# Generate and Edit Images Across Leading AI Models

Choosing and invoking image models individually slows creative work. This skill provides one belt CLI workflow for generation, editing, upscaling, and image stitching.

## Install

```bash
npx skillstore add 101-skills/ai-image-generation
```

## Metadata

- Status: approved
- Slug: 101-skills-ai-image-generation
- Skillstore revision: r1
- Version status: missing
- Tree hash: 6432408ae81bec8740b86cb1ccc51efbb606d98fbecf3565805cc7397fca3468
- Author: 101-skills
- GitHub username: 101-skills
- License: MIT
- Repository: https://github.com/101-skills/skills/tree/main/tools/image/ai-image-generation/
- Ref: d71c7417a35d5c2624161bd2fe8de8a41a362128
- Supported tools: Claude, Codex, Claude Code
- Audit status: complete
- Agent install advisory: allowed
- Manual install advisory: allowed
- Artifact signature: available
- Audit attestation: unavailable
- Human verification: not\_verified
- Risk factors: external\_commands, network
- Quality score: 50
- Quality tier: warning
- Public page: https://skillstore.pages.dev/skills/101-skills-ai-image-generation
- Manifest: https://skillstore.pages.dev/api/skills/101-skills-ai-image-generation/manifest

## Capabilities

- Lists hosted image models with app identifiers and recommended uses.
- Provides text-to-image commands for GPT-Image, FLUX, Gemini, Grok, Reve, and Seedream.
- Shows image editing with a prompt and a user-provided image URL.
- Supports example controls for quality and aspect ratio.
- Provides an image-upscaling workflow using the Topaz app.
- Shows how to stitch multiple images horizontally.

## Use Cases

- Create Product Concepts: Generate studio product images, compare model outputs, and refine backgrounds for early design reviews.
- Produce Campaign Visuals: Create social graphics, posters with text, and wide campaign scenes from structured creative prompts.
- Automate Image Workflows: Run repeatable generation, editing, upscaling, and stitching tasks from a command-line workflow.

## Prompt Templates

### Generate a Simple Image

```
Use this skill to generate an image of [subject] in [style] with [lighting]. Choose a suitable model and explain the selection.
```

### Create a Product Visual

```
Generate a professional product image for [product]. Use [background], [camera angle], and [aspect ratio]. Select a model suited to product photography.
```

### Edit and Upscale an Image

```
Edit the image at [image URL] by changing [requested element] while preserving [protected details]. Then upscale the approved result.
```

### Compare a Multi-Model Campaign

```
Create [number] campaign variants for [audience] using two suitable models. Keep [brand constraints], compare results, and stitch selected images horizontally.
```

## Limitations

- Requires the inference.sh belt CLI, authentication, network access, and hosted service availability.
- Does not generate images locally or provide an offline workflow.
- Does not verify current model availability, pricing, quotas, or output rights.
- Does not explain provider retention policies for prompts or source images.

## Best Practices

- State the subject, composition, style, lighting, aspect ratio, and required text before choosing a model.
- Use non-sensitive image URLs and review each provider policy before submitting source material.
- Generate small comparisons first, then edit and upscale only the selected result.

## Anti Patterns

- Do not submit confidential prompts, private image links, or personal images without authorization.
- Do not assume every model supports the same editing controls, dimensions, or text quality.
- Do not upscale every draft before composition and content are approved.

## Security Audit

- Audited at: 2026-07-12T09:52:20.533\+00:00
- Summary: The scanner mostly mistook Markdown formatting and model identifiers for Ruby or shell backtick execution. A remote image, mutable installation guidance, broad belt permission, and hosted processing create low-to-medium privacy and supply-chain risks. No prompt injection or malicious exfiltration intent was found.

## Stats

- Views: 0
- Downloads: 6
- Favorites: 0
- Popularity score: 0