commit files to HF hub

README.md

@@ -0,0 +1,62 @@
+---
+license: openrail++
+tags:
+- stable-diffusion
+- text-to-image
+- openvino
+ 
+---
+
+# OpenVINO Stable Diffusion 
+
+## stabilityai/stable-diffusion-2-1
+
+This repository contains the models from [stabilityai/stable-diffusion-2-1](https://huggingface.co/stabilityai/stable-diffusion-2-1) converted to
+OpenVINO, for accelerated inference on CPU or Intel GPU with OpenVINO's integration into Optimum:
+[optimum-intel](https://github.com/huggingface/optimum-intel#openvino). The model weights are stored with FP16
+precision, which reduces the size of the model by half.
+
+Please check out the [source model repository](https://huggingface.co/stabilityai/stable-diffusion-2-1) for more information about the model and its license.
+
+To install the requirements for this demo, do `pip install optimum[openvino]`. This installs all the necessary dependencies, 
+including Transformers and OpenVINO. For more detailed steps, please see this [installation guide](https://github.com/helena-intel/optimum-intel/wiki/OpenVINO-Integration-Installation-Guide).
+
+The simplest way to generate an image with stable diffusion takes only two lines of code, as shown below. The first line downloads the 
+model from the Hugging Face hub (if it has not been downloaded before) and loads it; the second line generates an image.
+
+```python
+from optimum.intel.openvino import OVStableDiffusionPipeline
+
+stable_diffusion = OVStableDiffusionPipeline.from_pretrained("stabilityai/stable-diffusion-2-1")
+images = stable_diffusion("a random image").images
+```
+
+The following example code uses static shapes for even faster inference. Using larger image sizes will
+require more memory and take longer to generate.
+
+If you have an 11th generation or later Intel Core processor, you can use the integrated GPU for inference, and if you have an Intel 
+discrete GPU, you can use that. Add the line `stable_diffusion.to("GPU")` before `stable_diffusion.compile()` in the example below. 
+Model loading will take some time the first time, but will be faster after that, because the model will be cached. On GPU, for stable
+diffusion only static shapes are supported at the moment.
+
+
+```python
+from optimum.intel.openvino.modeling_diffusion import OVStableDiffusionPipeline
+
+batch_size = 1
+num_images_per_prompt = 1
+height = 256
+width = 256
+
+# load the model and reshape to static shapes for faster inference
+model_id = "stabilityai/stable-diffusion-2-1"
+stable_diffusion = OVStableDiffusionPipeline.from_pretrained(model_id, compile=False)
+stable_diffusion.reshape( batch_size=batch_size, height=height, width=width, num_images_per_prompt=num_images_per_prompt)
+stable_diffusion.compile()
+
+# generate image!
+prompt = "a random image"
+images = stable_diffusion(prompt, height=height, width=width, num_images_per_prompt=num_images_per_prompt).images
+images[0].save("result.png")
+```
+

feature_extractor/preprocessor_config.json

@@ -0,0 +1,28 @@
+{
+  "crop_size": {
+    "height": 224,
+    "width": 224
+  },
+  "do_center_crop": true,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "feature_extractor_type": "CLIPFeatureExtractor",
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_processor_type": "CLIPFeatureExtractor",
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "shortest_edge": 224
+  }
+}

inference.py

@@ -0,0 +1,18 @@
+from optimum.intel.openvino.modeling_diffusion import OVStableDiffusionPipeline
+
+batch_size = 1
+num_images_per_prompt = 1
+height = 256
+width = 256
+
+# load the model and reshape to static shapes for faster inference
+model_id = "helenai/stabilityai-stable-diffusion-2-1-ov"
+stable_diffusion = OVStableDiffusionPipeline.from_pretrained(model_id, compile=False)
+stable_diffusion.reshape( batch_size=batch_size, height=height, width=width, num_images_per_prompt=num_images_per_prompt)
+stable_diffusion.compile()
+
+# generate image!
+prompt = "a random image"
+images = stable_diffusion(prompt, height=height, width=width, num_images_per_prompt=num_images_per_prompt).images
+images[0].save("result.png")
+

model_index.json

@@ -0,0 +1,33 @@
+{
+  "_class_name": "OVStableDiffusionPipeline",
+  "_diffusers_version": "0.13.1",
+  "feature_extractor": [
+    "transformers",
+    "CLIPFeatureExtractor"
+  ],
+  "requires_safety_checker": false,
+  "safety_checker": [
+    null,
+    null
+  ],
+  "scheduler": [
+    "diffusers",
+    "DDIMScheduler"
+  ],
+  "text_encoder": [
+    "optimum",
+    "OVModelTextEncoder"
+  ],
+  "tokenizer": [
+    "transformers",
+    "CLIPTokenizer"
+  ],
+  "unet": [
+    "optimum",
+    "OVModelUnet"
+  ],
+  "vae_decoder": [
+    "optimum",
+    "OVModelVaeDecoder"
+  ]
+}

scheduler/scheduler_config.json

@@ -0,0 +1,14 @@
+{
+  "_class_name": "DDIMScheduler",
+  "_diffusers_version": "0.13.1",
+  "beta_end": 0.012,
+  "beta_schedule": "scaled_linear",
+  "beta_start": 0.00085,
+  "clip_sample": false,
+  "num_train_timesteps": 1000,
+  "prediction_type": "v_prediction",
+  "set_alpha_to_one": false,
+  "skip_prk_steps": true,
+  "steps_offset": 1,
+  "trained_betas": null
+}

text_encoder/openvino_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3d5702e9aefe3f9426713201632b99005f17d77cf6f1bbfb54525a473206ffa
+size 680776428

tokenizer/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/tokenizer_config.json

@@ -0,0 +1,34 @@
+{
+  "add_prefix_space": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<|startoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "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,
+  "name_or_path": "models/stabilityai-stable-diffusion-2-1-ov/tokenizer",
+  "pad_token": "<|endoftext|>",
+  "special_tokens_map_file": "./special_tokens_map.json",
+  "tokenizer_class": "CLIPTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

unet/openvino_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d753b9848294357fe4d0b0d818ac220a3a763b291434cd6c0fc9100c77774f7b
+size 1731822168

vae_decoder/openvino_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bea41feef073b8e247dceeb0ec95d6e523a3c5acc1310882e22b6245509390d9
+size 98980700