init

decoder/config.json

@@ -0,0 +1,45 @@
+{
+  "_class_name": "UNet2DConditionModel",
+  "_diffusers_version": "0.12.0.dev0",
+  "_name_or_path": "/home/william_huggingface_co/.cache/huggingface/diffusers/models--kakaobrain--karlo-v1-alpha/snapshots/c8dc0970acf0db0b6b4efb8c47adc22072b4a67d/decoder",
+  "act_fn": "silu",
+  "attention_head_dim": 64,
+  "block_out_channels": [
+    320,
+    640,
+    960,
+    1280
+  ],
+  "center_input_sample": false,
+  "class_embed_type": "identity",
+  "cross_attention_dim": 1536,
+  "down_block_types": [
+    "ResnetDownsampleBlock2D",
+    "SimpleCrossAttnDownBlock2D",
+    "SimpleCrossAttnDownBlock2D",
+    "SimpleCrossAttnDownBlock2D"
+  ],
+  "downsample_padding": 1,
+  "dual_cross_attention": false,
+  "flip_sin_to_cos": true,
+  "freq_shift": 0,
+  "in_channels": 3,
+  "layers_per_block": 3,
+  "mid_block_scale_factor": 1,
+  "mid_block_type": "UNetMidBlock2DSimpleCrossAttn",
+  "norm_eps": 1e-05,
+  "norm_num_groups": 32,
+  "num_class_embeds": null,
+  "only_cross_attention": false,
+  "out_channels": 6,
+  "resnet_time_scale_shift": "scale_shift",
+  "sample_size": 64,
+  "up_block_types": [
+    "SimpleCrossAttnUpBlock2D",
+    "SimpleCrossAttnUpBlock2D",
+    "SimpleCrossAttnUpBlock2D",
+    "ResnetUpsampleBlock2D"
+  ],
+  "upcast_attention": false,
+  "use_linear_projection": false
+}

decoder/diffusion_pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df4c1b9bceeceb92a88ff252e964be3a39308e799fdf01d5557d247f11868310
+size 3542027081

decoder_scheduler/scheduler_config.json

@@ -0,0 +1,9 @@
+{
+  "_class_name": "UnCLIPScheduler",
+  "_diffusers_version": "0.12.0.dev0",
+  "clip_sample": true,
+  "clip_sample_range": 1.0,
+  "num_train_timesteps": 1000,
+  "prediction_type": "epsilon",
+  "variance_type": "learned_range"
+}

feature_extractor/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
+  }
+}

image_encoder/config.json

@@ -0,0 +1,23 @@
+{
+  "_name_or_path": "openai/clip-vit-large-patch14",
+  "architectures": [
+    "CLIPVisionModelWithProjection"
+  ],
+  "attention_dropout": 0.0,
+  "dropout": 0.0,
+  "hidden_act": "quick_gelu",
+  "hidden_size": 1024,
+  "image_size": 224,
+  "initializer_factor": 1.0,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "model_type": "clip_vision_model",
+  "num_attention_heads": 16,
+  "num_channels": 3,
+  "num_hidden_layers": 24,
+  "patch_size": 14,
+  "projection_dim": 768,
+  "torch_dtype": "float32",
+  "transformers_version": "4.25.1"
+}

image_encoder/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c304e9a1c99835f6c2d355cbb5438e7e6204d4903b2f1b056120be4bd5050f1f
+size 1215996977

model_index.json

@@ -0,0 +1,44 @@
+{
+  "_class_name": "UnCLIPImageVariationPipeline",
+  "_diffusers_version": "0.12.0.dev0",
+  "decoder": [
+    "diffusers",
+    "UNet2DConditionModel"
+  ],
+  "decoder_scheduler": [
+    "diffusers",
+    "UnCLIPScheduler"
+  ],
+  "feature_extractor": [
+    "transformers",
+    "CLIPImageProcessor"
+  ],
+  "image_encoder": [
+    "transformers",
+    "CLIPVisionModelWithProjection"
+  ],
+  "super_res_first": [
+    "diffusers",
+    "UNet2DModel"
+  ],
+  "super_res_last": [
+    "diffusers",
+    "UNet2DModel"
+  ],
+  "super_res_scheduler": [
+    "diffusers",
+    "UnCLIPScheduler"
+  ],
+  "text_encoder": [
+    "transformers",
+    "CLIPTextModelWithProjection"
+  ],
+  "text_proj": [
+    "unclip",
+    "UnCLIPTextProjModel"
+  ],
+  "tokenizer": [
+    "transformers",
+    "CLIPTokenizer"
+  ]
+}

super_res_first/config.json

@@ -0,0 +1,39 @@
+{
+  "_class_name": "UNet2DModel",
+  "_diffusers_version": "0.12.0.dev0",
+  "_name_or_path": "/home/william_huggingface_co/.cache/huggingface/diffusers/models--kakaobrain--karlo-v1-alpha/snapshots/c8dc0970acf0db0b6b4efb8c47adc22072b4a67d/super_res_first",
+  "act_fn": "silu",
+  "add_attention": false,
+  "attention_head_dim": 8,
+  "block_out_channels": [
+    320,
+    640,
+    960,
+    1280
+  ],
+  "center_input_sample": false,
+  "down_block_types": [
+    "ResnetDownsampleBlock2D",
+    "ResnetDownsampleBlock2D",
+    "ResnetDownsampleBlock2D",
+    "ResnetDownsampleBlock2D"
+  ],
+  "downsample_padding": 1,
+  "flip_sin_to_cos": true,
+  "freq_shift": 0,
+  "in_channels": 6,
+  "layers_per_block": 3,
+  "mid_block_scale_factor": 1,
+  "norm_eps": 1e-05,
+  "norm_num_groups": 32,
+  "out_channels": 3,
+  "resnet_time_scale_shift": "default",
+  "sample_size": 256,
+  "time_embedding_type": "positional",
+  "up_block_types": [
+    "ResnetUpsampleBlock2D",
+    "ResnetUpsampleBlock2D",
+    "ResnetUpsampleBlock2D",
+    "ResnetUpsampleBlock2D"
+  ]
+}

super_res_first/diffusion_pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be101081e8dba0d7dfe19845187c8efe6d4c68e32daa33224d1f8631333085b3
+size 2766471473

super_res_last/config.json

@@ -0,0 +1,39 @@
+{
+  "_class_name": "UNet2DModel",
+  "_diffusers_version": "0.12.0.dev0",
+  "_name_or_path": "/home/william_huggingface_co/.cache/huggingface/diffusers/models--kakaobrain--karlo-v1-alpha/snapshots/c8dc0970acf0db0b6b4efb8c47adc22072b4a67d/super_res_last",
+  "act_fn": "silu",
+  "add_attention": false,
+  "attention_head_dim": 8,
+  "block_out_channels": [
+    320,
+    640,
+    960,
+    1280
+  ],
+  "center_input_sample": false,
+  "down_block_types": [
+    "ResnetDownsampleBlock2D",
+    "ResnetDownsampleBlock2D",
+    "ResnetDownsampleBlock2D",
+    "ResnetDownsampleBlock2D"
+  ],
+  "downsample_padding": 1,
+  "flip_sin_to_cos": true,
+  "freq_shift": 0,
+  "in_channels": 6,
+  "layers_per_block": 3,
+  "mid_block_scale_factor": 1,
+  "norm_eps": 1e-05,
+  "norm_num_groups": 32,
+  "out_channels": 3,
+  "resnet_time_scale_shift": "default",
+  "sample_size": null,
+  "time_embedding_type": "positional",
+  "up_block_types": [
+    "ResnetUpsampleBlock2D",
+    "ResnetUpsampleBlock2D",
+    "ResnetUpsampleBlock2D",
+    "ResnetUpsampleBlock2D"
+  ]
+}

super_res_last/diffusion_pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3356695fc89b8fa39b3f1ec1d3d635cbc065387ef622a04593897aaae7247f2
+size 2766471473

super_res_scheduler/scheduler_config.json

@@ -0,0 +1,9 @@
+{
+  "_class_name": "UnCLIPScheduler",
+  "_diffusers_version": "0.12.0.dev0",
+  "clip_sample": true,
+  "clip_sample_range": 1.0,
+  "num_train_timesteps": 1000,
+  "prediction_type": "epsilon",
+  "variance_type": "fixed_small_log"
+}

text_encoder/config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "/home/william_huggingface_co/.cache/huggingface/diffusers/models--kakaobrain--karlo-v1-alpha/snapshots/c8dc0970acf0db0b6b4efb8c47adc22072b4a67d/text_encoder",
+  "architectures": [
+    "CLIPTextModelWithProjection"
+  ],
+  "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": "float32",
+  "transformers_version": "4.25.1",
+  "vocab_size": 49408
+}

text_encoder/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aec40a3f65f96219cb30a80554a39fcb365146b6aa7d0cb9621e08b010ba672d
+size 494666597

text_proj/config.json

@@ -0,0 +1,9 @@
+{
+  "_class_name": "UnCLIPTextProjModel",
+  "_diffusers_version": "0.12.0.dev0",
+  "_name_or_path": "/home/william_huggingface_co/.cache/huggingface/diffusers/models--kakaobrain--karlo-v1-alpha/snapshots/c8dc0970acf0db0b6b4efb8c47adc22072b4a67d/text_proj",
+  "clip_embeddings_dim": 768,
+  "clip_extra_context_tokens": 4,
+  "cross_attention_dim": 1536,
+  "time_embed_dim": 1280
+}

text_proj/diffusion_pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46c3cb5d013e22221d156a9f30ef9221a4f9cfc547ab295cff870b2e26405a62
+size 31517844

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": "!",
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer/tokenizer_config.json

@@ -0,0 +1,35 @@
+{
+  "add_prefix_space": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<|startoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "device_map": "auto",
+  "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": "/home/william_huggingface_co/.cache/huggingface/diffusers/models--kakaobrain--karlo-v1-alpha/snapshots/c8dc0970acf0db0b6b4efb8c47adc22072b4a67d/tokenizer",
+  "pad_token": "!",
+  "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
+  }
+}