EfficientNet V2 ImageNet-21k B2 is Google's image to text model. An EfficientNet V2 B2 image classification model pretrained on ImageNet-21k, combining compound scaling with broad category coverage for versatile transfer learning.
Specifications
Canonical IDgoogle-efficientnet-2-imagenet21k-b2
TypeImage to Text
StatusActive
CreatorGoogleGoogle
Input ModalitiesImage
Output ModalitiesText

Capabilities

Input1/5
Text·
Image
Audio·
Video·
PDF·
Output1/5
Text
Image·
Audio·
Video·
Embedding·
Capabilities0/13
Reasoning·
Adaptive Reasoning·
Function Calling·
Parallel Function Calling·
Structured Outputs·
Native JSON Schema·
Web Search·
URL Context·
Computer Use·
Code Execution·
File Search·
Prompt Caching·
Assistant Prefill·

Versions

VersionReleasedContextInput / 1MOutput / 1MStatus
EfficientNet V2 ImageNet-21k B2Current
EfficientNet V2 ImageNet-1k B0Available
EfficientNet V2 ImageNet-1k B1Available
EfficientNet V2 ImageNet-1k B2Available
EfficientNet V2 ImageNet-1k B3Available
EfficientNet V2 ImageNet-1k LargeAvailable
EfficientNet V2 ImageNet-1k MediumAvailable
EfficientNet V2 ImageNet-21k B0Available
EfficientNet V2 ImageNet-21k B1Available
EfficientNet V2 ImageNet-21k B3Available
EfficientNet V2 ImageNet-21k FT1k B0Available

Model IDs