Upload KandinskyV22PriorPipeline

image_encoder/config.json

@@ -0,0 +1,23 @@
+{
+  "_name_or_path": "/home/user/.cache/huggingface/hub/models--kandinsky-community--kandinsky-2-2-prior/snapshots/9fc51ad5732afc5d031724219d22e6c42179c5a8/image_encoder",
+  "architectures": [
+    "CLIPVisionModelWithProjection"
+  ],
+  "attention_dropout": 0.0,
+  "dropout": 0.0,
+  "hidden_act": "gelu",
+  "hidden_size": 1664,
+  "image_size": 224,
+  "initializer_factor": 1.0,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "layer_norm_eps": 1e-05,
+  "model_type": "clip_vision_model",
+  "num_attention_heads": 16,
+  "num_channels": 3,
+  "num_hidden_layers": 48,
+  "patch_size": 14,
+  "projection_dim": 1280,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.37.1"
+}

image_encoder/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9323e12b226aae9e11d5f4bc94e32652cd77296ba63b10b4299311d0dc37df18
+size 3689911288

image_processor/preprocessor_config.json

@@ -0,0 +1,27 @@
+{
+  "crop_size": {
+    "height": 224,
+    "width": 224
+  },
+  "do_center_crop": true,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "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 +1,29 @@
+{
+  "_class_name": "KandinskyV22PriorPipeline",
+  "_diffusers_version": "0.25.0",
+  "_name_or_path": "kandinsky-community/kandinsky-2-2-prior",
+  "image_encoder": [
+    "transformers",
+    "CLIPVisionModelWithProjection"
+  ],
+  "image_processor": [
+    "transformers",
+    "CLIPImageProcessor"
+  ],
+  "prior": [
+    "diffusers",
+    "PriorTransformer"
+  ],
+  "scheduler": [
+    "diffusers",
+    "UnCLIPScheduler"
+  ],
+  "text_encoder": [
+    "transformers",
+    "CLIPTextModelWithProjection"
+  ],
+  "tokenizer": [
+    "transformers",
+    "CLIPTokenizer"
+  ]
+}

prior/config.json

@@ -0,0 +1,20 @@
+{
+  "_class_name": "PriorTransformer",
+  "_diffusers_version": "0.25.0",
+  "_name_or_path": "/home/user/.cache/huggingface/hub/models--kandinsky-community--kandinsky-2-2-prior/snapshots/9fc51ad5732afc5d031724219d22e6c42179c5a8/prior",
+  "added_emb_type": "prd",
+  "additional_embeddings": 4,
+  "attention_head_dim": 64,
+  "clip_embed_dim": null,
+  "dropout": 0.0,
+  "embedding_dim": 1280,
+  "embedding_proj_dim": null,
+  "embedding_proj_norm_type": null,
+  "encoder_hid_proj_type": "linear",
+  "norm_in_type": null,
+  "num_attention_heads": 32,
+  "num_embeddings": 77,
+  "num_layers": 20,
+  "time_embed_act_fn": "silu",
+  "time_embed_dim": null
+}

prior/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3adb35328a082320140358484b5c8bcb20444caf2ad034aecf6df2759866bcae
+size 2052489288

scheduler/scheduler_config.json

@@ -0,0 +1,10 @@
+{
+  "_class_name": "UnCLIPScheduler",
+  "_diffusers_version": "0.25.0",
+  "beta_schedule": "squaredcos_cap_v2",
+  "clip_sample": true,
+  "clip_sample_range": 10.0,
+  "num_train_timesteps": 1000,
+  "prediction_type": "sample",
+  "variance_type": "fixed_small_log"
+}

text_encoder/config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "/home/user/.cache/huggingface/hub/models--kandinsky-community--kandinsky-2-2-prior/snapshots/9fc51ad5732afc5d031724219d22e6c42179c5a8/text_encoder",
+  "architectures": [
+    "CLIPTextModelWithProjection"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "dropout": 0.0,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_size": 1280,
+  "initializer_factor": 1.0,
+  "initializer_range": 0.02,
+  "intermediate_size": 5120,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 77,
+  "model_type": "clip_text_model",
+  "num_attention_heads": 20,
+  "num_hidden_layers": 32,
+  "pad_token_id": 1,
+  "projection_dim": 1280,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.37.1",
+  "vocab_size": 49408
+}

text_encoder/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:260e0127aca3c89db813637ae659ebb822cb07af71fedc16cbd980e9518dfdcd
+size 1389382688

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 +1,30 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "49406": {
+      "content": "<|startoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49407": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|startoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "do_lower_case": true,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "model_max_length": 77,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "CLIPTokenizer",
+  "unk_token": "<|endoftext|>"
+}