update

StableCascade-prior/feature_extractor/preprocessor_config.json

@@ -1,27 +0,0 @@
-{
-  "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
-  }
-}

StableCascade-prior/image_encoder/config.json

@@ -1,23 +0,0 @@
-{
-  "_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": "4.38.2"
-}

StableCascade-prior/image_encoder/model.bf16.safetensors

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

StableCascade-prior/model_index.json

@@ -1,29 +0,0 @@
-{
-  "_class_name": "StableCascadePriorPipeline",
-  "_diffusers_version": "0.27.0.dev0",
-  "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"
-  ]
-}

StableCascade-prior/prior/config.json

@@ -1,64 +0,0 @@
-{
-  "_class_name": "StableCascadeUNet",
-  "_diffusers_version": "0.27.0.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
-  ]
-}

StableCascade-prior/prior/diffusion_pytorch_model.bf16.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:44a4cd9540f327f2fb4ac09179e4e87912a01cdb1b3b86c79f0f853976fb4c98
-size 7178377816

StableCascade-prior/scheduler/scheduler_config.json

@@ -1,6 +0,0 @@
-{
-  "_class_name": "DDPMWuerstchenScheduler",
-  "_diffusers_version": "0.27.0.dev0",
-  "s": 0.008,
-  "scaler": 1.0
-}

StableCascade-prior/text_encoder/config.json

@@ -1,25 +0,0 @@
-{
-  "_name_or_path": "laion/CLIP-ViT-bigG-14-laion2B-39B-b160k",
-  "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": "bfloat16",
-  "transformers_version": "4.38.2",
-  "vocab_size": 49408
-}

StableCascade-prior/text_encoder/model.bf16.safetensors

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

StableCascade-prior/tokenizer/special_tokens_map.json

@@ -1,30 +0,0 @@
-{
-  "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
-  }
-}

StableCascade-prior/tokenizer/tokenizer_config.json

@@ -1,30 +0,0 @@
-{
-  "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|>"
-}