add v1-2 fp16 weights

model_index.json

@@ -9,14 +9,14 @@
     "stable_diffusion",
     "StableDiffusionSafetyChecker"
   ],
-  "text_encoder": [
-    "transformers",
-    "CLIPTextModel"
-  ],
   "scheduler": [
     "diffusers",
     "DDIMScheduler"
   ],
+  "text_encoder": [
+    "transformers",
+    "CLIPTextModel"
+  ],
   "tokenizer": [
     "transformers",
     "CLIPTokenizer"

safety_checker/config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "./safety_module",
+  "_name_or_path": "waifu-diffusion/safety_checker",
   "architectures": [
     "StableDiffusionSafetyChecker"
   ],
@@ -68,6 +68,7 @@
     "sep_token_id": null,
     "task_specific_params": null,
     "temperature": 1.0,
+    "tf_legacy_loss": false,
     "tie_encoder_decoder": false,
     "tie_word_embeddings": true,
     "tokenizer_class": null,
@@ -75,7 +76,7 @@
     "top_p": 1.0,
     "torch_dtype": null,
     "torchscript": false,
-    "transformers_version": "4.21.0.dev0",
+    "transformers_version": "4.21.3",
     "typical_p": 1.0,
     "use_bfloat16": false,
     "vocab_size": 49408
@@ -86,7 +87,7 @@
     "num_attention_heads": 12,
     "num_hidden_layers": 12
   },
-  "torch_dtype": "float32",
+  "torch_dtype": "float16",
   "transformers_version": null,
   "vision_config": {
     "_name_or_path": "",
@@ -133,6 +134,7 @@
     "num_attention_heads": 16,
     "num_beam_groups": 1,
     "num_beams": 1,
+    "num_channels": 3,
     "num_hidden_layers": 24,
     "num_return_sequences": 1,
     "output_attentions": false,
@@ -150,6 +152,7 @@
     "sep_token_id": null,
     "task_specific_params": null,
     "temperature": 1.0,
+    "tf_legacy_loss": false,
     "tie_encoder_decoder": false,
     "tie_word_embeddings": true,
     "tokenizer_class": null,
@@ -157,7 +160,7 @@
     "top_p": 1.0,
     "torch_dtype": null,
     "torchscript": false,
-    "transformers_version": "4.21.0.dev0",
+    "transformers_version": "4.21.3",
     "typical_p": 1.0,
     "use_bfloat16": false
   },

text_encoder/config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "openai/clip-vit-large-patch14",
+  "_name_or_path": "waifu-diffusion/text_encoder",
   "architectures": [
     "CLIPTextModel"
   ],
@@ -18,7 +18,7 @@
   "num_attention_heads": 12,
   "num_hidden_layers": 12,
   "pad_token_id": 1,
-  "torch_dtype": "float32",
-  "transformers_version": "4.21.2",
+  "torch_dtype": "float16",
+  "transformers_version": "4.21.3",
   "vocab_size": 49408
 }

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": "waifu-diffusion/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": "0.2.4",
+  "_name_or_path": "waifu-diffusion/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 sha256:5a0975433af275427f2feca4b2658803871443141efd54450323c72f5e824a34
+oid sha256:e560ff047c2f0227b5188a7325e59301ec61507200cc00543c2a71440fdb8da0
 size 1719322405

vae/config.json

@@ -1,6 +1,7 @@
 {
   "_class_name": "AutoencoderKL",
   "_diffusers_version": "0.2.4",
+  "_name_or_path": "waifu-diffusion/vae",
   "act_fn": "silu",
   "block_out_channels": [
     128,