feat: Updated Usage

README.md

@@ -195,33 +195,64 @@ This repo is contains ONNX checkpoints version of the model.
 - **License**: [Fair AI Public License 1.0-SD](https://freedevproject.org/faipl-1.0-sd/)
 - **Fine-tuned from**: [Animagine XL 3.0](https://huggingface.co/cagliostrolab/animagine-xl-3.0)
 
-## Gradio & Colab Integration
+## Jupyter Notebooks
 
-Try the demo powered by Gradio in Huggingface Spaces: [![Open In Spaces](https://img.shields.io/badge/🤗-Open%20In%20Spaces-blue.svg)](https://huggingface.co/spaces/cagliostrolab/animagine-xl-3.1)
+**Note**: Both Colab and Sagemaker Studio Lab does not have enough VRAM or RAM to run the inference.
 
-Or open the demo in Google Colab: [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/#fileId=https%3A//huggingface.co/spaces/cagliostrolab/animagine-xl-3.1/blob/main/demo.ipynb)
+Open the demo in Kaggle: [![Open In Kaggle](https://kaggle.com/static/images/open-in-kaggle.svg)](https://www.kaggle.com/code/ecyht2/animagine-xl-onnx-demo)
+
+Open the demo in Google Colab: [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/#fileId=https%3A//storage.googleapis.com/kaggle-colab-exported-notebooks/animagine-xl-onnx-demo-d5438574-4c5e-4a6b-8a1b-46c111a13e4d.ipynb%3FX-Goog-Algorithm%3DGOOG4-RSA-SHA256%26X-Goog-Credential%3Dgcp-kaggle-com%2540kaggle-161607.iam.gserviceaccount.com/20240413/auto/storage/goog4_request%26X-Goog-Date%3D20240413T140328Z%26X-Goog-Expires%3D259200%26X-Goog-SignedHeaders%3Dhost%26X-Goog-Signature%3D6262d18ddace3586153ef4f84b7b5486a7f868e3f2e32732510f4c3f0f470f1b544a6c7a9d839dac3ed9e9697bf8f0830821c30df76d66d06ac779554c30b814629b4d077acdb278e610b887c5ea443e2dd362fb52f796da876ffba8fc9de9e720aab0e1833cfb7dca9cc557c282a7aef8a2f21b174351cfb9a79ae0dd1b9ac24fca9d7854d4e45929fe31c861ee9a017d4dc9d859420493d897ff7ecb44b703013df1f7dd2699bb735ec5e2fd4838b12cd77ce68474772508f1e025b1e0037aea29fe0e9d79e1fb9d531933fc1c75c57d00f3d0cf3eb15851b7704be53116511d420d73e0d24e7d74f8f7df59a52c2614bd6cc915d2250c7b64e714dab6f8d5)
 
 ## 🧨 Diffusers Installation
 
+### CPU Inference
+
 First install the required libraries:
 
 ```bash
-pip install diffusers transformers accelerate safetensors --upgrade
+pip install iffusers "optimum[onnxruntime]" --upgrade
 ```
 
 Then run image generation with the following example code:
 
 ```python
-import torch
-from diffusers import DiffusionPipeline
-
-pipe = DiffusionPipeline.from_pretrained(
-    "Asahina2K/Animagine-xl-3.1-diffuser-variant-fp16", 
-    torch_dtype=torch.float16, 
-    use_safetensors=True,
-    variant="fp16"
-)
-pipe.to('cuda')
+from optimum.onnxruntime import ORTStableDiffusionXLPipeline
+
+base = "ecyht2/animagine-xl-3.1-onnx"
+pipe = ORTStableDiffusionXLPipeline.from_pretrained(base)
+pipe.to("cpu")
+
+prompt = "1girl, souryuu asuka langley, neon genesis evangelion, solo, upper body, v, smile, looking at viewer, outdoors, night"
+negative_prompt = "nsfw, lowres, (bad), text, error, fewer, extra, missing, worst quality, jpeg artifacts, low quality, watermark, unfinished, displeasing, oldest, early, chromatic aberration, signature, extra digits, artistic error, username, scan, [abstract]"
+
+image = pipe(
+    prompt, 
+    negative_prompt=negative_prompt,
+    width=832,
+    height=1216, 
+    guidance_scale=7,
+    num_inference_steps=28
+).images[0]
+
+image.save("./output/asuka_test.png")
+```
+
+### GPU Inference
+
+First install the required libraries:
+
+```bash
+pip install iffusers "optimum[onnxruntime-gpu]" --upgrade
+```
+
+Then run image generation with the following example code:
+
+```python
+from optimum.onnxruntime import ORTStableDiffusionXLPipeline
+
+base = "ecyht2/animagine-xl-3.1-onnx"
+pipe = ORTStableDiffusionXLPipeline.from_pretrained(base)
+pipe.to("cuda")
 
 prompt = "1girl, souryuu asuka langley, neon genesis evangelion, solo, upper body, v, smile, looking at viewer, outdoors, night"
 negative_prompt = "nsfw, lowres, (bad), text, error, fewer, extra, missing, worst quality, jpeg artifacts, low quality, watermark, unfinished, displeasing, oldest, early, chromatic aberration, signature, extra digits, artistic error, username, scan, [abstract]"