Pipeline Builder - Compose AI Models by File Type | Mixpeek

NEWYour agents can now see video. Connect Mixpeek via MCP in one command.Agents can now see video via MCP.Try it now →

Product Pricing Documentation

Sign in Request Demo

Pipeline Builder

Tasks

Modality

View all models →

Browse models and drag them into your pipeline

All Models

37 models

HFText Embeddings

sentence-transformers/all-MiniLM-L6-v2

1024-dim vector↓ 195.7M

HFVisual Embeddings

openai/clip-vit-large-patch14

768-dim vector↓ 28.6M

HFAudio Embeddings

laion/clap-htsat-fused

512-dim vector↓ 20.7M

HFSpeaker Diarization

pyannote/speaker-diarization-3.1

speaker segments↓ 10.9M

HFText Embeddings

BAAI/bge-large-en-v1.5

1024-dim vector↓ 7.1M

HFTranscription

openai/whisper-large-v3

text + timestamps↓ 4.7M

HFSegmentation

facebook/sam-vit-huge

mask + label↓ 3.2M

HFTable Extraction

microsoft/table-transformer-detection

table JSON↓ 3.0M

HFVisual Embeddings

facebook/dinov2-large

768-dim vector↓ 2.8M

HFSegmentation

facebook/sam2.1-hiera-large

mask + label↓ 1.8M

HFObject Detection

IDEA-Research/grounding-dino-base

bbox + label↓ 1.5M

HFScene Captioning

microsoft/Florence-2-large

text↓ 1.3M

HFVisual Embeddings

google/siglip-base-patch16-224

768-dim vector↓ 1.2M

HFVisual Embeddings

google/siglip2-giant-opt-patch16-384

768-dim vector↓ 1.2M

HFVisual Embeddings

laion/CLIP-ViT-bigG-14-laion2B-39B-b160k

768-dim vector↓ 890K

HFObject Detection

google/owlvit-large-patch14

bbox + label↓ 580K

HFDocument Structure

microsoft/layoutlmv3-base

structure tokens↓ 565K

HFOCR

microsoft/trocr-large-printed

text + bbox↓ 554K

HFScene Captioning

Salesforce/blip2-opt-2.7b

text↓ 516K

PyTorchVisual Embeddings

facebook/dinov3-large

768-dim vector↓ 450K

PyTorchSegmentation

facebook/sam3

mask + label↓ 420K

PyTorchObject Detection

AILab-CVC/YOLO-World-L

bbox + label↓ 320K

HFCode Extraction

microsoft/codebert-base

code + language↓ 261K

HFObject Detection

facebook/detr-resnet-50

bbox + label↓ 246K

HFDocument Structure

naver-clova-ix/donut-base

structure tokens↓ 216K

PyTorchAnomaly Detection

amazon/patchcore-resnet50

anomaly score + map↓ 180K

HFCode Extraction

Salesforce/codet5p-110m-embedding

code + language↓ 154K

HFAudio Embeddings

facebook/encodec_24khz

512-dim vector↓ 112K

HFObject Detection

hustvl/yolos-tiny

bbox + label↓ 107K

HFTranscription

facebook/wav2vec2-large-960h

text + timestamps↓ 37K

C++/PythonVector Indexing

facebook/faiss

index + results↓ 39.5K★

PyTorchObject Detection

ultralytics/yolov8n

bbox + label↓ —

HFFace Detection

deepinsight/retinaface-r50

face embedding↓ —

HFFace Detection

timesformer/facenet-pytorch

face embedding↓ —

PyTorchOCR

PaddlePaddle/paddleocr

text + bbox↓ —

PyTorchSegmentation

netflix/void-model

mask + label↓ —

C++/PythonVector Indexing

google/scann

index + results↓ -

DECOMPOSE

0 extractors

Drag models here