# eachlabs-image-generation

Turns a text prompt into a finished image through the EachLabs Predictions API. Handy when you need a picture and have no design tool open.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode · 318 installs · ★ 44
- Author: eachlabs
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/eachlabs/skills/tree/HEAD/skills/eachlabs-image-generation/SKILL.md
- Updated: 2026-10-07
- HTML: https://affpapa.org/en/nevibecode/skills/eachlabs-image-generation

## What it does

The skill wires your agent to more than 60 text-to-image models. Flux 2 ships in Turbo, Flash, Max, Klein, Pro, Flex and LoRA variants; the list also covers GPT Image v1.5 and v2, Gemini 3 Pro Image, Imagen 4, Seedream v4.5, Ideogram V3 Turbo, Hunyuan Image v3, Wan v2.6 and Nano Banana Pro. Three trainers handle custom LoRA work: Z Image Trainer, Flux LoRA Portrait Trainer and Flux Turbo Trainer.

Each run follows the same path. The agent first calls `GET https://api.eachlabs.ai/v1/model?slug=<slug>` to confirm the model exists and read its `request_schema`. Then it posts to `https://api.eachlabs.ai/v1/prediction` with version `"0.0.1"` and inputs matching that schema. After that it polls `GET https://api.eachlabs.ai/v1/prediction/{id}` until the status reads `"success"` or `"failed"`, and pulls the image URL out of the response. Sizes come from presets such as `landscape_16_9` or `square_hd`; P Image models take ratio strings instead — `1:1`, `16:9`, `custom`.

Nothing runs without `EACHLABS_API_KEY` in your environment, since the key travels in the `X-API-Key` header and you fetch it from eachlabs.ai. The skill also carries security rules: LoRA weights may only come from recognised sources like HuggingFace, Replicate or CivitAI repos, and third-party tokens are not accepted through prediction inputs. Editing finished images — upscaling, background removal, inpainting, face swap — belongs to the separate `eachlabs-image-edit` skill.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add eachlabs/skills --skill eachlabs-image-generation -a claude-code
```

2. **Manually: put the files in place**
- File: `~/.claude/skills/eachlabs-image-generation/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/eachlabs-image-generation/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add eachlabs/skills --skill eachlabs-image-generation -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/eachlabs-image-generation/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add eachlabs/skills --skill eachlabs-image-generation -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/eachlabs-image-generation/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install eachlabs/skills eachlabs-image-generation
```

2. **Manually: put the files in place**
- File: `.github/skills/eachlabs-image-generation/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add eachlabs/skills --skill eachlabs-image-generation -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/eachlabs/skills --path skills/eachlabs-image-generation
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/eachlabs-image-generation/SKILL.md` — The legacy .windsurf/skills/ path still works

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add eachlabs/skills --skill eachlabs-image-generation -a opencode
```

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/eachlabs/skills/tree/HEAD/skills/eachlabs-image-generation/SKILL.md

## When to use it
- generate an article illustration from a written description
- produce a logo with a transparent background
- compare several models against the same prompt
- train a LoRA for a personal style or portraits
- get an image in a specific aspect ratio without a graphics editor

## Example prompts
- Generate an image with eachlabs-image-generation: a mountain road at golden hour, photorealistic
- Make a transparent-background logo for a coffee shop called Brew Lab using gpt-image-v1-5-text-to-image
- Check the request schema for flux-2-turbo-text-to-image and generate one landscape_16_9 image

## Similar
- [ai-image-generation](https://affpapa.org/en/nevibecode/skills/prime-skills-ai-image-generation.md) — skill · 383000 installs
- [stable-diffusion-image-generation](https://affpapa.org/en/nevibecode/skills/stable-diffusion-image-generation.md) — skill · 1000 installs
- [gpt-image-2](https://affpapa.org/en/nevibecode/skills/gpt-image-2.md) — skill · 84300 installs
- [layer-image](https://affpapa.org/en/nevibecode/skills/layer-image.md) — skill · 3300 installs
- [p-image](https://affpapa.org/en/nevibecode/skills/p-image.md) — skill · 12400 installs
- [muapi-media-generation](https://affpapa.org/en/nevibecode/skills/muapi-media-generation.md) — skill · 1100 installs

From the same set: [eachlabs/skills](https://affpapa.org/en/nevibecode/by/eachlabs/skills.md) — 36 cards

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md