i1: A Simple and Fully Open Recipe for Strong Text-to-Image Models
AI & ML interests
None defined yet.
Recent Activity
View all activity
Papers
VisionFoundry: Teaching VLMs Visual Perception with Synthetic Images
Stronger Normalization-Free Transformers
Organization Card
Open source releases from Prof. Zhuang Liu's lab at Princeton University
models 9
zlab-princeton/i1-3B
Text-to-Image • Updated • 50
zlab-princeton/Vero-Qwen35-9B-Base
Image-Text-to-Text • 9B • Updated • 24 • 1
zlab-princeton/Vero-Qwen35-9B
Image-Text-to-Text • 9B • Updated • 50 • 3
zlab-princeton/derf
Updated • 1
zlab-princeton/Vero-MiMo-7B
Image-Text-to-Text • 8B • Updated • 4 • 2
zlab-princeton/Vero-Qwen3T-8B
Image-Text-to-Text • 9B • Updated • 30 • 3
zlab-princeton/Vero-Qwen3I-8B
Image-Text-to-Text • 9B • Updated • 17 • 2
zlab-princeton/Vero-Qwen25-7B
Image-Text-to-Text • 8B • Updated • 12 • 2
zlab-princeton/SoFlow
Updated • 2
datasets 8
zlab-princeton/i1-gptedit-tfrecord
Updated • 529 • 1
zlab-princeton/i1-captions
Viewer • Updated • 167M • 4.9k • 18
zlab-princeton/Vero-2.5M-unfiltered
Viewer • Updated • 2.45M • 5.07k • 1
zlab-princeton/Vero-1.6M
Viewer • Updated • 1.61M • 4.79k • 1
zlab-princeton/WorldBench
Viewer • Updated • 2k • 280 • 7
zlab-princeton/VisionFoundry-10K
Viewer • Updated • 2 • 267 • 5
zlab-princeton/Vero-600k
Viewer • Updated • 606k • 31.8k • 36
zlab-princeton/UEval
Viewer • Updated • 1k • 145 • 5