MSALab commited on
Commit
3d1ae71
Β·
verified Β·
1 Parent(s): 13a77b0

Update README

Browse files
Files changed (1) hide show
  1. README.md +59 -52
README.md CHANGED
@@ -1,14 +1,30 @@
1
- <div align="center">
 
 
 
 
 
 
 
 
 
 
 
 
2
 
3
- # LoomVideo: Unifying Multimodal Inputs into <br> Video Generation and Editing
4
-
5
- <h3>Peking University &middot; Alibaba Group</h3>
6
 
7
- <a href="TODO" target="_blank"><img src="https://img.shields.io/badge/Paper-b5212f.svg?logo=arxiv" height="22px"></a>
8
- <a href="https://github.com/MSALab-PKU/LoomVideo" target="_blank"><img src="https://img.shields.io/badge/GitHub-bb8a2e.svg?logo=github" height="22px"></a>
9
- <a href="https://msalab-pku.github.io/projects/LoomVideo/index.html" target="_blank"><img src="https://img.shields.io/badge/Project%20Page-333399.svg?logo=homepage" height="22px"></a>
10
 
11
- </div>
 
 
 
 
12
 
13
  # πŸ”₯ News
14
 
@@ -58,69 +74,60 @@ LoomVideo supports **four** unified video generation and editing tasks within a
58
 
59
  ### βœ‚οΈ Instruction Editing
60
 
61
- <table align="center">
62
- <tr>
63
- <td align="center" valign="middle"><img src="assets/results_1/edit_input.gif" height="180"/></td>
64
- <td align="center" valign="middle"><b><font size="5">β†’</font></b></td>
65
- <td align="center" valign="middle"><img src="assets/results_1/edit_demo.gif" height="180"/></td>
66
- </tr>
67
- </table>
68
 
69
  > **Prompt:** *Apply the Impressionist aesthetic to this video, ensuring seamless temporal consistency across all frames. The result should emulate the fluid brushstroke techniques and atmospheric focus of 19th-century Impressionist art, with each frame retaining the original motion, character actions, and camera movements.*
70
 
71
- <table align="center">
72
- <tr>
73
- <td align="center" valign="middle"><img src="assets/results_2/edit_input.gif" height="180"/></td>
74
- <td align="center" valign="middle"><b><font size="5">β†’</font></b></td>
75
- <td align="center" valign="middle"><img src="assets/results_2/edit_demo.gif" height="180"/></td>
76
- </tr>
77
- </table>
78
 
79
  > **Prompt:** *Replace the tree with a golden-leaved tree that shimmers softly, ensuring it maintains the same position and pose within the video scene.*
80
 
81
  ### πŸ–ΌοΈ Instruction-Image Editing
82
 
83
- <table align="center">
84
- <tr>
85
- <td align="center" valign="middle"><img src="assets/results_1/ref_edit_input.gif" height="180"/></td>
86
- <td align="center" valign="middle"><img src="assets/results_1/ref_edit_reference.jpg" height="100"/></td>
87
- <td align="center" valign="middle"><b><font size="5">β†’</font></b></td>
88
- <td align="center" valign="middle"><img src="assets/results_1/ref_edit_demo.gif" height="180"/></td>
89
- </tr>
90
- </table>
91
 
92
  > **Prompt:** *Replace the green t-shirt of the man with the suit in the image.*
93
 
94
- <table align="center">
95
- <tr>
96
- <td align="center" valign="middle"><img src="assets/results_2/ref_edit_input.gif" height="180"/></td>
97
- <td align="center" valign="middle"><img src="assets/results_2/ref_edit_reference.jpg" height="100"/></td>
98
- <td align="center" valign="middle"><b><font size="5">β†’</font></b></td>
99
- <td align="center" valign="middle"><img src="assets/results_2/ref_edit_demo.gif" height="180"/></td>
100
- </tr>
101
- </table>
102
 
103
  > **Prompt:** *Replace the background with a Chinese ink painting, featuring a large golden mountain peak rising above swirling clouds, ensuring it appears in the same position and pose within the video scene.*
104
 
105
  ### 🎞️ Multi-Image-to-Video
106
 
107
- <table align="center">
108
- <tr>
109
- <td align="center" valign="middle"><img src="assets/results_1/mi2v_input_1.jpg" height="140"/> <img src="assets/results_1/mi2v_input_2.jpg" height="140"/> <img src="assets/results_1/mi2v_input_3.jpg" height="140"/></td>
110
- <td align="center" valign="middle"><b><font size="5">β†’</font></b></td>
111
- <td align="center" valign="middle"><img src="assets/results_1/mi2v_demo.gif" height="180"/></td>
112
- </tr>
113
- </table>
114
 
115
  > **Prompt:** *The girl (@Image 2), wearing the denim jacket (@Image 3), black inner top, and black shorts, wearing sunglasses and carrying the handbag, walks down the street (@Image 1). Then, the girl (@Image 2) stops walking and turns her head to look to one side, followed by the girl (@Image 2) crossing her arms over her chest and striking a confident pose.*
116
 
117
- <table align="center">
118
- <tr>
119
- <td align="center" valign="middle"><img src="assets/results_2/mi2v_input_1.jpg" height="140"/> <img src="assets/results_2/mi2v_input_2.jpg" height="140"/></td>
120
- <td align="center" valign="middle"><b><font size="5">β†’</font></b></td>
121
- <td align="center" valign="middle"><img src="assets/results_2/mi2v_demo.gif" height="180"/></td>
122
- </tr>
123
- </table>
124
 
125
  > **Prompt:** *The man wearing a Polo shirt (@Image 2), black casual pants, white sneakers, sunglasses, and a watch, striding forward on the lawn (@Image 1) with one hand in his pocket.*
126
 
 
1
+ ---
2
+ license: apache-2.0
3
+ language:
4
+ - en
5
+ tags:
6
+ - video-generation
7
+ - video-editing
8
+ - multi-modal
9
+ - diffusion
10
+ base_model:
11
+ - Qwen/Qwen3-VL-8B-Instruct
12
+ - Wan-AI/Wan2.2-TI2V-5B
13
+ ---
14
 
15
+ <p align="center">
16
+ <b style="font-size:1.8em;">LoomVideo: Unifying Multimodal Inputs into<br>Video Generation and Editing</b>
17
+ </p>
18
 
19
+ <p align="center">
20
+ <b>Peking University &middot; Alibaba Group</b>
21
+ </p>
22
 
23
+ <p align="center">
24
+ <a href="TODO" target="_blank"><img src="https://img.shields.io/badge/Paper-b5212f.svg?logo=arxiv" height="22px"></a>
25
+ <a href="https://github.com/MSALab-PKU/LoomVideo" target="_blank"><img src="https://img.shields.io/badge/GitHub-bb8a2e.svg?logo=github" height="22px"></a>
26
+ <a href="https://msalab-pku.github.io/projects/LoomVideo/index.html" target="_blank"><img src="https://img.shields.io/badge/Project%20Page-333399.svg?logo=homepage" height="22px"></a>
27
+ </p>
28
 
29
  # πŸ”₯ News
30
 
 
74
 
75
  ### βœ‚οΈ Instruction Editing
76
 
77
+ <p align="center">
78
+ <img src="assets/results_1/edit_input.gif" height="180"/>
79
+ <b> &nbsp; β†’ &nbsp; </b>
80
+ <img src="assets/results_1/edit_demo.gif" height="180"/>
81
+ </p>
 
 
82
 
83
  > **Prompt:** *Apply the Impressionist aesthetic to this video, ensuring seamless temporal consistency across all frames. The result should emulate the fluid brushstroke techniques and atmospheric focus of 19th-century Impressionist art, with each frame retaining the original motion, character actions, and camera movements.*
84
 
85
+ <p align="center">
86
+ <img src="assets/results_2/edit_input.gif" height="180"/>
87
+ <b> &nbsp; β†’ &nbsp; </b>
88
+ <img src="assets/results_2/edit_demo.gif" height="180"/>
89
+ </p>
 
 
90
 
91
  > **Prompt:** *Replace the tree with a golden-leaved tree that shimmers softly, ensuring it maintains the same position and pose within the video scene.*
92
 
93
  ### πŸ–ΌοΈ Instruction-Image Editing
94
 
95
+ <p align="center">
96
+ <img src="assets/results_1/ref_edit_input.gif" height="180"/>
97
+ <img src="assets/results_1/ref_edit_reference.jpg" height="100"/>
98
+ <b> &nbsp; β†’ &nbsp; </b>
99
+ <img src="assets/results_1/ref_edit_demo.gif" height="180"/>
100
+ </p>
 
 
101
 
102
  > **Prompt:** *Replace the green t-shirt of the man with the suit in the image.*
103
 
104
+ <p align="center">
105
+ <img src="assets/results_2/ref_edit_input.gif" height="180"/>
106
+ <img src="assets/results_2/ref_edit_reference.jpg" height="100"/>
107
+ <b> &nbsp; β†’ &nbsp; </b>
108
+ <img src="assets/results_2/ref_edit_demo.gif" height="180"/>
109
+ </p>
 
 
110
 
111
  > **Prompt:** *Replace the background with a Chinese ink painting, featuring a large golden mountain peak rising above swirling clouds, ensuring it appears in the same position and pose within the video scene.*
112
 
113
  ### 🎞️ Multi-Image-to-Video
114
 
115
+ <p align="center">
116
+ <img src="assets/results_1/mi2v_input_1.jpg" height="140"/>
117
+ <img src="assets/results_1/mi2v_input_2.jpg" height="140"/>
118
+ <img src="assets/results_1/mi2v_input_3.jpg" height="140"/>
119
+ <b> &nbsp; β†’ &nbsp; </b>
120
+ <img src="assets/results_1/mi2v_demo.gif" height="180"/>
121
+ </p>
122
 
123
  > **Prompt:** *The girl (@Image 2), wearing the denim jacket (@Image 3), black inner top, and black shorts, wearing sunglasses and carrying the handbag, walks down the street (@Image 1). Then, the girl (@Image 2) stops walking and turns her head to look to one side, followed by the girl (@Image 2) crossing her arms over her chest and striking a confident pose.*
124
 
125
+ <p align="center">
126
+ <img src="assets/results_2/mi2v_input_1.jpg" height="140"/>
127
+ <img src="assets/results_2/mi2v_input_2.jpg" height="140"/>
128
+ <b> &nbsp; β†’ &nbsp; </b>
129
+ <img src="assets/results_2/mi2v_demo.gif" height="180"/>
130
+ </p>
 
131
 
132
  > **Prompt:** *The man wearing a Polo shirt (@Image 2), black casual pants, white sneakers, sunglasses, and a watch, striding forward on the lawn (@Image 1) with one hand in his pocket.*
133