HavenFeng/time_reversal
Official repo of "Time Reversal Fusion" (ECCV2024)
This tool helps animators, visual effects artists, and content creators generate video sequences by defining only the start and end frames. You provide two still images, and it intelligently fills in the motion or camera movement between them to create a smooth, coherent video. This is ideal for artists looking to create dynamic animations or extend short clips without manual frame-by-frame work.
No commits in the last 6 months.
Use this if you need to generate video content, such as animating a subject's movement, simulating camera motion through a static scene, or creating seamless video loops, using only two bounding images.
Not ideal if you require highly detailed control over every frame of the video or if your project demands extensive customization beyond the provided start and end frames.
Stars
49
Forks
3
Language
Python
License
—
Category
Last pushed
May 20, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/HavenFeng/time_reversal"
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...