OpenRaiser/CoW-Bench
Leaderboard for The Trinity of Consistency as a Defining Principle for General World Models
This project helps evaluate how well AI models can generate consistent and logical images and videos based on textual prompts. It takes a textual description of a desired image or video and assesses the AI's ability to maintain object identity, spatial relationships, and temporal changes accurately. Anyone working with or developing generative AI models for visual content creation, such as content creators, researchers, or AI product managers, would find this useful.
Use this if you need to rigorously test and compare different generative AI models on their ability to create visually consistent and semantically accurate images and videos.
Not ideal if you are looking for a tool to generate creative content directly or to fine-tune an existing generative AI model.
Stars
9
Forks
—
Language
HTML
License
—
Category
Last pushed
Mar 26, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/OpenRaiser/CoW-Bench"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
galilai-group/stable-worldmodel
Reliable, minimal and scalable library for evaluating and conducting world model research
NM512/dreamerv3-torch
Implementation of Dreamer v3 in pytorch.
danijar/dreamerv2
Mastering Atari with Discrete World Models
danijar/dreamerv3
Mastering Diverse Domains through World Models
leofan90/Awesome-World-Models
A comprehensive list of papers for the definition of World Models and using World Models for...