Explore Predictors
@roboflow/rf-detr
Detect objects in an image with RF-DETR.
@megvii/yolox-nano
Detect objects in an image with YOLOX (nano).
@kitten-ml/kitten-tts
Perform text-to-speech with Kitten TTS.
@google/embedding-gemma
Create embedding vectors from text with EmbeddingGemma.
@baidu/rt-detr
Detect objects in an image with RT-DETR.
@cuhk/modnet
Remove the background from a person's image with ModNet.
@pytorch/wide-resnet-101
Classify an image with Wide ResNet-101.
Classify an image with Vision Transformer (base/32).
Classify an image with VGG-19.
Classify an image with Swin Transformer V2 (tiny).
Classify an image with SqueezeNet 1.1.
Classify an image with ShuffleNet V2 (2.0x).
Classify an image with ResNeXt-101 (32x8d).
Classify an image with RegNet-Y (8GF).
Classify an image with RegNet-X (16GF).
Classify an image with MobileNet V3 (Large)
Classify an image with Mobile Neural Architecture Search (MnasNet) at depth 1.0.
Classify an image with Multi-Axis Vision Transformer (MaxViT-tiny).
Classify an image using Inception V3.
Classify an image using GoogLeNet.
Classify an image with AlexNet.
Image classification entirely using standard ConvNet modules.
@apple/depth-pro
Sharp monocular metric depth in less than a second.
Classify an image with ResNet 50.
Image classifier trained on ImageNet 1k.
@nomic/nomic-embed-text-v1.5-quant
Resizable production embeddings with Matryoshka representation learning.
@natml/movenet-multipose
Realtime pose detection from a single image.
@fxn/greeting
Say a friendly greeting!