dsh-fal-image-gen
FAL image generation for DeepSeek Harness: a generate_image tool backed by the FAL queue API (default model fal-ai/flux-2/klein/9b). Images render directly in the conversation, are saved to the workspace, and all settings are editable from the Web GUI.
安装
dsh plugin --profile web add github:goodandready/dsh-fal-image-gen
需要可复现安装时,可在仓库后追加 #commit 固定提交。
FAL image generation for DeepSeek Harness: a generate_image tool backed by the FAL queue API (default model fal-ai/flux-2/klein/9b). Images render directly in the conversation, are saved to the workspace, and all settings are editable from the Web GUI.
该插件未提供要点说明,请参考仓库 README。
- 安装并启动 DeepSeek Harness:
npx @deepseek-ai/dsh web - 在终端执行上面的安装命令(CLI 会解析插件并核验来源)
- 用 dsh plugins list 确认已安装,必要时重启 Harness 生效
插件以当前 dsh 进程的权限运行,安装时可能执行代码。请先通读仓库源码与许可证,确认无破坏性命令与越权访问;本站只做索引,不对第三方插件安全性作担保。
| 代码仓库 | github.com/goodandready/dsh-fal-image-gen |
| 许可证 | MIT |
| 主要语言 | main |
| 下载量 | 2 |
| GitHub 星标 | 0 |
| 最近推送 | 2026-08-18 |
| 收录日期 | 2026-09-19 |
| 分类 | 界面增强 |
事实信息来自公开插件目录快照(2026-10-01),介绍文案由本站再加工。
以下为插件仓库 README 全文(原始内容,由公开目录抓取整理)。
# dsh-fal-image-gen
**Image generation** for [DeepSeek Harness](https://github.com/deepseek-ai/deepseek-harness) (dsh): a `generate_image` tool backed by the [FAL](https://fal.ai) REST queue API. Default model — `fal-ai/flux-2/klein/9b`.
A generated image is:
- saved into the workspace (`/generated/fal/*.png`);
- rendered directly in the conversation (via the dsh attachments service);
- its `fal.media` file URL returned to the model with the path, size and seed.
## Install
```bash
# From npm after publishing:
dsh plugin --profile web add @goodandready/dsh-fal-image-gen
# From GitHub:
dsh plugin --profile web add github:GooDAnDReaDY/dsh-fal-image-gen
# Locally from a checkout:
dsh plugin --profile web add /path/to/dsh-fal-image-gen
```
Restart the Web UI afterwards.
## Configure (Web GUI)
All settings live in **Settings → Plugins → Plugin configuration → FAL Image Generation**:
| Field | Default | Description |
|---|---|---|
| `model` | `fal-ai/flux-2/klein/9b` | FAL model id, called as `{baseURL}/{model}`. |
| `apiKeyEnv` | `FAL_API_KEY` | API key reference (credentials / env var). |
| `baseURL` | `https://queue.fal.run` | FAL queue base URL. |
| `defaultSize` | `landscape_4_3` | Default image size. |
| `defaultFormat` | `png` | Default output format. |
| `pollIntervalMs` | `2000` | Job status poll interval. |
| `timeoutMs` | `180000` | Total generation timeout. |
| `outputDir` | `generated/fal` | Output folder (relative to the workspace root). |
| `numImagesMax` | `4` | Max images per call. |
Equivalent values can be set in `$DSH_HOME/settings.yaml` under `dsh-fal-image-gen:` — the GUI writes to the same settings document, so both ways are equivalent.
## API key
Store your key in **Credentials** (Web: **Settings → Credentials**, name `FAL_API_KEY`) or in `$DSH_HOME/.credentials.yaml`:
```yaml
FAL_API_KEY:
```
The plugin prepends the `Key ` auth prefix automatically.
## Usage
Just ask the model to draw an image:
> Generate an image: neon cyberpunk city at night in the rain, 16:9
Tool parameters (all except `prompt` are optional):
| Parameter | Description |
|---|---|
| `prompt` | required, detailed image description |
| `image_size` | `square_hd` / `square` / `portrait_4_3` / `portrait_16_9` / `landscape_4_3` / `landscape_16_9` |
| `num_images` | 1–4 (default 1; first is displayed) |
| `seed` | seed for reproducibility |
| `output_format` | `png` (default) / `jpeg` / `webp` |
| `output_name` | file name without extension |
## Structure
```
dsh-fal-image-gen/
├── package.json # dsh bundle/plugin metadata + peerDependencies
├── cordis.patch.yml # bundle layer: inserts the plugin row
├── lib/index.js # host: generate_image tool + FAL queue client
├── lib/client.js # browser: settings card in the Web GUI
├── README.md
└── LICENSE # MIT
```
No npm runtime dependencies (the `@deepseek-ai/*` peer deps resolve from the dsh install), no build step — plain ESM.
## License
MIT
数据来源:公开的 DeepSeek Harness 插件目录与各插件 GitHub 仓库。本站为独立第三方目录,与 DeepSeek、幻方(High-Flyer)及插件作者均无隶属或背书关系。