models from Olive

README.md

@@ -20,6 +20,11 @@ tags:
 
 This repository hosts the optimized versions of **SD Turbo** to accelerate inference with ONNX Runtime CUDA execution provider.
 
+The models are generated by [Olive](https://github.com/microsoft/Olive/tree/main/examples/stable_diffusion) with command like the following:
+```
+python stable_diffusion.py --provider cuda --model_id stabilityai/sd-turbo --optimize --use_fp16_fixed_vae
+```
+
 See the [usage instructions](#usage-example) for how to run the SDXL pipeline with the ONNX files hosted in this repository.
 
 ## Model Description
@@ -37,10 +42,10 @@ Below is average latency of generating an image of size 512x512 using NVIDIA A10
 
 | Engine      | Batch Size | Steps | PyTorch 2.1     | ONNX Runtime CUDA |
 |-------------|------------|------ | ----------------|-------------------|
-| Static      | 1          |   1   | 85.3 ms         |  32.9 ms          |
-| Static      | 4          |   1   | 213.8 ms        |  97.5 ms          |
-| Static      | 1          |   4   | 117.4 ms        |  62.5 ms          |
-| Static      | 4          |   4   | 294.3 ms        | 168.3 ms          |
+| Static      | 1          |   1   | 85.3 ms         |  38.2 ms          |
+| Static      | 4          |   1   | 213.8 ms        | 120.2 ms          |
+| Static      | 1          |   4   | 117.4 ms        |  68.7 ms          |
+| Static      | 4          |   4   | 294.3 ms        | 192.6 ms          |
 
 
 Static means the engine is built for the given batch size and image size combination, and CUDA graph is used to speed up.
@@ -61,7 +66,7 @@ cd onnxruntime
 2. Download the SDXL ONNX files from this repo
 ```shell
 git lfs install
-git clone https://huggingface.co/tlwu/sdxl-turbo-onnxruntime
+git clone https://huggingface.co/tlwu/sd-turbo-onnxruntime
 ```
 
 3. Launch the docker
@@ -97,5 +102,5 @@ python3 -m pip install --upgrade polygraphy onnx-graphsurgeon --extra-index-url
 python3 demo_txt2img.py \
   "starry night over Golden Gate Bridge by van gogh" \
   --version sd-turbo   \
-  --work-dir /workspace/sd-turbo-onnxruntime
+  --engine-dir /workspace/sd-turbo-onnxruntime
 ```

model_index.json

@@ -0,0 +1,37 @@
+{
+  "_class_name": "OnnxStableDiffusionPipeline",
+  "_diffusers_version": "0.24.0",
+  "feature_extractor": [
+    null,
+    null
+  ],
+  "requires_safety_checker": true,
+  "safety_checker": [
+    null,
+    null
+  ],
+  "scheduler": [
+    "diffusers",
+    "EulerDiscreteScheduler"
+  ],
+  "text_encoder": [
+    "diffusers",
+    "OnnxRuntimeModel"
+  ],
+  "tokenizer": [
+    "transformers",
+    "CLIPTokenizer"
+  ],
+  "unet": [
+    "diffusers",
+    "OnnxRuntimeModel"
+  ],
+  "vae_decoder": [
+    "diffusers",
+    "OnnxRuntimeModel"
+  ],
+  "vae_encoder": [
+    "diffusers",
+    "OnnxRuntimeModel"
+  ]
+}

scheduler/scheduler_config.json

@@ -0,0 +1,21 @@
+{
+  "_class_name": "EulerDiscreteScheduler",
+  "_diffusers_version": "0.24.0",
+  "beta_end": 0.012,
+  "beta_schedule": "scaled_linear",
+  "beta_start": 0.00085,
+  "clip_sample": false,
+  "interpolation_type": "linear",
+  "num_train_timesteps": 1000,
+  "prediction_type": "epsilon",
+  "sample_max_value": 1.0,
+  "set_alpha_to_one": false,
+  "sigma_max": null,
+  "sigma_min": null,
+  "skip_prk_steps": true,
+  "steps_offset": 1,
+  "timestep_spacing": "trailing",
+  "timestep_type": "discrete",
+  "trained_betas": null,
+  "use_karras_sigmas": false
+}

{ORT_CUDA/sd-turbo/engine/clip.ort_cuda.fp16 → text_encoder}/model.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f1b1d827fb6013c67ac3f349b06d1a159373c2faf5253555e20b14ce2ebaacf
-size 680852028
+oid sha256:a0d07fcce1858783b635c4027a562c89690d7c9f3f36c6129f1aa35af380f3d8
+size 680854339

tokenizer/special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "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": {
+    "content": "!",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer/tokenizer_config.json

@@ -0,0 +1,38 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "!",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49406": {
+      "content": "<|startoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49407": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|startoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "do_lower_case": true,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "model_max_length": 77,
+  "pad_token": "!",
+  "tokenizer_class": "CLIPTokenizer",
+  "unk_token": "<|endoftext|>"
+}

ORT_CUDA/sd-turbo/engine/unet.ort_cuda.fp16/model.onnx.data → unet/model.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:402069ca12429e3f7b810770a49f0121a3f0f025a38317ebfd4b956d7de1c41e
-size 1732024320
+oid sha256:3b1170b54ca0ceafe1c709cd0268bd98892928e5589a7d72aec817669472beda
+size 1732410827

{ORT_CUDA/sd-turbo/engine/unet.ort_cuda.fp16 → vae_decoder}/model.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf77e0fc1a30bd77cbe86ddefccaadc30e2dc3a667c92418f3811f5417ce2af1
-size 371766
+oid sha256:8b5a9263fbd3ebd2647bae8e99cc99fdcff70a0b1b6a77ca7544c5f3e9e91649
+size 99072656

{ORT_CUDA/sd-turbo/engine/vae.ort_cuda.fp16 → vae_encoder}/model.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a72b771027dde10c6bb0af1347c9e30b0df54f186f3ff7c688f2b89354bcc7a2
-size 99070385
+oid sha256:dac0a94d703ba0ed900efaadc9d6e8dc4e9f1977d0f87f050aa05cb40d7c1638
+size 68412355