SobeyMIL/TVG
code for "TVG: A Training-free Transition Video Generation Method with Diffusion Models"
This project helps video editors and content creators easily generate smooth, artistic transition videos between two distinct images or video frames. You provide a starting image and an ending image, and it outputs a high-quality video clip that seamlessly bridges the visual gap between them. It's designed for anyone needing professional-looking transitions without complex manual editing or specialized graphic design skills.
No commits in the last 6 months.
Use this if you need to create visually appealing and coherent transitions between different scenes or subjects in your video projects, using only an initial and final image.
Not ideal if you need to generate entirely new videos from text prompts or perform complex video editing tasks beyond creating transitions.
Stars
49
Forks
5
Language
Python
License
Apache-2.0
Category
Last pushed
Aug 19, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/SobeyMIL/TVG"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
hao-ai-lab/FastVideo
A unified inference and post-training framework for accelerated video generation.
ModelTC/LightX2V
Light Image Video Generation Inference Framework
thu-ml/TurboDiffusion
TurboDiffusion: 100–200× Acceleration for Video Diffusion Models
PKU-YuanGroup/Helios
Helios: Real Real-Time Long Video Generation Model
PKU-YuanGroup/MagicTime
[TPAMI 2025🔥] MagicTime: Time-lapse Video Generation Models as Metamorphic Simulators