Upload 14 files

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": "/home/disty/.cache/huggingface/hub/models--stabilityai--stable-cascade-prior/snapshots/7ca32c21c3b4d4e35bbb94fcfedfb4fa2259bd91/image_encoder",
+  "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": "float16",
+  "transformers_version": "4.38.0"
+}

image_encoder/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0dd0c1777bb75e2e9b7aa29b799b3ee8ebaaaa731e2c471a9ec589f12542cce7
+size 607980096

model_index.json

@@ -0,0 +1,30 @@
+{
+  "_class_name": "StableCascadePriorPipeline",
+  "_diffusers_version": "0.28.0.dev0",
+  "_name_or_path": "Disty0/sotediffusion-wuerstchen3-alpha1",
+  "feature_extractor": [
+    "transformers",
+    "CLIPImageProcessor"
+  ],
+  "image_encoder": [
+    "transformers",
+    "CLIPVisionModelWithProjection"
+  ],
+  "prior": [
+    "diffusers",
+    "StableCascadeUNet"
+  ],
+  "resolution_multiple": 42.67,
+  "scheduler": [
+    "diffusers",
+    "DDPMWuerstchenScheduler"
+  ],
+  "text_encoder": [
+    "transformers",
+    "CLIPTextModelWithProjection"
+  ],
+  "tokenizer": [
+    "transformers",
+    "CLIPTokenizerFast"
+  ]
+}

prior/config.json

@@ -0,0 +1,64 @@
+{
+  "_class_name": "StableCascadeUNet",
+  "_diffusers_version": "0.28.0.dev0",
+  "block_out_channels": [
+    2048,
+    2048
+  ],
+  "block_types_per_layer": [
+    [
+      "SDCascadeResBlock",
+      "SDCascadeTimestepBlock",
+      "SDCascadeAttnBlock"
+    ],
+    [
+      "SDCascadeResBlock",
+      "SDCascadeTimestepBlock",
+      "SDCascadeAttnBlock"
+    ]
+  ],
+  "clip_image_in_channels": 768,
+  "clip_seq": 4,
+  "clip_text_in_channels": 1280,
+  "clip_text_pooled_in_channels": 1280,
+  "conditioning_dim": 2048,
+  "down_blocks_repeat_mappers": [
+    1,
+    1
+  ],
+  "down_num_layers_per_block": [
+    8,
+    24
+  ],
+  "dropout": [
+    0.1,
+    0.1
+  ],
+  "effnet_in_channels": null,
+  "in_channels": 16,
+  "kernel_size": 3,
+  "num_attention_heads": [
+    32,
+    32
+  ],
+  "out_channels": 16,
+  "patch_size": 1,
+  "pixel_mapper_in_channels": null,
+  "self_attn": true,
+  "switch_level": [
+    false
+  ],
+  "timestep_conditioning_type": [
+    "sca",
+    "crp"
+  ],
+  "timestep_ratio_embedding_dim": 64,
+  "up_blocks_repeat_mappers": [
+    1,
+    1
+  ],
+  "up_num_layers_per_block": [
+    24,
+    8
+  ]
+}

prior/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2a0e03528df19cb0ca8de92260c4e6250efc229266417fbfb5ff29539fe0312
+size 7178376264

scheduler/scheduler_config.json

@@ -0,0 +1,6 @@
+{
+  "_class_name": "DDPMWuerstchenScheduler",
+  "_diffusers_version": "0.28.0.dev0",
+  "s": 0.008,
+  "scaler": 1.0
+}

text_encoder/config.json

@@ -0,0 +1,24 @@
+{
+  "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": "float16",
+  "transformers_version": "4.38.0",
+  "vocab_size": 49408
+}

text_encoder/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56e9219cc53d31ec26690f07587a065394173cceb75cef56b2e8a8bcb7a548f4
+size 1389382176

tokenizer/special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<|startoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "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": false,
+      "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|>"
+}