Upload StableCascadePriorPipeline

image_encoder/config.json

@@ -18,6 +18,6 @@
   "num_hidden_layers": 24,
   "patch_size": 14,
   "projection_dim": 768,
-  "torch_dtype": "bfloat16",
+  "torch_dtype": "float32",
   "transformers_version": "4.42.4"
 }

image_encoder/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e4b33d864f89a793357a768cb07d0dc18d6a14e6664f4110a0d535ca9ba78da8
-size 607980488
+oid sha256:77b33d2a3a643650857672e880ccf73adbaf114fbbadec36d142ee9d48af7e20
+size 1215912728

model_index.json

@@ -1,12 +1,20 @@
 {
-  "_class_name": "StableCascadeDecoderPipeline",
+  "_class_name": "StableCascadePriorPipeline",
   "_diffusers_version": "0.30.2",
-  "_name_or_path": "stabilityai/stable-cascade",
-  "decoder": [
+  "_name_or_path": "stabilityai/stable-cascade-prior",
+  "feature_extractor": [
+    "transformers",
+    "CLIPImageProcessor"
+  ],
+  "image_encoder": [
+    "transformers",
+    "CLIPVisionModelWithProjection"
+  ],
+  "prior": [
     "diffusers",
     "StableCascadeUNet"
   ],
-  "latent_dim_scale": 10.67,
+  "resolution_multiple": 42.67,
   "scheduler": [
     "diffusers",
     "DDPMWuerstchenScheduler"
@@ -18,9 +26,5 @@
   "tokenizer": [
     "transformers",
     "CLIPTokenizerFast"
-  ],
-  "vqgan": [
-    "wuerstchen",
-    "PaellaVQModel"
   ]
 }

prior/diffusion_pytorch_model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:497303431d8b99509af374a153b40e3e5fb12dd9e7da1bc493691b00582d8d5d
+size 9996332792

prior/diffusion_pytorch_model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ec49696ba8e5c4229844c88981185146501af3a0c00ffbec6947c914454635f
+size 4360250760

text_encoder/config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "/root/.cache/huggingface/hub/models--stabilityai--stable-cascade/snapshots/a89f66d459ae653e3b4d4f992a7c3789d0dc4d16/text_encoder",
+  "_name_or_path": "/root/.cache/huggingface/hub/models--stabilityai--stable-cascade-prior/snapshots/7ca32c21c3b4d4e35bbb94fcfedfb4fa2259bd91/text_encoder",
   "architectures": [
     "CLIPTextModelWithProjection"
   ],
@@ -19,7 +19,7 @@
   "num_hidden_layers": 32,
   "pad_token_id": 1,
   "projection_dim": 1280,
-  "torch_dtype": "bfloat16",
+  "torch_dtype": "float32",
   "transformers_version": "4.42.4",
   "vocab_size": 49408
 }

text_encoder/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:260e0127aca3c89db813637ae659ebb822cb07af71fedc16cbd980e9518dfdcd
-size 1389382688
+oid sha256:fa5b2e6f4c2efc2d82e4b8312faec1a5540eabfc6415126c9a05c8436a530ef4
+size 2778702264