dsh-image-gen
Run the following command in DeepSeek Harness:
dsh plugin install LeemanCheung/dsh-image-gen
Paste the following prompt into your AI chat to install this plugin:
To install this plugin in DeepSeek Harness, run the command 'dsh plugin install LeemanCheung/dsh-image-gen', with the source code at https://github.com/LeemanCheung/dsh-image-gen。
About this plugin
In AI-assisted development and creation, image generation has become a common need, but seamlessly integrating it into existing toolchains often requires complex configurations and extra API management. The dsh-image-gen plugin is designed to solve this problem, allowing users to generate images directly through simple natural language conversations within the DeepSeek Harness environment, leveraging OpenAI's gpt-image-2 model. Whether for rapid prototyping, visual content creation, or exploring AI's multimodal capabilities, the plugin provides an intuitive and efficient entry point.
The core strengths of this plugin lie in its flexible authentication mechanisms and enhanced user experience. It defaults to using a signed-in Codex subscription, enabling animated progress visualization without additional API key configuration; alternatively, it supports explicit API key mode, which can display up to three streamed partial images with cross-fade effects. Generated images are stored as durable DSH attachments, facilitating easy preview, download, or replay. Moreover, the plugin maintains compatibility with text-only models by keeping image references in UI metadata, preventing rejection of conversation history in text-focused models.
dsh-image-gen is particularly suitable for developers, AI researchers, and creative professionals already using DeepSeek Harness. If you're looking for a convenient way to integrate image generation into your AI workflows, or prefer using subscription-based services like Codex or on-demand APIs for image creation, this plugin offers seamless support. It emphasizes security through per-request credential resolution, redirect rejection, and other measures, ensuring a safe and reliable usage experience.
Screenshots
Use Cases
- Generate product prototype images through natural language conversations
- Quickly create visual content within AI workflows
- Perform batch image generation testing with Codex subscription
Best For
- AI developers using DeepSeek Harness
- Researchers needing integrated image generation capabilities
- Creative professionals with OpenAI Codex subscriptions or API keys
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.
