Add pipeline tag and license

README.md

@@ -1,5 +1,7 @@
 ---
 library_name: diffusers
+license: mit
+pipeline_tag: image-to-image
 ---
 
 # Paint by Inpaint: Learning to Add Image Objects by Removing Them First
@@ -12,7 +14,6 @@ We offer four different models:
 - Trained on the combined PIPE and InstructPix2Pix datasets, intended for general editing.
 - The general model fine-tuned on the full MagicBrush dataset.
 
-
 ## Resources
 
 - 💻 [**Visit Project Page**](https://rotsteinnoam.github.io/Paint-by-Inpaint/)
@@ -23,8 +24,6 @@ We offer four different models:
 
 - 🗂️ [**Use PIPE Dataset**](https://huggingface.co/datasets/paint-by-inpaint/PIPE)
 
-
-
 #### Running the model
 
 The model is simple to run using the InstructPix2Pix pipeline:
@@ -34,8 +33,12 @@ from diffusers import StableDiffusionInstructPix2PixPipeline, EulerAncestralDisc
 import torch
 import requests
 from io import BytesIO
+from PIL import Image
 
 model_name = "paint-by-inpaint/add-base"  # addition-base-model
+# model_name = "paint-by-inpaint/add-finetuned-mb"  # addition-finetuned-model
+# model_name = "paint-by-inpaint/general-base"  # general-base-model
+# model_name = "paint-by-inpaint/general-finetuned-mb"  # general-finetuned-model
 
 diffusion_steps = 50
 device = "cuda"
@@ -57,8 +60,6 @@ out_images = pipe(
 
 ```
 
-
-
 ## BibTeX
 
 ``` Citation
@@ -68,4 +69,4 @@ out_images = pipe(
   journal={arXiv preprint arXiv:2404.18212},
   year={2024}
 }
-
+```