omniroute-image

Route OpenAI-compatible image generation, editing, and variation requests through a single endpoint.

44.0k|5.9k|Updated Feb 13, 2026
One-click install
npx skills add https://github.com/diegosouzapw/OmniRoute --skill omniroute-image
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: omniroute-image
Source: https://github.com/diegosouzapw/OmniRoute/tree/main/skills/omniroute-image
Command: npx skills add https://github.com/diegosouzapw/OmniRoute --skill omniroute-image

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

OmniRoute Image generation removes the hassle of manually switching between image providers by routing your OpenAI-compatible image requests through a single endpoint with automatic fallback when a provider fails or a model is unavailable.

Core Features & Use Cases

  • Text-to-image generation: Create images from prompts using the OpenAI-style /v1/images/generations endpoint.
  • Image edits with masks: Modify existing images via the /v1/images/edits endpoint for targeted changes.
  • Variations: Generate new versions of an image using the /v1/images/variations endpoint.
  • Use case: You want a set of consistent product mockups—generate from a prompt, then iterate by editing masked regions, and finally produce variations for multiple options.

Quick Start

Send a POST request to $OMNIROUTE_URL/v1/images/generations with Authorization: Bearer $OMNIROUTE_KEY and a prompt, model, and size payload to generate images with fallback.

Frequently Asked Questions about omniroute-image

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I use an OpenAI compatible API for image generation with automatic fallback?

Image generation with automatic fallback is handled by routing OpenAI-compatible requests to a single OmniRoute endpoint, which requires OMNIROUTE_URL and OMNIROUTE_KEY credentials to manage provider unavailability.

Can I edit existing images with masks using an OpenAI-style endpoint?

Masked image edits are supported through the /v1/images/edits endpoint, allowing you to modify existing images for targeted changes when provider availability varies across models like DALL-E and Stable Diffusion.

Does OmniRoute support text-to-image generation across multiple models like DALL-E and Stable Diffusion?

Text-to-image generation supports routing across DALL-E, Stable Diffusion, Flux, and Imagen, automatically falling back to another provider if a requested model is unavailable or fails.

What happens when an image provider fails or returns a policy violation?

The gateway provides auto-fallback when a provider fails, and explicitly handles invalid size, policy violations, and provider unavailability responses to ensure your image request completes properly.

How do I discover which image models are available before sending a generation request?

You can discover available image models by querying the /v1/models/image endpoint, which lists the active providers and models you can specify in your subsequent text-to-image payload.