fp16 weights with Attention and other fusion optimizations

model_index.json

@@ -1,37 +1,37 @@
-{
-  "_class_name": "OnnxStableDiffusionPipeline",
-  "_diffusers_version": "0.19.3",
-  "feature_extractor": [
-    null,
-    null
-  ],
-  "requires_safety_checker": false,
-  "safety_checker": [
-    null,
-    null
-  ],
-  "scheduler": [
-    "diffusers",
-    "PNDMScheduler"
-  ],
-  "text_encoder": [
-    "diffusers",
-    "OnnxRuntimeModel"
-  ],
-  "tokenizer": [
-    "transformers",
-    "CLIPTokenizer"
-  ],
-  "unet": [
-    "diffusers",
-    "OnnxRuntimeModel"
-  ],
-  "vae_decoder": [
-    "diffusers",
-    "OnnxRuntimeModel"
-  ],
-  "vae_encoder": [
-    "diffusers",
-    "OnnxRuntimeModel"
-  ]
-}
+{
+  "_class_name": "OnnxStableDiffusionPipeline",
+  "_diffusers_version": "0.15.1",
+  "feature_extractor": [
+    null,
+    null
+  ],
+  "requires_safety_checker": false,
+  "safety_checker": [
+    null,
+    null
+  ],
+  "scheduler": [
+    "diffusers",
+    "PNDMScheduler"
+  ],
+  "text_encoder": [
+    "diffusers",
+    "OnnxRuntimeModel"
+  ],
+  "tokenizer": [
+    "transformers",
+    "CLIPTokenizer"
+  ],
+  "unet": [
+    "diffusers",
+    "OnnxRuntimeModel"
+  ],
+  "vae_decoder": [
+    "diffusers",
+    "OnnxRuntimeModel"
+  ],
+  "vae_encoder": [
+    "diffusers",
+    "OnnxRuntimeModel"
+  ]
+}

scheduler/scheduler_config.json

@@ -1,15 +1,14 @@
-{
-  "_class_name": "PNDMScheduler",
-  "_diffusers_version": "0.19.3",
-  "beta_end": 0.012,
-  "beta_schedule": "scaled_linear",
-  "beta_start": 0.00085,
-  "clip_sample": false,
-  "num_train_timesteps": 1000,
-  "prediction_type": "epsilon",
-  "set_alpha_to_one": false,
-  "skip_prk_steps": true,
-  "steps_offset": 1,
-  "timestep_spacing": "leading",
-  "trained_betas": null
-}
+{
+  "_class_name": "PNDMScheduler",
+  "_diffusers_version": "0.15.1",
+  "beta_end": 0.012,
+  "beta_schedule": "scaled_linear",
+  "beta_start": 0.00085,
+  "clip_sample": false,
+  "num_train_timesteps": 1000,
+  "prediction_type": "epsilon",
+  "set_alpha_to_one": false,
+  "skip_prk_steps": true,
+  "steps_offset": 1,
+  "trained_betas": null
+}

text_encoder/model.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ffe610e8989587f7398cd34111e757a3ff06b9e0d235321387f1e9cb17b3d42
-size 1362137844
+oid sha256:7d41f9323f0c94e9281cbbf2fe8e10dd0865912c80ef62c9ccf5595e2a23d4d5
+size 681552894

tokenizer/special_tokens_map.json

@@ -1,24 +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": "!",
-  "unk_token": {
-    "content": "<|endoftext|>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  }
-}
+{
+  "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": "!",
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer/tokenizer_config.json

@@ -1,33 +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
-  }
-}
+{
+  "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
+  }
+}

unet/model.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bcc0e210793e28ea70c6248d57e62469560bbf72722a4d9fc738907e38392ef9
-size 1449465
+oid sha256:cd6bbbc8a188c04866b7ae582c83c2c38eb2a0fca860868bdda712b70be1a14e
+size 1750977785

vae_decoder/model.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:290d77779ca7e16ff9fcbfe4304a48684c334614690e1c9915a0a7bd40130d62
-size 126872
+oid sha256:be9adba6f9abe96e7f6b4929588c40561000a088ed1fb32d8987719edd7798cd
+size 99116928

vae_encoder/model.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:11b7f0a64e4704dccd4976607db9ac4627919cf5e1cd89058919d6c448e8a594
-size 136760234
+oid sha256:42ed2b1574dae05bf705ccde24f8be4474b88cc10c51265e18df1c44eb7c407c
+size 136760235