XiangpengYang commited on
Commit
766ff88
·
1 Parent(s): 883a96e
Files changed (1) hide show
  1. README.md +2 -2
README.md CHANGED
@@ -54,8 +54,8 @@ authors:
54
  **VideoCoF** is a unified video editing model that bridges the gap between expert models (precise but restricted) and unified in-context models (flexible but spatially inaccurate). By introducing a **"See → Reason → Edit"**, a Chain-of-Frames paradigm, VideoCoF predicts reasoning tokens before generating the target video tokens, thereby removing the need for user-provided masks while achieving precise instruction to-region alignment.
55
 
56
  <div align="center">
57
- <a href="https://www.youtube.com/watch?v=3iNUH1Dq9-0" target="_blank">
58
- <img src="https://img.youtube.com/vi/3iNUH1Dq9-0/maxresdefault.jpg"
59
  alt="Video Demo"
60
  width="80%"
61
  style="max-width:900px; border-radius:10px; box-shadow:0 0 10px rgba(0,0,0,0.15);">
 
54
  **VideoCoF** is a unified video editing model that bridges the gap between expert models (precise but restricted) and unified in-context models (flexible but spatially inaccurate). By introducing a **"See &rarr; Reason &rarr; Edit"**, a Chain-of-Frames paradigm, VideoCoF predicts reasoning tokens before generating the target video tokens, thereby removing the need for user-provided masks while achieving precise instruction to-region alignment.
55
 
56
  <div align="center">
57
+ <a href="https://www.youtube.com/watch?v=XrYj0Qmc49w" target="_blank">
58
+ <img src="https://img.youtube.com/vi/XrYj0Qmc49w/maxresdefault.jpg"
59
  alt="Video Demo"
60
  width="80%"
61
  style="max-width:900px; border-radius:10px; box-shadow:0 0 10px rgba(0,0,0,0.15);">