Merge branch 'main' of https://huggingface.co/spaces/LiruiZhao/Diffree into main

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+video_demo.mp4 filter=lfs diff=lfs merge=lfs -text

README.md

@@ -10,4 +10,25 @@ pinned: false
 license: mit
 ---
 
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+# Diffree
+
+<p align="center">
+  <a href="https://arxiv.org/pdf/2407.16982"><u>[📜 Arxiv]</u></a>
+  &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;
+  <a href="https://github.com/OpenGVLab/Diffree"><u>[🔍 Code]</u></a>
+</p>
+
+[Diffree](https://arxiv.org/pdf/2407.16982) is a diffusion model that enables the addition of new objects to images using only text descriptions, seamlessly integrating them with consistent background and spatial context.
+
+In this repo, we provide the [🤗 Hugging Face demo](https://huggingface.co/spaces/LiruiZhao/Diffree) for Diffree, and you can also download our model via [🤗 Checkpoint](https://huggingface.co/LiruiZhao/Diffree).
+
+## Citation
+If you found this work useful, please consider citing:
+```
+@article{zhao2024diffree,
+  title={Diffree: Text-Guided Shape Free Object Inpainting with Diffusion Model},
+  author={Zhao, Lirui and Yang, Tianshuo and Shao, Wenqi and Zhang, Yuxin and Qiao, Yu and Luo, Ping and Zhang, Kaipeng and Ji, Rongrong},
+  journal={arXiv preprint arXiv:2407.16982},
+  year={2024}
+}
+```

app.py

@@ -1,5 +1,6 @@
 from __future__ import annotations
 
+import spaces
 import math
 import random
 import sys
@@ -18,7 +19,6 @@ from PIL import Image, ImageOps, ImageFilter
 from torch import autocast
 import cv2
 import imageio
-import spaces
 
 sys.path.append("./stable_diffusion")
 
@@ -351,7 +351,7 @@ with gr.Blocks(css="footer {visibility: hidden}") as demo:
                 ["Show Image Video", "Close Image Video"],
                 value="Close Image Video",
                 type="index",
-                label="Image Generation Process Selection ()",
+                label="Image Generation Process Selection (close for faster generation)",
                 interactive=True,
             )
             decode_image_batch = gr.Number(value=10, precision=0, label="Decode Image Batch (<steps)", interactive=True)

video_demo.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4f71dce37b7e62ad467ec5d24004e8714be7e76bf634cd610c1935b03501ca6
+size 32058066