dsh-nanobananapro
Run the following command in DeepSeek Harness:
dsh plugin install synmindai/dsh-nanobananapro
Paste the following prompt into your AI chat to install this plugin:
Run dsh plugin install synmindai/dsh-nanobananapro to install this plugin in DeepSeek Harness; the source repository is available at https://github.com/synmindai/dsh-nanobananapro .
About this plugin
DeepSeek Harness excels at model inference and tool orchestration but lacks a built-in path for image and video generation. dsh-nanobananapro fills that gap by wiring the NanoBananaPro public API directly into Harness, letting you produce visual content as a native step in your workflow with nothing more than a self-owned NanoBananaPro API key.
The plugin exposes five tools: image generation, video generation, task-status polling, API balance inquiry, and account help. On the safety and billing side, paid tools require explicit user approval by default, every submission carries an idempotency key to prevent duplicate charges, transient 429 and 5xx responses are retried with bounded backoff, and timed-out tasks are returned with a timed_out flag so you can poll for results instead of resubmitting. Reference media must be supplied as public HTTPS URLs; the plugin does not upload local files.
If you have already built multi-step reasoning pipelines in DeepSeek Harness and want to slot in an image or video generation step without leaving the environment, this plugin turns a text prompt into a finished visual asset in a single tool call, provided you hold an active NanoBananaPro API wallet.
Use Cases
- Generate images or videos inline within a Harness workflow
- Poll asynchronous generation tasks and track final results
- Check NanoBananaPro API balance and real-time usage
Best For
- Developers already building inference pipelines in DeepSeek Harness
- Users holding a NanoBananaPro API key who need multimodal output
- Teams wanting to integrate visual generation without managing a proxy
Related Plugins
ModLens is a vision plugin for DeepSeek Harness that gives text-only models sight by reading images pasted directly into chat, with zero-config setup and multiple vision engines.
On-demand vision for text-only DeepSeek Harness agents: built-in free keyless vision chain and 14 vision tools, routing image turns as tool calls to vision models with pixel fidelity, no Python needed, one-command install.
Give text-only models in DeepSeek Harness eyes, enabling image Q&A, long-screenshot OCR, UI restoration, and GUI visual tasks.
An armor-breaking plugin for DeepSeek: rewrites instruction priority, expands refusal-blocked phrases, persists across sessions, and shows a green active indicator.