versatile-diffusion

shi-labs/versatile-diffusion

Text to ImagediffusersLicense: mit
Tracked by OpenModelStats since September 27, 2026View on Hugging Face ↗
Downloads 30D
1,409
Total downloads
146.7K
Gained 7D
+155(increase)
0.1%(up) vs baseline
Gained 30D
—
Likes
48
+0 in 7D
Rank · tracked models
#27,245
7247(down 7247 places)this week
Parameters
—
Last source update
Mar 27, 2023
Momentum
32.6
  • versatile-diffusion gained 155 downloads during the last seven tracked days.
  • It moved from #664 to #852 among tracked Text to Image models this week.

Downloads over time

Cumulative total downloads observed by OpenModelStats

Likes over time

Rank among tracked models

Lower is better

Overview

versatile-diffusion is a text to image model published by shi-labs. OpenModelStats has tracked the model since Sep 27, 2026, most recently observing it Oct 4, 2026.

Published
Nov 22, 2022
Last updated
Mar 27, 2023
Library
diffusers
License
mit
Task
Text to Image
Parameters
—
Spaces
—
Derivative models
—
Velocity 7D/day
22
diffusersimage-to-textimage-to-imagetext-to-imagetext-to-textimage-editingimage-variationgenerationvisiondataset:Laion2B-enarxiv:2211.08332license:mit

Similar models

Models similar to versatile-diffusion
ModelDL 30D
stable-diffusion-xl-base-1.0stabilityai4.3M
stable-diffusion-v1-5stable-diffusion-v1-51.6M
Qwen-Image-2.1-Uncensored-GGUFabenzerps1.6M
sdxl-turbostabilityai965.6K
dreamshaper-7Lykon883.5K
Z-Image-Turbo-GGUFunsloth720.9K
shi-labs/versatile-diffusion — Downloads, Growth & Stats | OpenModelStats