Data

Tools

Indexes

Applications

Experiments

Open Source Science

https://github.com/altunenes/calcarine

Desktop VLM: Real-time FastVLM analysis of video & textures with live compute shaders

https://github.com/altunenes/calcarine

Science Score: 26.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • ○
    CITATION.cff file
  • ✓
    codemeta.json file
    Found codemeta.json file
  • ✓
    .zenodo.json file
    Found .zenodo.json file
  • ○
    DOI references
  • ○
    Academic publication links
  • ○
    Committers with academic emails
  • ○
    Institutional organization owner
  • ○
    JOSS paper metadata
  • ○
    Scientific vocabulary similarity
    Low similarity (10.1%) to scientific vocabulary

Keywords

compute-shader fastvlm large-language-models onnxruntime shaders vision-language-model vlm wgpu
Last synced: 6 months ago · JSON representation

Repository

Desktop VLM: Real-time FastVLM analysis of video & textures with live compute shaders

Basic Info
  • Host: GitHub
  • Owner: altunenes
  • License: mit
  • Language: Rust
  • Default Branch: master
  • Homepage:
  • Size: 224 KB
Statistics
  • Stars: 3
  • Watchers: 0
  • Forks: 1
  • Open Issues: 1
  • Releases: 3
Topics
compute-shader fastvlm large-language-models onnxruntime shaders vision-language-model vlm wgpu
Created 8 months ago · Last pushed 6 months ago
Metadata Files
Readme License

README.md

Calcarine

Scene analysis from Apple FastVLM model

prompt: What is written in the upper left and upper right corners?
3.58 seconds processing time. MacOS m3 16 GB

calcarine

Features

  • Multi-source input: Images, videos, webcam feeds - We pass textures directly to the GPU
  • Real-time GPU processing: Compute shaders with hot reload via Cuneus
  • VLM analysis: Real-time predictions using Apple FastVLM model
  • Interactive controls: Real-time parameter adjustment via egui

Installation

See INSTALL.md for detailed installation instructions.

What You're Actually Using

Under the hood, Calcarine is powered by Cuneus. The real focus is passing textures to GPU and having the VLM make real-time predictions and analysis. The simple image effects (brightness, contrast, etc.) are just examples of what compute shaders can do.

AI Model Details

Model: Apple FastVLM-1B - Size: ~1.4 GB (one-time download) - Storage: Models are downloaded to data/fastvlm/ directory - Performance: Macbook M3 CPU: - ~3-4 second inference time

Owner

  • Name: Enes
  • Login: altunenes
  • Kind: user

I like science, computers, and budgies :-)

GitHub Events

Total
  • Release event: 1
  • Watch event: 1
  • Delete event: 2
  • Issue comment event: 1
  • Push event: 20
  • Pull request event: 3
  • Create event: 5
Last Year
  • Release event: 1
  • Watch event: 1
  • Delete event: 2
  • Issue comment event: 1
  • Push event: 20
  • Pull request event: 3
  • Create event: 5

Committers

Last synced: 8 months ago

All Time
  • Total Commits: 18
  • Total Committers: 1
  • Avg Commits per committer: 18.0
  • Development Distribution Score (DDS): 0.0
Past Year
  • Commits: 18
  • Committers: 1
  • Avg Commits per committer: 18.0
  • Development Distribution Score (DDS): 0.0
Top Committers
Name Email Commits
altunenes e****2@g****m 18

Issues and Pull Requests

Last synced: 6 months ago

All Time
  • Total issues: 0
  • Total pull requests: 3
  • Average time to close issues: N/A
  • Average time to close pull requests: N/A
  • Total issue authors: 0
  • Total pull request authors: 1
  • Average comments per issue: 0
  • Average comments per pull request: 0.0
  • Merged pull requests: 0
  • Bot issues: 0
  • Bot pull requests: 0
Past Year
  • Issues: 0
  • Pull requests: 3
  • Average time to close issues: N/A
  • Average time to close pull requests: N/A
  • Issue authors: 0
  • Pull request authors: 1
  • Average comments per issue: 0
  • Average comments per pull request: 0.0
  • Merged pull requests: 0
  • Bot issues: 0
  • Bot pull requests: 0
View more stats
Top Authors
Issue Authors
Pull Request Authors
  • altunenes (3)
Top Labels
Issue Labels
Pull Request Labels

Dependencies

.github/workflows/release.yml actions
  • actions/checkout v4 composite
  • actions/download-artifact v4 composite
  • actions/upload-artifact v4 composite
  • dtolnay/rust-toolchain stable composite
  • softprops/action-gh-release v1 composite
Cargo.lock cargo
  • 601 dependencies
Cargo.toml cargo