AI Model Hub

Browse AI models for multimodal decomposition and recomposition pipelines — plug any model into your extractors.

12,807 models available

Start free Schedule Demo Read Documentation

Showing 2761–2784 of 12,807 models

Image Classification

timm/tf_efficientnet_b3.ns_jft_in1k

37K

timm

View Details

Fill Mask

mikemayuare/SELFYAPE

37K

transformers

View Details

Object Detection

foduucom/stockmarket-pattern-detection-yolov8

37K

408

ultralytics

View Details

Text To Image

RunDiffusion/Juggernaut-XI-v11

37K

123

diffusers

View Details

Image Feature Extraction

prov-gigapath/prov-gigapath

37K

176

timm

View Details

Image Text To Text

unsloth/Qwen3-VL-8B-Instruct-unsloth-bnb-4bit

37K

View Details

Fill Mask

neulab/codebert-python

37K

transformers

View Details

Audio Classification

aufklarer/Qwen3-ForcedAligner-0.6B-4bit

37K

mlx

View Details

Image Classification

timm/resnet50d.ra2_in1k

37K

timm

View Details

Feature Extraction

ibm-granite/granite-embedding-english-r2

36K

sentence-transformers

View Details

Image Segmentation

facebook/mask2former-swin-large-mapillary-vistas-panoptic

36K

transformers

View Details

Image Classification

facebook/convnextv2-tiny-22k-384

36K

transformers

View Details

Image Classification

timm/maxvit_nano_rw_256.sw_in1k

36K

timm

View Details

Feature Extraction

farbodtavakkoli/OTel-Embedding-33M

36K

View Details

Text Classification

protectai/xlm-roberta-base-language-detection-onnx

36K

transformers

View Details

Robotics

lerobot/smolvla_base

36K

391

lerobot

View Details

Image To Image

Runware/BFL-FLUX.2-klein-4B

36K

diffusers

View Details

Automatic Speech Recognition

TBOGamer22/wav2vec2-quran-phonetics

36K

transformers

View Details

Image Classification

timm/convnext_tiny.in12k

36K

timm

View Details

Text Classification

seara/rubert-tiny2-russian-sentiment

36K

transformers

View Details

Any To Any

nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-FP8

36K

transformers

View Details

Feature Extraction

farbodtavakkoli/OTel-Embedding-34M

36K

View Details

Text To Speech

canopylabs/orpheus-3b-0.1-ft

36K

696

transformers

View Details

Text To Image

dataautogpt3/ProteusV0.3

36K

diffusers

View Details

......

116 / 534

Connectors

Retrievers