock2D"
   ],
   "downsample_padding": 1,
-  "dual_cross_attention": false,
   "flip_sin_to_cos": true,
   "freq_shift": 0,
   "in_channels": 8,
+  "num_class_embeds":1000,
   "layers_per_block": 2,
   "mid_block_scale_factor": 1,
   "norm_eps": 1e-05,
   "norm_num_groups": 32,
-  "num_class_embeds": 1000,
-  "only_cross_attention": [
-    true,
-    true,
-    true,
-    false
-  ],
   "out_channels": 4,
-  "sample_size": 128,
+  "sample_size": 64,
   "up_block_types": [
+    "UpBlock2D",
     "CrossAttnUpBlock2D",
     "CrossAttnUpBlock2D",
-    "CrossAttnUpBlock2D",
-    "UpBlock2D"
-  ],
-  "use_linear_projection": true
+    "CrossAttnUpBlock2D"
+  ]
 }

unet/diffusion_pytorch_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:009c228d871942d23a6d0b946d311225bdede48aec47ad61ed61a22c94f5ef78
-size 3443333824
+oid sha256:875f4a72e6ebdb147bb40bdb46524de35ea59303b0a4d4a1fda1d398f4a0c945
+size 3443333744