fp16 weights

model_index.json

@@ -1,5 +1,5 @@
 {
-  "_class_name": "StableDiffusionPipeline",
+  "_class_name": "StableDiffusionInstructPix2PixPipeline",
   "_diffusers_version": "0.12.0.dev0",
   "feature_extractor": [
     "transformers",

safety_checker/config.json

@@ -1,6 +1,6 @@
 {
-  "_commit_hash": "cb41f3a270d63d454d385fc2e4f571c487c253c5",
-  "_name_or_path": "CompVis/stable-diffusion-safety-checker",
+  "_commit_hash": null,
+  "_name_or_path": "./instruct-pix2pix/safety_checker",
   "architectures": [
     "StableDiffusionSafetyChecker"
   ],
@@ -80,7 +80,7 @@
     "top_p": 1.0,
     "torch_dtype": null,
     "torchscript": false,
-    "transformers_version": "4.26.0.dev0",
+    "transformers_version": "4.25.1",
     "typical_p": 1.0,
     "use_bfloat16": false,
     "vocab_size": 49408
@@ -91,7 +91,7 @@
     "num_attention_heads": 12,
     "num_hidden_layers": 12
   },
-  "torch_dtype": "float32",
+  "torch_dtype": "float16",
   "transformers_version": null,
   "vision_config": {
     "_name_or_path": "",
@@ -167,7 +167,7 @@
     "top_p": 1.0,
     "torch_dtype": null,
     "torchscript": false,
-    "transformers_version": "4.26.0.dev0",
+    "transformers_version": "4.25.1",
     "typical_p": 1.0,
     "use_bfloat16": false
   },

safety_checker/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16d28f2b37109f222cdc33620fdd262102ac32112be0352a7f77e9614b35a394
-size 1216064769
+oid sha256:70b4ace4d3096de0a0c6d3574377bbaa17c6338daa9c728ea32f9cfd80a8907c
+size 608101569

text_encoder/config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "openai/clip-vit-large-patch14",
+  "_name_or_path": "./instruct-pix2pix/text_encoder",
   "architectures": [
     "CLIPTextModel"
   ],
@@ -19,7 +19,7 @@
   "num_hidden_layers": 12,
   "pad_token_id": 1,
   "projection_dim": 768,
-  "torch_dtype": "float32",
-  "transformers_version": "4.26.0.dev0",
+  "torch_dtype": "float16",
+  "transformers_version": "4.25.1",
   "vocab_size": 49408
 }

text_encoder/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:98124f3d5663b2f14ff08d4c29db93800622b4fcfa3d952bb6f9112f5d6dadd7
-size 492307041
+oid sha256:a371c4c8b166f660e8a97f5e618f27fb1b21d56dc2d171df1973e09e988d003c
+size 246186081

tokenizer/tokenizer_config.json

@@ -19,7 +19,7 @@
   },
   "errors": "replace",
   "model_max_length": 77,
-  "name_or_path": "openai/clip-vit-large-patch14",
+  "name_or_path": "./instruct-pix2pix/tokenizer",
   "pad_token": "<|endoftext|>",
   "special_tokens_map_file": "./special_tokens_map.json",
   "tokenizer_class": "CLIPTokenizer",

unet/config.json

@@ -1,6 +1,7 @@
 {
   "_class_name": "UNet2DConditionModel",
   "_diffusers_version": "0.12.0.dev0",
+  "_name_or_path": "./instruct-pix2pix/unet",
   "act_fn": "silu",
   "attention_head_dim": 8,
   "block_out_channels": [

unet/diffusion_pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b83d6c874bc598364d113910c8d5a521eb83550fcecc0b4ddd2472c6de4323db
-size 3438412453
+oid sha256:d5c12f3ea6e5173c706fcd6052698b8e5029f2185c329225f57f7c071e37e916
+size 1719347493

vae/config.json

@@ -1,6 +1,7 @@
 {
   "_class_name": "AutoencoderKL",
   "_diffusers_version": "0.12.0.dev0",
+  "_name_or_path": "./instruct-pix2pix/vae",
   "act_fn": "silu",
   "block_out_channels": [
     128,

vae/diffusion_pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:af27ea858349760ebe3311953e0bfe8d6fd257dc9537ae0b2b938c262132a2c6
-size 334711857
+oid sha256:f6e817ec7c5c6641c0000a1a7fc7893f6625251131f33f7bb034c55e5d949455
+size 167404145