DuNGEOnmassster/VideoGen-of-Thought
[Neurips 2025 NextVid Workshop Oral✨] Official Implementation of VideoGen-of-Thought: Step-by-step generating multi-shot video with minimal manual intervention
This project helps video creators, marketers, and storytellers automatically produce multi-shot videos from a single text description. You input a sentence describing your desired video, and it outputs a complete video with a cohesive storyline, consistent characters, and smooth transitions, saving significant manual editing time. It's designed for anyone needing to generate dynamic, narrative-driven video content quickly.
No commits in the last 6 months.
Use this if you need to generate complex, multi-scene video narratives from a simple text prompt, ensuring consistent characters and story flow without extensive manual editing.
Not ideal if you need to create very short, single-shot video clips or have highly specific, frame-by-frame control over every visual detail and character action.
Stars
60
Forks
3
Language
Python
License
BSD-3-Clause
Category
Last pushed
Sep 22, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/DuNGEOnmassster/VideoGen-of-Thought"
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