snap-research/SF-V
This respository contains the code for the NeurIPS 2024 paper SF-V: Single Forward Video Generation Model.
This project helps video creators, animators, and digital artists generate realistic, high-quality videos from text descriptions or existing images. It takes your prompt or input image and quickly produces a smooth, motion-consistent video, dramatically speeding up the creative process. You'll use this if you need to rapidly prototype video concepts or produce visual content efficiently.
No commits in the last 6 months.
Use this if you need to generate high-quality, motion-consistent videos quickly, especially when iterating on creative ideas or producing content under tight deadlines.
Not ideal if you require extremely fine-grained, frame-by-frame control over every aspect of the video generation process, as it focuses on speed and overall quality rather than detailed manual editing.
Stars
99
Forks
4
Language
—
License
—
Category
Last pushed
Nov 27, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/snap-research/SF-V"
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