Add library_name tag, link to paper and project page

README.md

@@ -1,16 +1,22 @@
 ---
-thumbnail: "https://repository-images.githubusercontent.com/523487884/fdb03a69-8353-4387-b5fc-0d85f888a63f"
 datasets:
 - ChristophSchuhmann/improved_aesthetics_6plus
 license: creativeml-openrail-m
+library_name: diffusers
+pipeline_tag: image-to-image
 tags:
 - stable-diffusion
 - stable-diffusion-diffusers
 - image-to-image
+thumbnail: https://repository-images.githubusercontent.com/523487884/fdb03a69-8353-4387-b5fc-0d85f888a63f
 ---
 
 # Stable Diffusion Image Variations Model Card
 
+Model based on [Aligned Novel View Image and Geometry Synthesis via Cross-modal Attention Instillation](https://huggingface.co/papers/2506.11924)
+
+Project page: https://cvlab-kaist.github.io/MoAI/
+
 📣 V2 model released, and blurriness issues fixed! 📣
 
 🧨🎉 Image Variations is now natively supported in 🤗 Diffusers! 🎉🧨
@@ -33,6 +39,7 @@ Make sure you are using a version of Diffusers >=0.8.0 (for older version see th
 ```python
 from diffusers import StableDiffusionImageVariationPipeline
 from PIL import Image
+from torchvision import transforms
 
 device = "cuda:0"
 sd_pipe = StableDiffusionImageVariationPipeline.from_pretrained(
@@ -185,7 +192,7 @@ If you are using a diffusers version <0.8.0 there is no `StableDiffusionImageVar
 in this case you need to use an older revision (`2ddbd90b14bc5892c19925b15185e561bc8e5d0a`) in conjunction with the lambda-diffusers repo:
 
 
-First clone [Lambda Diffusers](https://github.com/LambdaLabsML/lambda-diffusers) and install any requirements (in a virtual environment in the example below):
+First clone [Lambda Diffusers](https://github.com/LambdaLabsML/lambda-diffusers) and install any requirements (in a virtual environment in the example below):\
 
 ```bash
 git clone https://github.com/LambdaLabsML/lambda-diffusers.git
@@ -202,6 +209,7 @@ from pathlib import Path
 from lambda_diffusers import StableDiffusionImageEmbedPipeline
 from PIL import Image
 import torch
+from torchvision import transforms
 
 device = "cuda" if torch.cuda.is_available() else "cpu"
 pipe = StableDiffusionImageEmbedPipeline.from_pretrained(