ZonglinL/TLBVFI
ICCV 2025
This project helps videographers, editors, and animators make videos appear smoother or slower by adding new, natural-looking frames between existing ones. You provide two consecutive video frames, and it generates realistic intermediate frames, effectively increasing the frame rate or extending the duration of a scene. The end user is anyone working with video who needs to create fluid motion where original footage might be lacking frames.
No commits in the last 6 months.
Use this if you need to increase the frame rate of video footage or slow down a clip smoothly, generating highly realistic frames to bridge gaps in motion.
Not ideal if you're looking for a simple, off-the-shelf application; this project requires some technical setup and command-line execution.
Stars
33
Forks
1
Language
Python
License
—
Category
Last pushed
Oct 03, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/ZonglinL/TLBVFI"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
PRIS-CV/DemoFusion
Let us democratise high-resolution generation! (CVPR 2024)
mit-han-lab/distrifuser
[CVPR 2024 Highlight] DistriFusion: Distributed Parallel Inference for High-Resolution Diffusion Models
Tencent-Hunyuan/HunyuanPortrait
[CVPR-2025] The official code of HunyuanPortrait: Implicit Condition Control for Enhanced...
giuvecchio/matfuse
MatFuse: Controllable Material Generation with Diffusion Models (CVPR2024)
Shilin-LU/TF-ICON
[ICCV 2023] "TF-ICON: Diffusion-Based Training-Free Cross-Domain Image Composition" (Official...