Initial Commit

R35-A_Bstage.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18394f42b0c8b2904f137a77b62d44b5582b1d5c8f82bacb00a54be4dda7345e
+size 2953754192

R35-A_Cstage.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:800b6221fde13ac216306a4744ab0a07332b3d19139b6029feaa45c4da7c416d
+size 7178351136

R35-A_text_encoder.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58b55b2fb7cda78df35c49eab411396c4b8fb0e0d361ec867222ba1dbe44593b
+size 1389383040

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": "bfloat16",
+  "transformers_version": "4.41.1"
+}

image_encoder/model.bf16.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4b33d864f89a793357a768cb07d0dc18d6a14e6664f4110a0d535ca9ba78da8
+size 607980488

image_encoder/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77b33d2a3a643650857672e880ccf73adbaf114fbbadec36d142ee9d48af7e20
+size 1215912728

model_index.json

@@ -0,0 +1,34 @@
+{
+  "_class_name": "StableCascadePriorPipeline",
+  "_diffusers_version": "0.28.2",
+  "_name_or_path": "c0ur4ge/R35ON4NCE",
+  "feature_extractor": [
+    null,
+    null
+  ],
+  "feature_extractor": [
+	"transformers",
+	"CLIPImageProcessor"
+  ],
+  "image_encoder": [
+    "transformers",
+    "CLIPVisionModelWithProjection"
+  ],
+  "prior": [
+    "diffusers",
+    "StableCascadeUNet"
+  ],
+  "resolution_multiple": 42.67,
+  "scheduler": [
+    "diffusers",
+    "DDPMWuerstchenScheduler"
+  ],
+  "text_encoder": [
+    "transformers",
+    "CLIPTextModelWithProjection"
+  ],
+  "tokenizer": [
+    "transformers",
+    "CLIPTokenizer"
+  ]
+}

optimizer/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b574353071774ab1332493f40093fc7865d5e4b9a5f449300597102de263fcd
+size 104546818

prior/config.json

@@ -0,0 +1,64 @@
+{
+  "_class_name": "StableCascadeUNet",
+  "_diffusers_version": "0.28.2",
+  "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:c8e35af3698f674d2d90d40332e1c5c8c75c7e66462efe374b9796a7e4318520
+size 14356584672

scheduler/scheduler_config.json

@@ -0,0 +1,6 @@
+{
+  "_class_name": "DDPMWuerstchenScheduler",
+  "_diffusers_version": "0.28.2",
+  "s": 0.008,
+  "scaler": 1.0
+}

text_encoder/config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "workspace/v2\\backup\\2024-04-13_11-01-19-backup-316502-15-685",
+  "architectures": [
+    "CLIPTextModelWithProjection"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 49406,
+  "dropout": 0.0,
+  "eos_token_id": 49407,
+  "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": "float32",
+  "transformers_version": "4.41.1",
+  "vocab_size": 49408
+}

text_encoder/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4343bc78d3c2d94647c80b4877824ce62cc23e59784fffd2393d06165fb791dd
+size 2778702264

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|>"
+}