# AI use cases for Edit Drift (MegaTroll222/edit-drift)

Repo: [MegaTroll222/edit-drift](https://github.com/MegaTroll222/edit-drift) | Use cases: 3 | Page: https://dedupedai.com/use-cases/megatroll222-edit-drift/

Edit Drift is a chained-edit benchmark and scorer that measures how much image models alter the untouched parts of a photo across 40 consecutive edits, with a CLI and a Claude Code plugin.

This file holds every use case of this repo. Each one starts with a "## " heading and ends with its URL.

- Score how much an image model changes what it shouldn't: https://dedupedai.com/use-cases/megatroll222-edit-drift/score-image-model-edit-fidelity/
- Compare image models with a leaderboard and video: https://dedupedai.com/use-cases/megatroll222-edit-drift/compare-models-side-by-side/
- Run the benchmark from Claude Code: https://dedupedai.com/use-cases/megatroll222-edit-drift/run-edit-drift-from-claude-code/

## How to score how much an image model changes what it shouldn't with Edit Drift

Repo: [MegaTroll222/edit-drift](https://github.com/MegaTroll222/edit-drift) | Difficulty: Advanced | Time: 2 hours | Basis: From the README

Run the 40-edit benchmark with your model and compute its Edit Fidelity Score.

**Who it is for:** An ML engineer picking an image editing model for a product.

**The problem:** Models quietly alter areas they were told to leave alone.

**The outcome:** Per-step drift and an Edit Fidelity Score in scores.json.

### Steps

1. Install with `pip install git+https://github.com/MegaTroll222/edit-drift`
2. List the edits with `editdrift steps  benchmarks/milk`
3. Generate each edit with your model, applying it to the previous result
4. Score with `editdrift score  benchmarks/milk results/milk/my-model`

### Prompt to paste into your agent

```text
Using MegaTroll222/edit-drift, run the milk benchmark edits with <model>, score them, and report the Edit Fidelity Score and final drift.
```

### Caveat

The score averages all 40 steps, so it can rank models differently from final drift alone.

Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/

URL: https://dedupedai.com/use-cases/megatroll222-edit-drift/score-image-model-edit-fidelity/

## How to compare image models with a leaderboard and video with Edit Drift

Repo: [MegaTroll222/edit-drift](https://github.com/MegaTroll222/edit-drift) | Difficulty: Intermediate | Time: 30 minutes | Basis: From the README

Generate a report and side-by-side videos for every model you scored.

**Who it is for:** A team presenting model choices to stakeholders.

**The problem:** Numbers alone do not show how drift looks.

**The outcome:** A leaderboard, drift curves and comparison videos.

### Steps

1. Score each model's results
2. Build the report with `editdrift report benchmarks/milk results/milk --out report`
3. Make a side-by-side video with editdrift video
4. Share the report

### Prompt to paste into your agent

```text
Run `editdrift report benchmarks/milk results/milk --out report` and summarize the ranking. Create a side-by-side video of the top two models.
```

### Caveat

Comparisons are only fair when every model used the same edits in order.

Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/

URL: https://dedupedai.com/use-cases/megatroll222-edit-drift/compare-models-side-by-side/

## How to run the benchmark from Claude Code with Edit Drift

Repo: [MegaTroll222/edit-drift](https://github.com/MegaTroll222/edit-drift) | Difficulty: Intermediate | Time: 30 minutes | Basis: From the README

Install the plugin and let Claude Code drive scoring and reporting.

**Who it is for:** A developer who prefers asking an agent over learning a CLI.

**The problem:** Benchmark CLIs have many steps.

**The outcome:** Agent-run scoring and reports.

### Steps

1. Run `/plugin marketplace add MegaTroll222/edit-drift`
2. Run `/plugin install edit-drift@edit-drift`
3. Point it at your results folder
4. Ask for scores and a report

### Prompt to paste into your agent

```text
Using the edit-drift Claude Code plugin, score results in <folder> and produce the report. Confirm scores.json exists for each model.
```

### Caveat

Masks per step must match your image size; use editdrift mask to generate them.

Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/

URL: https://dedupedai.com/use-cases/megatroll222-edit-drift/run-edit-drift-from-claude-code/