Generate images from text prompts via a multi-provider CLI.
npx skills add https://github.com/freestylefly/canghe-skills --skill canghe-image-gen
Please help me install this Agent Skill. Skill: canghe-image-gen Source: https://github.com/freestylefly/canghe-skills/tree/main/skills/canghe-image-gen Command: npx skills add https://github.com/freestylefly/canghe-skills --skill canghe-image-gen
The skill unifies AI-based image generation across multiple providers (OpenAI, Google Gemini, DashScope, and Canghe) into a single, scriptable CLI, eliminating the need to switch tools or rewrite prompts for each provider.
Provide a prompt and an output path, then run the CLI to generate and save the image to the specified file.
High-intent search queries and answers about installing and using this skill.
You can generate AI images from the command line by providing a prompt and output path to the CLI. It unifies text-to-image generation across OpenAI, Google Gemini, DashScope, and Canghe providers, automatically detecting the provider based on available API keys.
Yes, the CLI supports reference images and aspect ratios for AI image generation. You provide these parameters with your text prompt, and the tool validates inputs and handles prompt input from files or stdin to create your specified visual output.
Yes, the CLI supports automatic provider detection based on available API keys. It routes requests to OpenAI, Google Gemini, DashScope, or Canghe without requiring you to manually switch tools or rewrite prompts for each provider.
The best way to automate batch AI image generation is using a unified CLI that supports optional parallel generation across multiple providers. It eliminates the need to switch tools or rewrite prompts, applying safe retry logic to ensure robust image yields.
You can pass long text prompts to the CLI image generation script by reading input from files or stdin. The tool validates these inputs and handles prompt input seamlessly, ensuring the provider receives the correct text-to-image instructions.
Multi-provider AI image generation fails when API keys are missing because the CLI relies on these credentials for automatic provider detection. Without the correct API keys for OpenAI, Gemini, DashScope, or Canghe, the tool cannot route or authenticate the image generation requests.
chengyihuaGenerate AI images from text prompts via OpenAI, Google, or DashScope.
michaelboedingGenerate AI videos from prompts and reference media via Vertex AI or AI Studio.
guanyangAutomate Gemini Web text and image generation with session management.
neo-unicornGenerate AI images from text prompts and reference images via CLI.
