Generate images across multiple AI providers from prompts and reference images.
npx skills add https://github.com/open-fox/agents --skill baoyu-imagine
Please help me install this Agent Skill. Skill: baoyu-imagine Source: https://github.com/open-fox/agents/tree/main/skills/baoyu-imagine Command: npx skills add https://github.com/open-fox/agents --skill baoyu-imagine
Unifies AI image generation across multiple providers from prompts, supporting reference images and flexible sizing to streamline creative workflows.
Generate a sci-fi poster from a prompt, optionally including a reference image, and save the result.
High-intent search queries and answers about installing and using this skill.
Multi-provider AI image generation unifies platforms like Google, OpenAI, and Azure from a single prompt. This skill validates inputs, resolves provider models from environment configs, and handles diverse API outputs to streamline creative workflows.
Yes, reference image workflows are supported across provider ecosystems. You can supply an optional reference image alongside a text prompt and specify flexible sizing to fit varied creative briefs across different AI models.
Batch-file driven workflows enable production-grade AI image generation at scale. By processing batch prompts and applying per-task sizing, this approach scales output efficiently while resolving specific models from environment or EXTEND configs.
Yes, it supports DashScope and MiniMax, alongside OpenRouter, Replicate, Jimeng, and Seedream. It validates your inputs and resolves these specific provider models from your environment and EXTEND configurations to handle the resulting images.
Environment and EXTEND configs are used to resolve provider models for image generation. Configuring these settings allows the skill to validate inputs and successfully route your prompts and reference images to the correct AI provider APIs.
Limitations depend on the specific provider's API capabilities for reference images and flexible sizing. While the skill unifies the workflow, output handling and model resolution are bound by the constraints of each underlying provider ecosystem.
Lutra23Automate anime image generation across multiple AI providers with fallback.
SJTU-IPADSAutomate deterministic image editing tasks on image collections with Pillow.
shenxingyGenerate and edit images via prompt-engineered Gemini Nano Banana requests.
jackspaceOrchestrate synchronized branching and batch commits across multiple Git repositories.
