# AI use cases for Pocket Men with You (six-nut/PocketMen-with-you)

Repo: [six-nut/PocketMen-with-you](https://github.com/six-nut/PocketMen-with-you) | Use cases: 3 | Page: https://dedupedai.com/use-cases/six-nut-pocketmen-with-you/

PocketMen with You is a local tool that turns two or more photos into an animated Codex companion pet, using open-weight image editing when the hardware allows it.

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

- Install a Codex pet from two or more photos: https://dedupedai.com/use-cases/six-nut-pocketmen-with-you/install-codex-pet-from-photos/
- Build a high-fidelity pet with the Qwen identity backend: https://dedupedai.com/use-cases/six-nut-pocketmen-with-you/build-pet-with-local-neural-identity-backend/
- Create a Codex pet with no OpenAI API key: https://dedupedai.com/use-cases/six-nut-pocketmen-with-you/create-pet-without-openai-key/

## How to install a Codex pet from two or more photos with Pocket Men with You

Repo: [six-nut/PocketMen-with-you](https://github.com/six-nut/PocketMen-with-you) | Difficulty: Intermediate | Time: 1 hour | Basis: From the README

Turn your own photos into an installed Codex companion pet with one create command.

**Who it is for:** A Codex user who wants a personal animated companion based on a person or animal they photographed.

**The problem:** Making an animated pet for Codex by hand means drawing or animating every state, which takes skill and time.

**The outcome:** An installed Codex pet with a pet.json and spritesheet.webp built from the supplied photos.

### Steps

1. Run `INSTALL_SKILL.bat` to install the skill and create the isolated runtime.
2. Run `pocketmen doctor` to check the hardware.
3. Run `pocketmen create --reference photo-1.jpg --reference photo-2.jpg --name "Mochi" --subject-type animal --style soft-real --engine auto --quality balanced --output ./pocketmen-output --install`, replacing the file names, name, and subject type with your own. (inferred, check the README)

### Prompt to paste into your agent

```text
Using the repo six-nut/PocketMen-with-you, run `pocketmen doctor`, then create a companion with `pocketmen create` from the two reference images at <photo-1> and <photo-2>, output to ./pocketmen-output with --install. Expected output: pet.json and spritesheet.webp in the output folder and an installed Codex pet. Verify the atlas is 1536x1872 with 8 columns and 9 rows.
```

### Caveat

The README does not state a Python version or the exact VRAM needed, so check the installer output before relying on the neural path.

Risk, reverse engineering: Remove or keep private the reference photos of real people; only pet.json and spritesheet.webp are meant for the install package.

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/six-nut-pocketmen-with-you/install-codex-pet-from-photos/

## How to build a high-fidelity pet with the Qwen identity backend with Pocket Men with You

Repo: [six-nut/PocketMen-with-you](https://github.com/six-nut/PocketMen-with-you) | Difficulty: Advanced | Time: 2 hours | Basis: From the README

Prepare the heavier local Qwen editor and create a max-quality pet that keeps the subject's look.

**Who it is for:** A user who cares more about identity fidelity than setup size or latency, and has a GPU that can run the heavier model.

**The problem:** The default backend may not hold a subject's likeness closely enough for a companion the user wants to look like them.

**The outcome:** A max-quality companion created with the Qwen-Image-Edit-2511 backend, with state-specific key poses for every state.

### Steps

1. Run `PREPARE_IDENTITY_MAX.bat` to download and cache the Qwen-Image-Edit-2511 weights.
2. Run `pocketmen doctor` to confirm the hardware can run the heavier backend.
3. Run `pocketmen create --reference photo-1.jpg --reference photo-2.jpg --engine neural --backend qwen-image-edit-2511 --quality max`, adding the name, style, and output flags you need. (inferred, check the README)
4. Check the output folder for pet.json and spritesheet.webp before installing.

### Prompt to paste into your agent

```text
In the repo six-nut/PocketMen-with-you, run `pocketmen create` with --engine neural --backend qwen-image-edit-2511 --quality max using the references at <photo-1> and <photo-2>. Expected output: a pet.json and spritesheet.webp built from the Qwen backend. Verify that the run did not use the OpenAI API and that the atlas is 8 by 9 cells.
```

### Caveat

The README says this backend is heavier than the default, so the model download and generation time may be long on consumer hardware.

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/six-nut-pocketmen-with-you/build-pet-with-local-neural-identity-backend/

## How to create a Codex pet with no OpenAI API key with Pocket Men with You

Repo: [six-nut/PocketMen-with-you](https://github.com/six-nut/PocketMen-with-you) | Difficulty: Intermediate | Time: 1 hour | Basis: From the README

Generate a companion through local open-weight editing and avoid hosted image APIs entirely.

**Who it is for:** A privacy-minded developer who does not want to send photos to a hosted image service or manage an OpenAI key.

**The problem:** Most image-to-pet workflows depend on a hosted API key, which adds cost and sends personal photos out of the machine.

**The outcome:** A companion built on local open-weight neural editing, with the raw references kept on the local machine.

### Steps

1. Run `INSTALL_SKILL.bat` to set up the isolated local runtime.
2. Run `PREPARE_NEURAL_ENGINE.bat` to cache the default FLUX.2 [klein] 4B model locally.
3. Run `pocketmen create --reference photo-1.jpg --reference photo-2.jpg --engine neural --backend flux2-klein-4b --quality max`, then keep only the installed package for sharing. (inferred, check the README)

### Prompt to paste into your agent

```text
Using the repo six-nut/PocketMen-with-you, run `pocketmen create` with --engine neural --backend flux2-klein-4b on the references at <photo-1> and <photo-2>. Expected output: pet.json and spritesheet.webp, with no OPENAI_API_KEY set. Verify that the final package contains only pet.json and spritesheet.webp.
```

### Caveat

The README says the default engine falls back to the v0.2 engine when the GPU or neural runtime is missing, so confirm which engine ran before assuming neural output.

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/six-nut-pocketmen-with-you/create-pet-without-openai-key/