Olive models

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+*.data filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,3 +1,35 @@
 ---
-license: creativeml-openrail-m
+license: openrail++
+base_model: stabilityai/stable-diffusion-xl-refiner-1.0
+language:
+  - en
+tags:
+  - stable-diffusion
+  - stable-diffusion-xl
+  - onnxruntime
+  - onnx
+  - text-to-image
 ---
+
+
+# Stable Diffusion XL 1.0 for ONNX Runtime CUDA provider
+
+## Introduction
+
+This repository hosts the optimized versions of **Stable Diffusion XL Refiner 1.0** 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_xl.py --provider cuda --optimize --use_fp16_fixed_vae --model_id stabilityai/stable-diffusion-xl-refiner-1.0
+```
+
+See the [usage instructions](#usage-example) for how to run the SDXL pipeline with the ONNX files hosted in this repository.
+
+## Model Description
+
+- **Developed by:** Stability AI
+- **Model type:** Diffusion-based text-to-image generative model
+- **License:** [CreativeML Open RAIL++-M License](https://huggingface.co/stabilityai/stable-diffusion-xl-refiner-1.0/blob/main/LICENSE.md)
+- **Model Description:** This is a conversion of the [SDXL base 1.0](https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0) and [SDXL refiner 1.0](https://huggingface.co/stabilityai/stable-diffusion-xl-refiner-1.0) models for [ONNX Runtime](https://github.com/microsoft/onnxruntime) inference with CUDA execution provider.
+
+The VAE decoder is converted from [sdxl-vae-fp16-fix](https://huggingface.co/madebyollin/sdxl-vae-fp16-fix). There are slight discrepancies between its output and that of the original VAE, but the decoded images should be [close enough for most purposes](https://huggingface.co/madebyollin/sdxl-vae-fp16-fix/discussions/7#64c5c0f8e2e5c94bd04eaa80).

model_index.json

@@ -0,0 +1,47 @@
+{
+  "_class_name": "ORTStableDiffusionXLImg2ImgPipeline",
+  "_diffusers_version": "0.24.0",
+  "_name_or_path": "stabilityai/stable-diffusion-xl-refiner-1.0",
+  "feature_extractor": [
+    null,
+    null
+  ],
+  "force_zeros_for_empty_prompt": false,
+  "image_encoder": [
+    null,
+    null
+  ],
+  "requires_aesthetics_score": true,
+  "scheduler": [
+    "diffusers",
+    "EulerDiscreteScheduler"
+  ],
+  "text_encoder": [
+    "diffusers",
+    "OnnxRuntimeModel"
+  ],
+  "text_encoder_2": [
+    null,
+    null
+  ],
+  "tokenizer": [
+    null,
+    null
+  ],
+  "tokenizer_2": [
+    "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": "leading",
+  "timestep_type": "discrete",
+  "trained_betas": null,
+  "use_karras_sigmas": false
+}

text_encoder_2/model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b9f04f2d71f0ae8cbb085a78e1e65e2509607d694a84c15dde6de1ce2db58e0
+size 1389427378

text_encoder_2/model.onnx.data

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3da7ac65349fbd092e836e3eeca2c22811317bc804fd70af157b4550f2d4bcb5
+size 2778639360

tokenizer_2/special_tokens_map.json

@@ -0,0 +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
+  }
+}

tokenizer_2/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|>"
+}

unet/model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d60e07a44541db5c405e1d6210a04e6b1fa1b19a79758e0837cedaa3b00f06a1
+size 568878

unet/model.onnx.data

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f196e86f27210deadd211e86c079f57eb3468e6ac0d1d1b111a75facad9efd97
+size 4519331328

vae_decoder/model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7987d20deef6934d7d30bd7486da698940765d5383a5ca009f0aad74c737ec70
+size 99072671

vae_encoder/model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a56f9f96a763bc9995d032d6e03159cf433569047488e7594f0b15066cbed44f
+size 68412330