Upload folder using huggingface_hub

SpeechTokenizer/SpeechTokenizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d04593b6c9a4b475f91ca481141a6ef5b23e6ac112f347dd2b2717f193c1c728
+size 481906997

SpeechTokenizer/config.json

@@ -0,0 +1,48 @@
+{
+    "resblock": "1",
+    "num_gpus": 3,
+    "batch_size": 60,
+    "learning_rate": 0.0001,
+    "adam_b1": 0.5,
+    "adam_b2": 0.9,
+    "lr_decay": 0.98,
+    "seed": 1234,
+    "lambda_distill": 0.15,
+
+    "n_filters": 64,
+    "strides": [8,5,4,2],
+    "dimension": 1024,
+    "semantic_dimension": 768,
+    "bidirectional": true,
+    "dilation_base": 2,
+    "residual_kernel_size": 3,
+    "n_residual_layers": 1,
+    "lstm_layers": 2,
+    "activation": "ELU",
+
+
+    "segment_size": 48000,
+    "num_mels": 80,
+    "num_freq": 1025,
+    "n_fft": 1024,
+    "hop_size": 240,
+    "win_size": 1024,
+
+    "sampling_rate": 16000,
+    "sample_rate": 16000,
+
+    "codebook_size": 1024,
+    "n_q": 8,
+
+    "fmin": 0,
+    "fmax": 8000,
+    "fmax_for_loss": null,
+
+    "num_workers": 12,
+
+    "dist_config": {
+        "dist_backend": "nccl",
+        "dist_url": "tcp://localhost:54322",
+        "world_size": 1
+    }
+}

seed-tokenizer-2/eva_vit_g.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99d2bb36c6b52c94fe6e2e12373afb27de57ae81378c3d8c53bf0e83b0f4275f
+size 2025249237

seed-tokenizer-2/seed_quantizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:322a9fba55cb0e97e1a633981fbbdff20577af69146a0f23fa7b14201459a13f
+size 1228836570

seed-tokenizer-2/special_tokens_map.json

@@ -0,0 +1,27 @@
+{
+  "additional_special_tokens": [
+    "<img>",
+    "</img>"
+  ],
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

seed-tokenizer-2/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

seed-tokenizer-2/tokenizer_config.json

@@ -0,0 +1,33 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": false,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

stable-diffusion-2-1-unclip/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
+  }
+}

stable-diffusion-2-1-unclip/image_encoder/config.json

@@ -0,0 +1,23 @@
+{
+  "_name_or_path": "./image_encoder",
+  "architectures": [
+    "CLIPVisionModelWithProjection"
+  ],
+  "attention_dropout": 0.0,
+  "dropout": 0.0,
+  "hidden_act": "gelu",
+  "hidden_size": 1280,
+  "image_size": 224,
+  "initializer_factor": 1.0,
+  "initializer_range": 0.02,
+  "intermediate_size": 5120,
+  "layer_norm_eps": 1e-05,
+  "model_type": "clip_vision_model",
+  "num_attention_heads": 16,
+  "num_channels": 3,
+  "num_hidden_layers": 32,
+  "patch_size": 14,
+  "projection_dim": 1024,
+  "torch_dtype": "float16",
+  "transformers_version": "4.28.0.dev0"
+}

stable-diffusion-2-1-unclip/image_encoder/model.fp16.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64a7ef761bfccbadbaa3da77366aac4185a6c58fa5de5f589b42a65bcc21f161
+size 1264219396

stable-diffusion-2-1-unclip/image_encoder/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d277aeaed13ebc0ef33e56027b826a74433d45d755b3e0b3829440c1ea7b72e
+size 2528373452

stable-diffusion-2-1-unclip/image_encoder/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d3ec1e66737f77a4f3bc2df3c52eacefc69ce7825e2784183b1d4e9877d9193
+size 2528481905

stable-diffusion-2-1-unclip/image_encoder/pytorch_model.fp16.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49e56ff753584e2fd7708b8315b66b20f0c4ccd09723d6e589b797d3ea019d23
+size 1264330920

stable-diffusion-2-1-unclip/image_noising_scheduler/scheduler_config.json

@@ -0,0 +1,16 @@
+{
+  "_class_name": "DDPMScheduler",
+  "_diffusers_version": "0.15.0.dev0",
+  "beta_end": 0.02,
+  "beta_schedule": "squaredcos_cap_v2",
+  "beta_start": 0.0001,
+  "clip_sample": true,
+  "clip_sample_range": 1.0,
+  "dynamic_thresholding_ratio": 0.995,
+  "num_train_timesteps": 1000,
+  "prediction_type": "epsilon",
+  "sample_max_value": 1.0,
+  "thresholding": false,
+  "trained_betas": null,
+  "variance_type": "fixed_small"
+}

stable-diffusion-2-1-unclip/image_normalizer/config.json

@@ -0,0 +1,6 @@
+{
+  "_class_name": "StableUnCLIPImageNormalizer",
+  "_diffusers_version": "0.15.0.dev0",
+  "_name_or_path": "./image_normalizer",
+  "embedding_dim": 1024
+}

stable-diffusion-2-1-unclip/image_normalizer/diffusion_pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62d9bea2335c36ba4aad0dee4d406ecbd1011b1364b0b88c34141bef471824c8
+size 9383

stable-diffusion-2-1-unclip/image_normalizer/diffusion_pytorch_model.fp16.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:124906d7b0b0c3af7a5ec242159700f788e736928f763fe135c4caa88ba03b58
+size 5307

stable-diffusion-2-1-unclip/image_normalizer/diffusion_pytorch_model.fp16.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:532a80f90c5602b0f76f557b01417afc5b438598e0f02459ae4c254f5755ad74
+size 4268

stable-diffusion-2-1-unclip/image_normalizer/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da5bbf61227cec34fa82500488b80162ba0d3a9b89f8428444dc766ac17a510d
+size 8364

stable-diffusion-2-1-unclip/model_index.json

@@ -0,0 +1,40 @@
+{
+  "_class_name": "StableUnCLIPImg2ImgPipeline",
+  "_diffusers_version": "0.15.0.dev0",
+  "feature_extractor": [
+    "transformers",
+    "CLIPImageProcessor"
+  ],
+  "image_encoder": [
+    "transformers",
+    "CLIPVisionModelWithProjection"
+  ],
+  "image_noising_scheduler": [
+    "diffusers",
+    "DDPMScheduler"
+  ],
+  "image_normalizer": [
+    "stable_diffusion",
+    "StableUnCLIPImageNormalizer"
+  ],
+  "scheduler": [
+    "diffusers",
+    "PNDMScheduler"
+  ],
+  "text_encoder": [
+    "transformers",
+    "CLIPTextModel"
+  ],
+  "tokenizer": [
+    "transformers",
+    "CLIPTokenizer"
+  ],
+  "unet": [
+    "diffusers",
+    "UNet2DConditionModel"
+  ],
+  "vae": [
+    "diffusers",
+    "AutoencoderKL"
+  ]
+}

stable-diffusion-2-1-unclip/scheduler/scheduler_config.json

@@ -0,0 +1,18 @@
+{
+  "_class_name": "PNDMScheduler",
+  "_diffusers_version": "0.15.0.dev0",
+  "beta_end": 0.012,
+  "beta_schedule": "scaled_linear",
+  "beta_start": 0.00085,
+  "clip_sample": false,
+  "clip_sample_range": 1.0,
+  "dynamic_thresholding_ratio": 0.995,
+  "num_train_timesteps": 1000,
+  "prediction_type": "v_prediction",
+  "sample_max_value": 1.0,
+  "set_alpha_to_one": false,
+  "skip_prk_steps": true,
+  "steps_offset": 1,
+  "thresholding": false,
+  "trained_betas": null
+}

stable-diffusion-2-1-unclip/sd21-unclip-h.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4124cbcf397ace8c536908f5f877a1f091a41168d1d3d9fd0c84484c1653693b
+size 7967306143

stable-diffusion-2-1-unclip/sd21-unclip-l.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed12098385701c1850defd3d2bc20905c7c64dad3ccad895a7f13b406aab7602
+size 6161550731

stable-diffusion-2-1-unclip/text_encoder/config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "./text_encoder",
+  "architectures": [
+    "CLIPTextModel"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "dropout": 0.0,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_size": 1024,
+  "initializer_factor": 1.0,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 77,
+  "model_type": "clip_text_model",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 23,
+  "pad_token_id": 1,
+  "projection_dim": 512,
+  "torch_dtype": "float16",
+  "transformers_version": "4.28.0.dev0",
+  "vocab_size": 49408
+}

stable-diffusion-2-1-unclip/text_encoder/model.fp16.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ab158327d06ce861b5c78843672c78433ea82fcf03f142097ba204b81251cd2
+size 680821102

stable-diffusion-2-1-unclip/text_encoder/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e4aa519f64dc6386f88221a66c106a09fa027b47a20cc0e126687695f2a6669
+size 1361597016

stable-diffusion-2-1-unclip/text_encoder/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2188379b05015f531d61503e714234d00a64939792f3098b324e516547f0194f
+size 1361674657

stable-diffusion-2-1-unclip/text_encoder/pytorch_model.fp16.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7bb11b1da63986aaaaefb5ef2100d34109c024ac640cacd9ed697150c1c57f01
+size 680900852

stable-diffusion-2-1-unclip/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
+  }
+}

stable-diffusion-2-1-unclip/tokenizer/tokenizer_config.json

@@ -0,0 +1,33 @@
+{
+  "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,
+  "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
+  }
+}

stable-diffusion-2-1-unclip/unet/config.json

@@ -0,0 +1,57 @@
+{
+  "_class_name": "UNet2DConditionModel",
+  "_diffusers_version": "0.15.0.dev0",
+  "_name_or_path": "./unet",
+  "act_fn": "silu",
+  "attention_head_dim": [
+    5,
+    10,
+    20,
+    20
+  ],
+  "block_out_channels": [
+    320,
+    640,
+    1280,
+    1280
+  ],
+  "center_input_sample": false,
+  "class_embed_type": "projection",
+  "class_embeddings_concat": false,
+  "conv_in_kernel": 3,
+  "conv_out_kernel": 3,
+  "cross_attention_dim": 1024,
+  "down_block_types": [
+    "CrossAttnDownBlock2D",
+    "CrossAttnDownBlock2D",
+    "CrossAttnDownBlock2D",
+    "DownBlock2D"
+  ],
+  "downsample_padding": 1,
+  "dual_cross_attention": false,
+  "flip_sin_to_cos": true,
+  "freq_shift": 0,
+  "in_channels": 4,
+  "layers_per_block": 2,
+  "mid_block_scale_factor": 1,
+  "mid_block_type": "UNetMidBlock2DCrossAttn",
+  "norm_eps": 1e-05,
+  "norm_num_groups": 32,
+  "num_class_embeds": null,
+  "only_cross_attention": false,
+  "out_channels": 4,
+  "projection_class_embeddings_input_dim": 2048,
+  "resnet_time_scale_shift": "default",
+  "sample_size": 96,
+  "time_cond_proj_dim": null,
+  "time_embedding_type": "positional",
+  "timestep_post_act": null,
+  "up_block_types": [
+    "UpBlock2D",
+    "CrossAttnUpBlock2D",
+    "CrossAttnUpBlock2D",
+    "CrossAttnUpBlock2D"
+  ],
+  "upcast_attention": true,
+  "use_linear_projection": true
+}

stable-diffusion-2-1-unclip/unet/diffusion_pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4661ff3ad977deec42ee692862f6664614686647bd61be2a9aedbff2b95b7b04
+size 3480976157

stable-diffusion-2-1-unclip/unet/diffusion_pytorch_model.fp16.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc2f1654fc8192838a742d99db3ec1558615a3c3726892dc4334f222f47720d1
+size 1740633377

stable-diffusion-2-1-unclip/unet/diffusion_pytorch_model.fp16.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a11c42f0619d06677f792a29b36277bf78bcefb7c010583c631da62e40630ff5
+size 1740430084

stable-diffusion-2-1-unclip/unet/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:902a190c84ff59777cb0ecb7cd0eb86be822e6e2687376aa744ffb2d398b0b86
+size 3480776620

stable-diffusion-2-1-unclip/vae/config.json

@@ -0,0 +1,31 @@
+{
+  "_class_name": "AutoencoderKL",
+  "_diffusers_version": "0.15.0.dev0",
+  "_name_or_path": "./vae",
+  "act_fn": "silu",
+  "block_out_channels": [
+    128,
+    256,
+    512,
+    512
+  ],
+  "down_block_types": [
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D"
+  ],
+  "in_channels": 3,
+  "latent_channels": 4,
+  "layers_per_block": 2,
+  "norm_num_groups": 32,
+  "out_channels": 3,
+  "sample_size": 768,
+  "scaling_factor": 0.18215,
+  "up_block_types": [
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D"
+  ]
+}

stable-diffusion-2-1-unclip/vae/diffusion_pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36bb8e1b54aba3a0914eb35fba13dcb107e9f18d379d1df2158732cd4bf56a94
+size 334711857

stable-diffusion-2-1-unclip/vae/diffusion_pytorch_model.fp16.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c13979094c6566d9aa5936879055457022f34a747eeba12542504853385077c8
+size 167405395

stable-diffusion-2-1-unclip/vae/diffusion_pytorch_model.fp16.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8b011e5a18c53888d51a81aa28223ddec87b450c14dc9650d9c3ebbcd17624e
+size 167335350

stable-diffusion-2-1-unclip/vae/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1d993488569e928462932c8c38a0760b874d166399b14414135bd9c42df5815
+size 334643276