# Atlas Cloud

> Generate images and videos using Atlas Cloud AI models (Kling, Flux, etc.). Use when the user wants to create AI-generated images or videos.

- Skill: `ankitjh4/atlas-cloud` (Agent Skill, multi-file: 5 files)
- Install (CLI): `npx skillmds@latest add ankitjh4/atlas-cloud`
- Raw SKILL.md: https://api.skillmd.com/api/skills/ankitjh4/atlas-cloud/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: DevOps & Infra
- Author: ankitjh4 (https://skillmd.com/u/ankitjh4)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/ankitjh4/atlas-cloud

---


# Atlas Cloud AI

Generate images and videos using Atlas Cloud's AI models (Kling for video, Nano Banana for images).

## Setup

The API key is stored in your secrets as `ATLASCLOUD_API_KEY`. The skill reads it automatically.

## Scripts

### Text-to-Video

Generate video from a text prompt using Kling v3.0 Pro.

```bash
bun Skills/Community/atlas-cloud/scripts/video.ts --prompt "A minimal cube rotating in dark space" --aspect-ratio "16:9" --duration 5
```

**Options:**
| Flag | Description | Default |
|------|-------------|---------|
| `--prompt` | Video description (required) | - |
| `--aspect-ratio` | 16:9, 9:16, 1:1 | 16:9 |
| `--duration` | 5 or 10 seconds | 5 |
| `--cfg-scale` | Creativity 0-1 | 0.5 |
| `--negative-prompt` | Things to avoid | - |
| `--no-sound` | Disable audio | false |

---

### Image-to-Video

Generate video from an input image.

```bash
bun Skills/Community/atlas-cloud/scripts/image-to-video.ts --image "https://example.com/image.jpg" --prompt "Camera pans left"
```

**Options:**
| Flag | Description | Default |
|------|-------------|---------|
| `--image` | Input image URL (required) | - |
| `--end-image` | End frame image URL | - |
| `--prompt` | Video description | - |
| `--aspect-ratio` | 16:9, 9:16, 1:1 | 16:9 |
| `--duration` | 5 or 10 seconds | 5 |
| `--cfg-scale` | Creativity 0-1 | 0.5 |
| `--negative-prompt` | Things to avoid | - |
| `--no-sound` | Disable audio | false |

---

### Text-to-Image

Generate images using Google's Nano Banana 2 model.

```bash
bun Skills/Community/atlas-cloud/scripts/text-to-image.ts --prompt "cyberpunk city at night" --aspect-ratio "16:9" --resolution "2k"
```

**Options:**
| Flag | Description | Default |
|------|-------------|---------|
| `--prompt` | Image description (required) | - |
| `--aspect-ratio` | 16:9, 9:16, 1:1 | 16:9 |
| `--resolution` | 2k, 4k, 1k | 2k |
| `--negative-prompt` | Things to avoid | - |

---

### Image Edit

Edit images using Nano Banana 2 developer model.

```bash
bun Skills/Community/atlas-cloud/scripts/image-edit.ts --image "https://example.com/image.jpg" --prompt "Transform into 3D"
```

**Options:**
| Flag | Description | Default |
|------|-------------|---------|
| `--image` | Input image URL (required) | - |
| `--prompt` | Edit description (required) | - |
| `--aspect-ratio` | 16:9, 9:16, 1:1 | 16:9 |
| `--resolution` | 2k, 4k, 1k | 2k |

---

## Output

All scripts save the result URL to a file:
- Video: `atlas-last-video.txt`
- Image: `atlas-last-image.txt`