TypingMindTypingMindThe best frontend for AI
3ddfa V2 logo

3ddfa V2

Organization
VectorSpaceLab
3ddfa-v2

Routes 3DDFA_V2 face-alignment setup, still-image demos, video tracking, and ONNX benchmarking workflows.

Overview

PublisherVectorSpaceLab
RepositoryAREX-Skill
Skill name3ddfa-v2
Stars
341
Forks
26
Bundled files
22
LicenseMIT
Links
Skill sourceRepository
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 22 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by VectorSpaceLab on GitHub. Read the source before you install it.

Installation

Install the 3ddfa V2 AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/VectorSpaceLab/AREX-Skill/tree/main/skills/repositories/repo-skills/3ddfa-v2
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/VectorSpaceLab/AREX-Skill.git /tmp/AREX-Skill
mkdir -p .claude/skills
cp -r /tmp/AREX-Skill/skills/repositories/repo-skills/3ddfa-v2 .claude/skills/3ddfa-v2
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable 3ddfa V2 in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads 3ddfa V2 on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so 3ddfa V2 is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

3DDFA_V2

Use this skill for the 3DDFA_V2 face-alignment repo. The public workflow is a small pipeline: build the native pieces, then run still-image, video/tracking, or ONNX/benchmark commands.

Start here

  1. If anything fails to build or import, open references/troubleshooting.md.
  2. If you need model files or config choices, open references/model-assets.md.
  3. If you need class/function details, open references/api-reference.md.
  4. Run the setup route first whenever render.so, cpu_nms, or Sim3DR_Cython is missing.

The repository is source-first, not a packaged wheel. Use the bundled helpers in this skill tree instead of calling the original repo scripts directly.

Routes

setup-and-assets

Use when the user asks to install or verify the runtime, build compiled pieces, check checkpoint/config assets, or fix import/build failures.

Read sub-skills/setup-and-assets/SKILL.md, references/model-assets.md, and references/troubleshooting.md.

Use the bundled helpers:

  • scripts/build_native_extensions.py
  • scripts/check_assets.py
  • scripts/check_core_imports.py

still-image-demo

Use for single-image inference, 2D landmark overlays, 3D renderings, depth, PNCC, UV texture, pose boxes, PLY, or OBJ exports.

Read sub-skills/still-image-demo/SKILL.md and sub-skills/still-image-demo/references/workflows.md.

Use sub-skills/still-image-demo/scripts/run-still-image.py for a headless-friendly wrapper.

video-and-tracking

Use for MP4/AVI processing, tracking, smoothing, or frame-window control.

Read sub-skills/video-and-tracking/SKILL.md and sub-skills/video-and-tracking/references/workflows.md.

Use sub-skills/video-and-tracking/scripts/run-video.py and sub-skills/video-and-tracking/scripts/run-video-smooth.py.

onnx-and-benchmarking

Use for ONNX acceleration, CPU latency, thread tuning, or microbenchmarks.

Read sub-skills/onnx-and-benchmarking/SKILL.md and sub-skills/onnx-and-benchmarking/references/workflows.md.

Use sub-skills/onnx-and-benchmarking/scripts/run-latency.py and sub-skills/onnx-and-benchmarking/scripts/run-speed-cpu.py.

Common runtime facts

  • Default config: configs/mb1_120x120.yml.
  • Alternate configs: configs/mb05_120x120.yml and configs/resnet_120x120.yml.
  • Provide an input image or video path for demos; local smoke fixtures may be used when the checkout includes them.
  • Generated outputs live under examples/results/.
  • demo.py supports 2d_sparse, 2d_dense, 3d, depth, pncc, uv_tex, pose, ply, and obj.
  • demo_video.py and demo_video_smooth.py support 2d_sparse and 3d; webcam mode is manual-only and is documented, but not bundled as a runnable helper.
  • --onnx switches the demo pipeline to the CPU-friendly ONNX path.
  • uv_tex needs SciPy and the BFM UV/config assets.
  • The repo still references deprecated NumPy aliases such as np.long, so the bundled runtime helpers restore a compatibility layer before importing the pipeline.

Headless use

The bundled helpers default to headless plotting behavior so they work in non-GUI environments. If you need interactive windows, override that behavior explicitly.

What not to route here

  • Experimental Gradio notebook/demo code.
  • Generic face detection tasks that do not involve the 3DDFA_V2 alignment pipeline.
  • Training or dataset creation tasks; this repo is inference-oriented.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the 3ddfa V2 AI skill do?

Routes 3DDFA_V2 face-alignment setup, still-image demos, video tracking, and ONNX benchmarking workflows.

Why use 3ddfa V2 on TypingMind?

Because you install it once and use it with any model. 3ddfa V2 is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install 3ddfa V2 in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/VectorSpaceLab/AREX-Skill/tree/main/skills/repositories/repo-skills/3ddfa-v2. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use 3ddfa V2?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with 3ddfa V2?

As many as you like. As long as a model supports skills, you can use 3ddfa V2 with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the 3ddfa V2 AI skill free?

Yes. It is published on GitHub by VectorSpaceLab under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

Related AI Skills

View all
openclaw logo

Slack E2e

openclaw
OrganizationPopular

Test Slack with Convex-leased user OAuth or QA bots; check credentials, exercise owned messages, prove Gateway behavior, and distinguish API evidence from real Slack client interactions.

82.2K
391K
4 files
View
openclaw logo

Telegram E2e Userbot

openclaw
OrganizationPopular

Prove user-visible OpenClaw Telegram behavior on Telegram's Test Server with Convex-leased team credentials; drive real-user turns and record messages, edits, deletions, reactions, typing, or rich…

82.2K
391K
45 files
View
affaan-m logo

Module Regression

affaan-m
CommunityPopular

Govern cross-module regression in large repositories with a REGRESSION.md ledger that records each module's downstream consumers and executable acceptance command. After a change, run the changed…

41.4K
277.3K
2 files
View
affaan-m logo

Test Collaboration

affaan-m
CommunityPopular

Inventory and govern a project's test assets. Connect requirements, business rules, risks, bugs, and cross-boundary contracts to stable TEST-IDs and executable evidence in the repository's existing…

41.4K
277.3K
2 files
View

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇