Upload folder using huggingface_hub

efficient_net/config.json

@@ -1,6 +1,6 @@
 {
   "_class_name": "EfficientNetEncoder",
-  "_diffusers_version": "0.19.0.dev0",
+  "_diffusers_version": "0.20.0.dev0",
   "c_latent": 16,
   "effnet": "efficientnet_v2_s"
 }

efficient_net/diffusion_pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f1f3d235e79d86c2be4f8593b5bdf698961d46513951be8171afe7d43463f9fd
-size 81693533
+oid sha256:e57aa4d30b24fb974eb60128389a76d9a91d05fc234a70a4feeb820239f219b9
+size 81693998

generator/config.json

@@ -1,6 +1,6 @@
 {
   "_class_name": "DiffNeXt",
-  "_diffusers_version": "0.19.0.dev0",
+  "_diffusers_version": "0.20.0.dev0",
   "blocks": [
     4,
     4,

generator/diffusion_pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a9c206b0ea6feb149622a6b149ad05831bd4fa2980c734ec04f442f6c239dc06
-size 4221776293
+oid sha256:7a72fcca3d792222e0a02a28f3d908f7cf84720ebe33be21c2de4864b46d866b
+size 4221776758

model_index.json

@@ -1,6 +1,6 @@
 {
   "_class_name": "WuerstchenGeneratorPipeline",
-  "_diffusers_version": "0.19.0.dev0",
+  "_diffusers_version": "0.20.0.dev0",
   "efficient_net": [
     "wuerstchen",
     "EfficientNetEncoder"
@@ -13,6 +13,14 @@
     "diffusers",
     "DDPMWuerstchenScheduler"
   ],
+  "text_encoder": [
+    "transformers",
+    "CLIPTextModel"
+  ],
+  "tokenizer": [
+    "transformers",
+    "CLIPTokenizerFast"
+  ],
   "vqgan": [
     "diffusers",
     "VQModelPaella"

scheduler/scheduler_config.json

@@ -1,6 +1,6 @@
 {
   "_class_name": "DDPMWuerstchenScheduler",
-  "_diffusers_version": "0.19.0.dev0",
+  "_diffusers_version": "0.20.0.dev0",
   "s": 0.008,
   "scaler": 1.0
 }

text_encoder/config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "laion/CLIP-ViT-H-14-laion2B-s32B-b79K",
+  "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": 24,
+  "pad_token_id": 1,
+  "projection_dim": 1024,
+  "torch_dtype": "float32",
+  "transformers_version": "4.32.0.dev0",
+  "vocab_size": 49408
+}

text_encoder/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0483b11b48b0f5a5079f778c0df4057d7b797cf58ef176087ec03a236d3e16e0
+size 1412064410

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": "<|endoftext|>",
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

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
+  },
+  "clean_up_tokenization_spaces": true,
+  "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|>",
+  "tokenizer_class": "CLIPTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

vqgan/config.json

@@ -1,6 +1,6 @@
 {
   "_class_name": "VQModelPaella",
-  "_diffusers_version": "0.19.0.dev0",
+  "_diffusers_version": "0.20.0.dev0",
   "bottleneck_blocks": 12,
   "c_hidden": 384,
   "c_latent": 4,

vqgan/diffusion_pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:877e0e8a634e9e43b66d1e52ad8a6110a9853025322e8293a82dcc88740f0acc
-size 73673677
+oid sha256:f3ab7752b474058d177e8565860367a438b8016ba788954394fbb7f1da16d6e1
+size 73674142