add wd 1.4 anime model

feature_extractor/preprocessor_config.json

@@ -1,8 +1,12 @@
 {
-  "crop_size": 224,
+  "crop_size": {
+    "height": 224,
+    "width": 224
+  },
   "do_center_crop": true,
   "do_convert_rgb": true,
   "do_normalize": true,
+  "do_rescale": true,
   "do_resize": true,
   "feature_extractor_type": "CLIPFeatureExtractor",
   "image_mean": [
@@ -10,11 +14,15 @@
     0.4578275,
     0.40821073
   ],
+  "image_processor_type": "CLIPImageProcessor",
   "image_std": [
     0.26862954,
     0.26130258,
     0.27577711
   ],
   "resample": 3,
-  "size": 224
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "shortest_edge": 224
+  }
 }

model_index.json

@@ -1,17 +1,18 @@
 {
   "_class_name": "StableDiffusionPipeline",
-  "_diffusers_version": "0.4.1",
+  "_diffusers_version": "0.10.2",
   "feature_extractor": [
     "transformers",
-    "CLIPFeatureExtractor"
+    "CLIPImageProcessor"
   ],
+  "requires_safety_checker": true,
   "safety_checker": [
     "stable_diffusion",
     "StableDiffusionSafetyChecker"
   ],
   "scheduler": [
     "diffusers",
-    "LMSDiscreteScheduler"
+    "PNDMScheduler"
   ],
   "text_encoder": [
     "transformers",

safety_checker/config.json

@@ -1,5 +1,5 @@
 {
-  "_commit_hash": null,
+  "_commit_hash": "cb41f3a270d63d454d385fc2e4f571c487c253c5",
   "_name_or_path": "CompVis/stable-diffusion-safety-checker",
   "architectures": [
     "StableDiffusionSafetyChecker"
@@ -14,6 +14,7 @@
     "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,
@@ -61,12 +62,14 @@
     "pad_token_id": 1,
     "prefix": null,
     "problem_type": null,
+    "projection_dim": 512,
     "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,
@@ -77,7 +80,7 @@
     "top_p": 1.0,
     "torch_dtype": null,
     "torchscript": false,
-    "transformers_version": "4.22.2",
+    "transformers_version": "4.25.1",
     "typical_p": 1.0,
     "use_bfloat16": false,
     "vocab_size": 49408
@@ -96,6 +99,7 @@
     "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,
@@ -145,12 +149,14 @@
     "patch_size": 14,
     "prefix": null,
     "problem_type": null,
+    "projection_dim": 512,
     "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,
@@ -161,7 +167,7 @@
     "top_p": 1.0,
     "torch_dtype": null,
     "torchscript": false,
-    "transformers_version": "4.22.2",
+    "transformers_version": "4.25.1",
     "typical_p": 1.0,
     "use_bfloat16": false
   },

safety_checker/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:193490b58ef62739077262e833bf091c66c29488058681ac25cf7df3d8190974
-size 1216061799
+oid sha256:16d28f2b37109f222cdc33620fdd262102ac32112be0352a7f77e9614b35a394
+size 1216064769

scheduler/scheduler_config.json

@@ -1,9 +1,14 @@
 {
-  "_class_name": "LMSDiscreteScheduler",
-  "_diffusers_version": "0.4.1",
+  "_class_name": "PNDMScheduler",
+  "_diffusers_version": "0.10.2",
   "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,
+  "skip_prk_steps": true,
+  "steps_offset": 1,
   "trained_betas": null
 }

text_encoder/config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "openai/clip-vit-large-patch14",
+  "_name_or_path": "/mnt/sd-finetune-data/finetunes/step_57000",
   "architectures": [
     "CLIPTextModel"
   ],
@@ -7,19 +7,19 @@
   "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": "4.22.2",
+  "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 sha256:770a47a9ffdcfda0b05506a7888ed714d06131d60267e6cf52765d61cf59fd67
-size 492305335
+oid sha256:040fc6498aa3cdbb926dc2d01c3d6629521e5f085d901d5e8d8c2b0e0aa2b1ce
+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": "openai/clip-vit-large-patch14",
+  "name_or_path": "/mnt/sd-finetune-data/finetunes/step_57000",
   "pad_token": "<|endoftext|>",
   "special_tokens_map_file": "./special_tokens_map.json",
   "tokenizer_class": "CLIPTokenizer",

unet/config.json

@@ -1,8 +1,14 @@
 {
   "_class_name": "UNet2DConditionModel",
-  "_diffusers_version": "0.4.1",
+  "_diffusers_version": "0.10.2",
+  "_name_or_path": "/mnt/sd-finetune-data/finetunes/step_57000",
   "act_fn": "silu",
-  "attention_head_dim": 8,
+  "attention_head_dim": [
+    5,
+    10,
+    20,
+    20
+  ],
   "block_out_channels": [
     320,
     640,
@@ -10,7 +16,7 @@
     1280
   ],
   "center_input_sample": false,
-  "cross_attention_dim": 768,
+  "cross_attention_dim": 1024,
   "down_block_types": [
     "CrossAttnDownBlock2D",
     "CrossAttnDownBlock2D",
@@ -18,6 +24,7 @@
     "DownBlock2D"
   ],
   "downsample_padding": 1,
+  "dual_cross_attention": false,
   "flip_sin_to_cos": true,
   "freq_shift": 0,
   "in_channels": 4,
@@ -25,12 +32,16 @@
   "mid_block_scale_factor": 1,
   "norm_eps": 1e-05,
   "norm_num_groups": 32,
+  "num_class_embeds": null,
+  "only_cross_attention": false,
   "out_channels": 4,
-  "sample_size": 32,
+  "sample_size": 64,
   "up_block_types": [
     "UpBlock2D",
     "CrossAttnUpBlock2D",
     "CrossAttnUpBlock2D",
     "CrossAttnUpBlock2D"
-  ]
+  ],
+  "upcast_attention": false,
+  "use_linear_projection": true
 }

unet/diffusion_pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f47e5665f0e85155a5f6f58683b04940c6b132023d584396226bf54419a78831
-size 3438354725
+oid sha256:24d2d0a39a4cd06869c91173d507cb153f272a1a328514f70b7ce9b48cab7e2b
+size 3463934693

vae/config.json

@@ -1,6 +1,7 @@
 {
   "_class_name": "AutoencoderKL",
-  "_diffusers_version": "0.4.1",
+  "_diffusers_version": "0.10.2",
+  "_name_or_path": "/mnt/sd-finetune-data/base/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",

vae/diffusion_pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b134cded8eb78b184aefb8805b6b572f36fa77b255c483665dda931fa0130c5
-size 334707217
+oid sha256:3e174991e5609bc5c2b3995e3f223fb2c5f0ae3be307fa9591b351d837a08770
+size 334711857