Download the PHP package b7s/fluentvision without Composer
On this page you can find all versions of the php package b7s/fluentvision. It is possible to download/install these versions without Composer. Possible dependencies are resolved automatically.
Download b7s/fluentvision
More information about b7s/fluentvision
Files in b7s/fluentvision
Package fluentvision
Short Description A fluent PHP API for YOLO object detection powered by Ultralytics YOLO26 and NanoDet - detect, segment, classify, and annotate images with an elegant chainable interface
License MIT
Informations about the package fluentvision
FluentVision
A fluent PHP 8.3+ API for YOLO object detection powered by Ultralytics YOLO26 and NanoDet-Plus.
Detect, segment, classify, and annotate images with an elegant chainable interface — same PHP result types regardless of which backend runs inference.
Quick Start
Installation
First, install Python dependencies and download models:
The local user running your system must be the same user who will be using FluentVision.
Try something like this:
This will create the environment in the user's "www" folder: /home/www/.fluentvision.
Check your environment:
Providers
| Provider | Backend | Best For |
|---|---|---|
| Ultralytics | YOLO26 (n/s/m/l/x), YOLOE-26 (s/m/l + PF) | Full-featured, multi-task, open-vocabulary detection |
| NanoDet | NanoDet-Plus (M/T/G) | Ultra-lightweight, edge devices, real-time |
Both providers return identical PHP result types — switch backends without changing your code.
YOLOE-26 Open-Vocabulary Detection
YOLOE models support text prompts to detect anything you can describe — not just the 80 COCO classes:
| Variant | Suffix | Prompts | Best For |
|---|---|---|---|
| Text-prompted | yoloe-26*-seg.pt |
->prompts([...]) required |
Targeted attribute/concept detection |
| Prompt-free | yoloe-26*-seg-pf.pt |
Not supported | Auto-detect without specifying prompts |
Ultralytics Solutions
Run 12 built-in Ultralytics solutions (counting, heatmaps, speed estimation, etc.) with a single fluent call:
See docs/solutions.md for all 12 solutions and their parameters.
Detection Examples
Modern Workspace
Person + Cup
Street Scene with Segment
Video Detection — Street Traffic
Detection Result Array
The detect() method returns an InferenceResult object. Call toArray() to get a plain array:
Fluent API
Image Detection
Video Detection
For realtime stream, check: Real-Time Streaming
Image Annotation
Detect + Annotate in One Call
Use process() to get both detections and an annotated image in a single inference run:
process() runs inference once — more efficient than calling detect() and annotate() separately.
Working with Results
NanoDet Example
Custom Trained Models
Pass a path to your own trained model — provider is auto-inferred from the file extension:
See Custom Models for full details on supported formats, model resolution, and provider auto-inference.
Configuration
Create fluentvision-config.php in your project root:
Or load from a custom path:
CLI Commands
Requirements
- PHP 8.3+
- Python 3.8+ with pip
- Ultralytics or NanoDet Python packages (installed via
fluentvision install)
Documentation
- Installation Guide — step-by-step setup
- Configuration Reference — all config options
- Usage Guide — complete fluent API reference
- Providers — Ultralytics vs NanoDet details
- Custom Models — using your own trained models
- Result Objects — InferenceResult, ProcessResult, StreamResult, SolutionResult, DetectionResult, BoundingBox API
- Ultralytics Solutions — object counting, heatmaps, speed estimation, and 9 more built-in solutions
- Real-Time Streaming — RTSP, RTMP, webcam frame-by-frame detection
- CLI Commands — install, doctor, and options
License
MIT