Upload 13 files

decoder/config.json

@@ -0,0 +1,83 @@
+{
+  "_class_name": "StableCascadeUNet",
+  "_diffusers_version": "0.28.0.dev0",
+  "block_out_channels": [
+    320,
+    640,
+    1280,
+    1280
+  ],
+  "block_types_per_layer": [
+    [
+      "SDCascadeResBlock",
+      "SDCascadeTimestepBlock"
+    ],
+    [
+      "SDCascadeResBlock",
+      "SDCascadeTimestepBlock"
+    ],
+    [
+      "SDCascadeResBlock",
+      "SDCascadeTimestepBlock",
+      "SDCascadeAttnBlock"
+    ],
+    [
+      "SDCascadeResBlock",
+      "SDCascadeTimestepBlock",
+      "SDCascadeAttnBlock"
+    ]
+  ],
+  "clip_image_in_channels": null,
+  "clip_seq": 4,
+  "clip_text_in_channels": null,
+  "clip_text_pooled_in_channels": 1280,
+  "conditioning_dim": 1280,
+  "down_blocks_repeat_mappers": [
+    1,
+    1,
+    1,
+    1
+  ],
+  "down_num_layers_per_block": [
+    2,
+    6,
+    28,
+    6
+  ],
+  "dropout": [
+    0,
+    0,
+    0.1,
+    0.1
+  ],
+  "effnet_in_channels": 16,
+  "in_channels": 4,
+  "kernel_size": 3,
+  "num_attention_heads": [
+    0,
+    0,
+    20,
+    20
+  ],
+  "out_channels": 4,
+  "patch_size": 2,
+  "pixel_mapper_in_channels": 3,
+  "self_attn": true,
+  "switch_level": null,
+  "timestep_conditioning_type": [
+    "sca"
+  ],
+  "timestep_ratio_embedding_dim": 64,
+  "up_blocks_repeat_mappers": [
+    3,
+    3,
+    2,
+    2
+  ],
+  "up_num_layers_per_block": [
+    6,
+    28,
+    6,
+    2
+  ]
+}

decoder/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e73c9e39bdb6e1e4cafd1c8874812bf72d4733257d464194083da088367ab58
+size 3126069360

model_index.json

@@ -0,0 +1,26 @@
+{
+  "_class_name": "StableCascadeDecoderPipeline",
+  "_diffusers_version": "0.28.0.dev0",
+  "_name_or_path": "Disty0/sotediffusion-wuerstchen3-alpha3-decoder",
+  "decoder": [
+    "diffusers",
+    "StableCascadeUNet"
+  ],
+  "latent_dim_scale": 10.67,
+  "scheduler": [
+    "diffusers",
+    "DDPMWuerstchenScheduler"
+  ],
+  "text_encoder": [
+    "transformers",
+    "CLIPTextModelWithProjection"
+  ],
+  "tokenizer": [
+    "transformers",
+    "CLIPTokenizerFast"
+  ],
+  "vqgan": [
+    "wuerstchen",
+    "PaellaVQModel"
+  ]
+}

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": 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": "float16",
+  "transformers_version": "4.36.2",
+  "vocab_size": 49408
+}

text_encoder/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00ff831dd81b2e2a6b0952fb7f59ea07bcef5046de97e671978e1ad84cb44975
+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|>"
+}

vqgan/config.json

@@ -0,0 +1,14 @@
+{
+  "_class_name": "PaellaVQModel",
+  "_diffusers_version": "0.28.0.dev0",
+  "_name_or_path": "madebyollin/stage-a-ft-hq",
+  "bottleneck_blocks": 12,
+  "embed_dim": 384,
+  "in_channels": 3,
+  "latent_channels": 4,
+  "levels": 2,
+  "num_vq_embeddings": 8192,
+  "out_channels": 3,
+  "scale_factor": 0.3764,
+  "up_down_scale_factor": 2
+}

vqgan/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cdaaa4be9238d7e2d68528d284f9b69fb9c34de6c06528c35d6dedd878b29cd0
+size 36825700