Generate images from text prompts across multiple AI providers.
npx skills add https://github.com/cvenwu/AiFlow --skill baoyu-imagine-cvenwu
Please help me install this Agent Skill. Skill: baoyu-imagine Source: https://github.com/cvenwu/AiFlow/tree/main/skills/baoyu-imagine Command: npx skills add https://github.com/cvenwu/AiFlow --skill baoyu-imagine-cvenwu
Consolidates multi-provider AI image generation into a single workflow, simplifying cross-provider prompts, references, and batching.
Provide a text prompt and optional references to generate an image using the integrated providers.
High-intent search queries and answers about installing and using this skill.
You can consolidate cross-provider AI image generation into a single workflow that validates inputs, resolves model sizes, and handles automatic provider selection across major platforms.
Yes, text-to-image generation supports both reference images to guide visual style and aspect-ratio controls to define output dimensions across all supported providers.
Yes, batch generation from saved prompts enables high-throughput workflows by handling multiple prompt inputs automatically and resolving models for each provider.
Supported providers include Google, OpenAI, Azure, OpenRouter, DashScope, ZAI, MiniMax, Jimeng, Seedream, and Replicate for cross-provider image generation.
The workflow validates your inputs, automatically selects the appropriate provider and model size, applies provider-specific guardrails, and handles errors during image generation.
JimLiuGenerate images from prompts via OpenAI, Google Gemini/Imagen, and DashScope with optional references.
ChegginUpload, store, serve, and manage files in Convex apps.
shenxingyGenerate and edit images via prompt-engineered Gemini Nano Banana requests.
cloudlinessRun 150+ AI apps through a unified CLI with JSON inputs.
