Img2mo Std logo

Img2mo Std

Community
WU-HAOTIAN34
img2mo-std

Standardize a 2D animation baseline image with `/img2mo-std xxx.png/pos`. Use when preparing a character, creature, prop, or weapon baseline before motion generation, especially if the source image is too large, tightly cropped, lacks transparent action margin, has a white background, or later walk/attack/idle frames show clipping, overlap, scale popping, or inconsistent character size.

Overview

PublisherWU-HAOTIAN34
Repository2dimg2motion
Skill nameimg2mo-std
Stars
233
Forks
10
Bundled files
Instructions only
LicenseMIT
Links
  • 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.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by WU-HAOTIAN34 on GitHub. Read the source before you install it.

Installation

Install the Img2mo Std 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/WU-HAOTIAN34/2dimg2motion/tree/main/skills/img2mo-std
  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/WU-HAOTIAN34/2dimg2motion.git /tmp/2dimg2motion
mkdir -p .claude/skills
cp -r /tmp/2dimg2motion/skills/img2mo-std .claude/skills/img2mo-std
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Img2mo Std 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 Img2mo Std 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 Img2mo Std 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.

Img2mo-std

Overview

Use this skill when the user invokes:

text
/img2mo-std xxx.png/pos

The command audits and standardizes a baseline frame before animation generation. It creates a smaller, padded, transparent-canvas source image that leaves enough room for walk, attack, idle, weapon swing, cape, tail, horn, or limb stretch poses.

Input Resolution

Resolve the argument after /img2mo-std as follows:

  1. If it is an existing relative or absolute path, use it directly.
  2. If it is a bare file name such as s7.png, first try sample\s7.png.
  3. If it has no extension such as s7, first try sample\s7.png, then sample\s7.jpg, then sample\s7.webp.
  4. If no matching image exists, report the missing path and do not guess from unrelated files.

Examples:

text
/img2mo-std s7
/img2mo-std s7.png
/img2mo-std sample\s7.png
/img2mo-std C:\AI\2dimg2motion-v1\sample\s7.png

Audit Criteria

A baseline is not standard if any of these are true:

  • The foreground subject is larger than about 300-400 px on its longest side.
  • The subject touches or nearly touches the canvas edge.
  • There is not enough empty transparent space for arms, legs, weapons, tails, capes, horns, or effects to extend during motion.
  • The background is opaque white or near-white when the character should be isolated.
  • The source has a huge canvas that will slow generation without adding useful detail.
  • Previous generated frames show inconsistent character size, off-center motion, clipped body parts, or crowded sprite-sheet cells.

Tool

Run the repository tool from the workspace root after resolving the image path:

powershell
python scripts\standardize_baseline.py <resolved-image-path>

Default output:

text
sample\<input-stem>-standard.png

Useful options:

powershell
python scripts\standardize_baseline.py sample\s7.png --subject-max 360 --margin-ratio 0.75
python scripts\standardize_baseline.py sample\s7.png --output sample\s7-standard.png
python scripts\standardize_baseline.py sample\s7.png --check-only

Recommended default target:

  • Subject longest side: 360
  • Margin ratio: 0.65 to 0.85
  • Output format: PNG with transparency

Report Interpretation

The tool prints a JSON report. Treat the standardized output as ready when:

  • needs_standardization is false after processing.
  • subject_longest_side is between 300 and 400.
  • edge_clearance_ratio leaves enough room for the intended motion.
  • warnings is empty or only contains acceptable notes.

If the report still warns that the image is tight or too large, rerun with a smaller --subject-max or larger --margin-ratio.

Animation Workflow Rule

After /img2mo-std, use the standardized output image as the baseline for all later walk, attack, idle, or other sprite generation. Do not continue from the original oversized or tightly cropped source unless the user explicitly asks to bypass standardization.

Frequently asked questions

What does the Img2mo Std AI skill do?

Standardize a 2D animation baseline image with `/img2mo-std xxx.png/pos`. Use when preparing a character, creature, prop, or weapon baseline before motion generation, especially if the source image is too large, tightly cropped, lacks transparent action margin, has a white background, or later walk/attack/idle frames show clipping, overlap, scale popping, or inconsistent character size.

Why use Img2mo Std on TypingMind?

Because you install it once and use it with any model. Img2mo Std 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 Img2mo Std in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/WU-HAOTIAN34/2dimg2motion/tree/main/skills/img2mo-std. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Img2mo Std?

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 Img2mo Std?

As many as you like. As long as a model supports skills, you can use Img2mo Std with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Img2mo Std AI skill free?

Yes. It is published on GitHub by WU-HAOTIAN34 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.

View all

Set up your own AI workspace now

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