Adamdad/vico
Vico: Compositional Video Generation as Flow Equalization
This helps creative professionals, marketers, or educators generate high-quality videos from text descriptions. You provide a text prompt detailing the scene and actions, and it produces a video that accurately represents all elements in your description, avoiding any single concept from overwhelming others. This is ideal for anyone needing precise control over AI-generated video content.
No commits in the last 6 months.
Use this if you need to create videos from text prompts where every detail, character, and action you describe must be clearly and compositionally present in the final output.
Not ideal if you are looking for a simple, ready-to-use video generation app without needing to engage with code or underlying models.
Stars
59
Forks
3
Language
Python
License
—
Category
Last pushed
Nov 15, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/Adamdad/vico"
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