thanks to TencentARC ❤

feature_extractor/preprocessor_config.json

@@ -0,0 +1,28 @@
+{
+  "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": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_processor_type": "CLIPImageProcessor",
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "shortest_edge": 224
+  }
+}

model_index.json

@@ -0,0 +1,34 @@
+{
+  "_class_name": "StableDiffusionPipeline",
+  "_diffusers_version": "0.19.3",
+  "_name_or_path": "experiments/pretrained_models/anything-v4.0",
+  "feature_extractor": [
+    "transformers",
+    "CLIPImageProcessor"
+  ],
+  "requires_safety_checker": false,
+  "safety_checker": [
+    null,
+    null
+  ],
+  "scheduler": [
+    "diffusers",
+    "DPMSolverMultistepScheduler"
+  ],
+  "text_encoder": [
+    "transformers",
+    "CLIPTextModel"
+  ],
+  "tokenizer": [
+    "transformers",
+    "CLIPTokenizer"
+  ],
+  "unet": [
+    "diffusers",
+    "UNet2DConditionModel"
+  ],
+  "vae": [
+    "diffusers",
+    "AutoencoderKL"
+  ]
+}

new_concept_cfg.json

@@ -0,0 +1 @@
+{"<hina1>": {"concept_token_ids": [49408, 49409, 49410, 49411, 49412, 49413, 49414, 49415, 49416, 49417, 49418, 49419, 49420, 49421, 49422, 49423], "concept_token_names": ["<new0>", "<new1>", "<new2>", "<new3>", "<new4>", "<new5>", "<new6>", "<new7>", "<new8>", "<new9>", "<new10>", "<new11>", "<new12>", "<new13>", "<new14>", "<new15>"]}, "<hina2>": {"concept_token_ids": [49424, 49425, 49426, 49427, 49428, 49429, 49430, 49431, 49432, 49433, 49434, 49435, 49436, 49437, 49438, 49439], "concept_token_names": ["<new16>", "<new17>", "<new18>", "<new19>", "<new20>", "<new21>", "<new22>", "<new23>", "<new24>", "<new25>", "<new26>", "<new27>", "<new28>", "<new29>", "<new30>", "<new31>"]}, "<kaori1>": {"concept_token_ids": [49440, 49441, 49442, 49443, 49444, 49445, 49446, 49447, 49448, 49449, 49450, 49451, 49452, 49453, 49454, 49455], "concept_token_names": ["<new32>", "<new33>", "<new34>", "<new35>", "<new36>", "<new37>", "<new38>", "<new39>", "<new40>", "<new41>", "<new42>", "<new43>", "<new44>", "<new45>", "<new46>", "<new47>"]}, "<kaori2>": {"concept_token_ids": [49456, 49457, 49458, 49459, 49460, 49461, 49462, 49463, 49464, 49465, 49466, 49467, 49468, 49469, 49470, 49471], "concept_token_names": ["<new48>", "<new49>", "<new50>", "<new51>", "<new52>", "<new53>", "<new54>", "<new55>", "<new56>", "<new57>", "<new58>", "<new59>", "<new60>", "<new61>", "<new62>", "<new63>"]}, "<tezuka1>": {"concept_token_ids": [49472, 49473, 49474, 49475, 49476, 49477, 49478, 49479, 49480, 49481, 49482, 49483, 49484, 49485, 49486, 49487], "concept_token_names": ["<new64>", "<new65>", "<new66>", "<new67>", "<new68>", "<new69>", "<new70>", "<new71>", "<new72>", "<new73>", "<new74>", "<new75>", "<new76>", "<new77>", "<new78>", "<new79>"]}, "<tezuka2>": {"concept_token_ids": [49488, 49489, 49490, 49491, 49492, 49493, 49494, 49495, 49496, 49497, 49498, 49499, 49500, 49501, 49502, 49503], "concept_token_names": ["<new80>", "<new81>", "<new82>", "<new83>", "<new84>", "<new85>", "<new86>", "<new87>", "<new88>", "<new89>", "<new90>", "<new91>", "<new92>", "<new93>", "<new94>", "<new95>"]}}

scheduler/scheduler_config.json

@@ -0,0 +1,25 @@
+{
+  "_class_name": "DPMSolverMultistepScheduler",
+  "_diffusers_version": "0.19.3",
+  "algorithm_type": "dpmsolver++",
+  "beta_end": 0.012,
+  "beta_schedule": "scaled_linear",
+  "beta_start": 0.00085,
+  "clip_sample": false,
+  "dynamic_thresholding_ratio": 0.995,
+  "lambda_min_clipped": -Infinity,
+  "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": "midpoint",
+  "steps_offset": 1,
+  "thresholding": false,
+  "timestep_spacing": "linspace",
+  "trained_betas": null,
+  "use_karras_sigmas": false,
+  "variance_type": null
+}

text_encoder/config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "experiments/pretrained_models/anything-v4.0/text_encoder",
+  "architectures": [
+    "CLIPTextModel"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "dropout": 0.0,
+  "eos_token_id": 2,
+  "hidden_act": "quick_gelu",
+  "hidden_size": 768,
+  "initializer_factor": 1.0,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 77,
+  "model_type": "clip_text_model",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "projection_dim": 768,
+  "torch_dtype": "float16",
+  "transformers_version": "4.25.1",
+  "vocab_size": 49504
+}

text_encoder/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3739f68350fa9e5421045b38733f1e3146bec0cfd980756dc3e4174304cd54e
+size 246334519

tokenizer/added_tokens.json

@@ -0,0 +1,98 @@
+{
+  "<new0>": 49408,
+  "<new10>": 49418,
+  "<new11>": 49419,
+  "<new12>": 49420,
+  "<new13>": 49421,
+  "<new14>": 49422,
+  "<new15>": 49423,
+  "<new16>": 49424,
+  "<new17>": 49425,
+  "<new18>": 49426,
+  "<new19>": 49427,
+  "<new1>": 49409,
+  "<new20>": 49428,
+  "<new21>": 49429,
+  "<new22>": 49430,
+  "<new23>": 49431,
+  "<new24>": 49432,
+  "<new25>": 49433,
+  "<new26>": 49434,
+  "<new27>": 49435,
+  "<new28>": 49436,
+  "<new29>": 49437,
+  "<new2>": 49410,
+  "<new30>": 49438,
+  "<new31>": 49439,
+  "<new32>": 49440,
+  "<new33>": 49441,
+  "<new34>": 49442,
+  "<new35>": 49443,
+  "<new36>": 49444,
+  "<new37>": 49445,
+  "<new38>": 49446,
+  "<new39>": 49447,
+  "<new3>": 49411,
+  "<new40>": 49448,
+  "<new41>": 49449,
+  "<new42>": 49450,
+  "<new43>": 49451,
+  "<new44>": 49452,
+  "<new45>": 49453,
+  "<new46>": 49454,
+  "<new47>": 49455,
+  "<new48>": 49456,
+  "<new49>": 49457,
+  "<new4>": 49412,
+  "<new50>": 49458,
+  "<new51>": 49459,
+  "<new52>": 49460,
+  "<new53>": 49461,
+  "<new54>": 49462,
+  "<new55>": 49463,
+  "<new56>": 49464,
+  "<new57>": 49465,
+  "<new58>": 49466,
+  "<new59>": 49467,
+  "<new5>": 49413,
+  "<new60>": 49468,
+  "<new61>": 49469,
+  "<new62>": 49470,
+  "<new63>": 49471,
+  "<new64>": 49472,
+  "<new65>": 49473,
+  "<new66>": 49474,
+  "<new67>": 49475,
+  "<new68>": 49476,
+  "<new69>": 49477,
+  "<new6>": 49414,
+  "<new70>": 49478,
+  "<new71>": 49479,
+  "<new72>": 49480,
+  "<new73>": 49481,
+  "<new74>": 49482,
+  "<new75>": 49483,
+  "<new76>": 49484,
+  "<new77>": 49485,
+  "<new78>": 49486,
+  "<new79>": 49487,
+  "<new7>": 49415,
+  "<new80>": 49488,
+  "<new81>": 49489,
+  "<new82>": 49490,
+  "<new83>": 49491,
+  "<new84>": 49492,
+  "<new85>": 49493,
+  "<new86>": 49494,
+  "<new87>": 49495,
+  "<new88>": 49496,
+  "<new89>": 49497,
+  "<new8>": 49416,
+  "<new90>": 49498,
+  "<new91>": 49499,
+  "<new92>": 49500,
+  "<new93>": 49501,
+  "<new94>": 49502,
+  "<new95>": 49503,
+  "<new9>": 49417
+}

tokenizer/special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<|startoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|endoftext|>",
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer/tokenizer_config.json

@@ -0,0 +1,34 @@
+{
+  "add_prefix_space": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<|startoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "do_lower_case": true,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "errors": "replace",
+  "model_max_length": 77,
+  "name_or_path": "experiments/pretrained_models/anything-v4.0/tokenizer",
+  "pad_token": "<|endoftext|>",
+  "special_tokens_map_file": "./special_tokens_map.json",
+  "tokenizer_class": "CLIPTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

unet/config.json

@@ -0,0 +1,65 @@
+{
+  "_class_name": "UNet2DConditionModel",
+  "_diffusers_version": "0.19.3",
+  "_name_or_path": "experiments/pretrained_models/anything-v4.0/unet",
+  "act_fn": "silu",
+  "addition_embed_type": null,
+  "addition_embed_type_num_heads": 64,
+  "addition_time_embed_dim": null,
+  "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,
+  "encoder_hid_dim_type": 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_attention_heads": null,
+  "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": 64,
+  "time_cond_proj_dim": null,
+  "time_embedding_act_fn": null,
+  "time_embedding_dim": null,
+  "time_embedding_type": "positional",
+  "timestep_post_act": null,
+  "transformer_layers_per_block": 1,
+  "up_block_types": [
+    "UpBlock2D",
+    "CrossAttnUpBlock2D",
+    "CrossAttnUpBlock2D",
+    "CrossAttnUpBlock2D"
+  ],
+  "upcast_attention": false,
+  "use_linear_projection": false
+}

unet/diffusion_pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43625b82a0fec7006e96260939b7c4418edb070a8bf85502012d19e8fc185008
+size 1719322405

vae/config.json

@@ -0,0 +1,32 @@
+{
+  "_class_name": "AutoencoderKL",
+  "_diffusers_version": "0.19.3",
+  "_name_or_path": "experiments/pretrained_models/anything-v4.0/vae",
+  "act_fn": "silu",
+  "block_out_channels": [
+    128,
+    256,
+    512,
+    512
+  ],
+  "down_block_types": [
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D"
+  ],
+  "force_upcast": true,
+  "in_channels": 3,
+  "latent_channels": 4,
+  "layers_per_block": 2,
+  "norm_num_groups": 32,
+  "out_channels": 3,
+  "sample_size": 512,
+  "scaling_factor": 0.18215,
+  "up_block_types": [
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D"
+  ]
+}

vae/diffusion_pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97f7d79fc422ffd14a4addce422b50a74ef86679367df658884c08a16392f867
+size 167403217