commit files to HF hub

README.md

@@ -0,0 +1,62 @@
+---
+license: creativeml-openrail-m
+tags:
+- stable-diffusion
+- text-to-image
+- openvino
+ 
+---
+
+# OpenVINO Stable Diffusion 
+
+## Linaqruf/anything-v3.0
+
+This repository contains the models from [Linaqruf/anything-v3.0](https://huggingface.co/Linaqruf/anything-v3.0) 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/Linaqruf/anything-v3.0) 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("Linaqruf/anything-v3.0")
+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 = "Linaqruf/anything-v3.0"
+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")
+```
+

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/Linaqruf-anything-v3.0-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": [
+    null,
+    null
+  ],
+  "requires_safety_checker": null,
+  "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": "epsilon",
+  "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:e606971d7d658486d91db450fbf4b9f75c2cf90bfe40d4d0f9c03bbb8eff2989
+size 246121704

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": "<|endoftext|>",
+  "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/Linaqruf-anything-v3.0-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 sha256:5661b566572e6ac6c434ac81e28ffb6c546f0d145b1fe4c8ff1ce168087746ad
+size 1719042636

vae_decoder/openvino_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea381262fba41515ad43fbe4c1d9459b9b4f397b14418b82a99365d68cd4ab4b
+size 98980700