Upload StableCascadeDecoderPipeline

decoder/config.json

@@ -1,12 +1,12 @@
 {
   "_class_name": "StableCascadeUNet",
   "_diffusers_version": "0.30.2",
-  "_name_or_path": "/root/.cache/huggingface/hub/models--stabilityai--stable-cascade/snapshots/a89f66d459ae653e3b4d4f992a7c3789d0dc4d16/decoder",
+  "_name_or_path": "stabilityai/stable-cascade",
   "block_out_channels": [
     320,
-    640,
-    1280,
-    1280
+    576,
+    1152,
+    1152
   ],
   "block_types_per_layer": [
     [
@@ -41,9 +41,9 @@
   ],
   "down_num_layers_per_block": [
     2,
-    6,
-    28,
-    6
+    4,
+    14,
+    4
   ],
   "dropout": [
     0,
@@ -56,9 +56,9 @@
   "kernel_size": 3,
   "num_attention_heads": [
     0,
-    0,
-    20,
-    20
+    9,
+    18,
+    18
   ],
   "out_channels": 4,
   "patch_size": 2,
@@ -70,15 +70,15 @@
   ],
   "timestep_ratio_embedding_dim": 64,
   "up_blocks_repeat_mappers": [
-    3,
-    3,
+    2,
+    2,
     2,
     2
   ],
   "up_num_layers_per_block": [
-    6,
-    28,
-    6,
+    4,
+    14,
+    4,
     2
   ]
 }

decoder/diffusion_pytorch_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:76f506c71dbaac04ade47f31f9eb546f7fb6543adc4d7f44d24ab9e6177476fe
-size 6251952232
+oid sha256:7dcb3fc8b1e3f2a1756503472043a7d6810003a418b60b08674633b20b452ffb
+size 2797989648

model_index.json

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

text_encoder/config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "/root/.cache/huggingface/hub/models--stabilityai--stable-cascade-prior/snapshots/7ca32c21c3b4d4e35bbb94fcfedfb4fa2259bd91/text_encoder",
+  "_name_or_path": "/root/.cache/huggingface/hub/models--stabilityai--stable-cascade/snapshots/a89f66d459ae653e3b4d4f992a7c3789d0dc4d16/text_encoder",
   "architectures": [
     "CLIPTextModelWithProjection"
   ],

text_encoder/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa5b2e6f4c2efc2d82e4b8312faec1a5540eabfc6415126c9a05c8436a530ef4
+oid sha256:30e7a50f59884f068ac6bdc41b0ade553f23c0cbe2eaf3bac76369d2c39bfa37
 size 2778702264