OpenClaw

pixeldojo

Access PixelDojo's API for AI image and video generation. Use when an agent needs to create images or videos, choose a model from the live PixelDojo catalog, check async job status, or download finished assets. PixelDojo is a subscription-based creative platform that exposes multiple generation models through one API, including general image, editing-oriented image, and video workflows.

blovett800 来源安装数☆ 0 仓库 Stars

查看来源 ↗安装与使用 SKILL.md ↗

安装与使用

请根据来源仓库和你的 AI 工具说明安装此技能。先阅读技能文件和依赖要求，再添加到工作流。

SkillHub CLI

skillhub install blovett80/pixeldojo

打开来源仓库，查看说明和兼容环境后，按来源提供的命令或步骤安装。

将来源链接提供给你的 Agent，让它先读取说明、核对依赖，并向你说明将执行的安装步骤。

查看来源 ↗使用指南

技能说明

PixelDojo

Use PixelDojo's async API to generate and download AI images or videos.

Setup

Runtime requirements:

Environment variable: PIXELDOJO_API_KEY
Binaries: curl, jq, python3
Optional override: PIXELDOJO_API_BASE

Set the API key before running any helper:

export PIXELDOJO_API_KEY=your_api_key_here

Optional local env file:

cp ~/.openclaw/skills/pixeldojo/.env.example ~/.openclaw/skills/pixeldojo/.env

Default API base: https://pixeldojo.ai/api/v1

Workflow

Check the live model catalog first.
Pick a model that matches the requested workflow.
Submit the job with generate.sh or the Nano Banana helper.
Poll status until complete, then return the downloaded asset path.

Do not guess model IDs.

Check the live catalog

bash ~/.openclaw/skills/pixeldojo/models.sh

For a pinned snapshot of known-good model IDs and example picks, read:

references/model-catalog.md

Generate an image

bash ~/.openclaw/skills/pixeldojo/generate.sh image "editorial product photo of a silver robot" flux-2-pro --aspect-ratio 16:9

Good defaults:

Best general image quality: flux-2-max
Prompt adherence and typography: nano-banana-2
Editing-oriented image work: flux-kontext-pro

Generate a video

bash ~/.openclaw/skills/pixeldojo/generate.sh video "cinematic ocean waves at sunset" seedance-1.5 --duration 5

Use --image-url for image-to-video models:

bash ~/.openclaw/skills/pixeldojo/generate.sh video "slow camera push-in" wan-2.6-flash --image-url https://example.com/input.png --duration 5

Nano Banana helper

Use this when the user specifically wants Nano Banana 2 or strong prompt adherence:

python3 ~/.openclaw/skills/pixeldojo/scripts/generate-nano-banana.py "clean ecommerce hero shot of running shoes" --aspect-ratio 16:9 --output ~/Desktop/shoes.png

Check job status

bash ~/.openclaw/skills/pixeldojo/status.sh job_abc123
`...

来源信息

Source: github
Repository: openclaw/skills
Path: skills/blovett80/pixeldojo
Version: —
Commit: df54039409038f1a3615bd2f044a0ba844d5886e
分类来源: rules
状态: active
可见性: public

这些信息来自收录时的来源分析，可能滞后；使用前请核对最新来源文件。

来源内容

SKILL.md

# PixelDojo

Use PixelDojo's async API to generate and download AI images or videos.

## Setup

Runtime requirements:
- Environment variable: `PIXELDOJO_API_KEY`
- Binaries: `curl`, `jq`, `python3`
- Optional override: `PIXELDOJO_API_BASE`

Set the API key before running any helper:

```bash
export PIXELDOJO_API_KEY=your_api_key_here
```

Optional local env file:

```bash
cp ~/.openclaw/skills/pixeldojo/.env.example ~/.openclaw/skills/pixeldojo/.env
```

Default API base: `https://pixeldojo.ai/api/v1`

## Workflow

1. Check the live model catalog first.
2. Pick a model that matches the requested workflow.
3. Submit the job with `generate.sh` or the Nano Banana helper.
4. Poll status until complete, then return the downloaded asset path.

Do not guess model IDs.

## Check the live catalog

```bash
bash ~/.openclaw/skills/pixeldojo/models.sh
```

For a pinned snapshot of known-good model IDs and example picks, read:
- `references/model-catalog.md`

## Generate an image

```bash
bash ~/.openclaw/skills/pixeldojo/generate.sh image "editorial product photo of a silver robot" flux-2-pro --aspect-ratio 16:9
```

Good defaults:
- Best general image quality: `flux-2-max`
- Prompt adherence and typography: `nano-banana-2`
- Editing-oriented image work: `flux-kontext-pro`

## Generate a video

```bash
bash ~/.openclaw/skills/pixeldojo/generate.sh video "cinematic ocean waves at sunset" seedance-1.5 --duration 5
```

Use `--image-url` for image-to-video models:

```bash
bash ~/.openclaw/skills/pixeldojo/generate.sh video "slow camera push-in" wan-2.6-flash --image-url https://example.com/input.png --duration 5
```

## Nano Banana helper

Use this when the user specifically wants Nano Banana 2 or strong prompt adherence:

```bash
python3 ~/.openclaw/skills/pixeldojo/scripts/generate-nano-banana.py "clean ecommerce hero shot of running shoes" --aspect-ratio 16:9 --output ~/Desktop/shoes.png
```

## Check job status

```bash
bash ~/.openclaw/skills/pixeldojo/status.sh job_abc123
`...

搜索