Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
wusize
/
Harmon-1_5B
like
2
Text-to-Image
Safetensors
English
vision
image-to-text
multimodal
custom_code
arxiv:
2503.21979
Model card
Files
Files and versions
xet
Community
main
Harmon-1_5B
/
LICENSE
Commit History
Upload LICENSE
eed7604
verified
wusize
commited on
Mar 31
wusize
commited on
