AionUi Image Generation Tool Model Configuration Guide

AionUi Image Generation Tool Model Configuration Guide

This guide will help you configure multiple image generation models:

1. Gemini official 2.5 Flash Image Preview model configuration
2. OpenRouter platform paid image model configuration
3. Model selection and usage recommendations

English | 简体中文

---

1. Gemini Official Image Model Configuration (Recommended)

1.1 Get Gemini API Key

1. Visit Google AI Studio: https://aistudio.google.com/
2. Log in with your Google account.
3. Create a new API Key on the API Keys page.

1.2 Bind Gemini in AionUi

1. Open AionUi → Settings → LLM Settings.
2. Add new model, select "Gemini" platform.
3. Enter Gemini API Key and save.

1.3 Configure Gemini Image Model

1. Open AionUi → Settings → Tools Configuration → Image Generation Tool.
2. Select Gemini model that supports image generation (e.g., gemini-2.5-flash-image-preview) from Gemini platform.
3. If Gemini platform has no image models, the system will automatically add gemini-2.5-flash-image-preview as default option.
4. Confirm the model supports image generation functionality and save configuration.

---

2. OpenRouter Platform Image Model Configuration

2.1 Get OpenRouter API Key

1. Visit https://openrouter.ai/, register and log in with Google / GitHub / email.
2. Open Keys page: https://openrouter.ai/keys.
3. Click "Create Key", name your key (e.g., "AionUi"), create and copy to save (only shown once).

Important: Most image models on OpenRouter platform require purchasing credits. However, the system will automatically add google/gemini-2.5-flash-image-preview as a free option (if no other image models exist on the platform).

2.2 Bind OpenRouter in AionUi

1. Open AionUi → Settings → LLM Settings.
2. Add new model, select "OpenRouter" platform.
3. Paste the API Key copied in the previous step into the key input field and save.

2.3 Configure Image Model

1. Open AionUi → Settings → Tools Configuration → Image Generation Tool.
2. In model selection, choose models with image generation capabilities from OpenRouter platform:
   • Look for models containing keywords like image, dall-e, midjourney, stable-diffusion, flux, diffusion, imagen
   • If OpenRouter platform has no image models, the system will automatically add google/gemini-2.5-flash-image-preview as free option
   • Select image generation models suitable for your needs
   • Pay attention to model pricing and usage limits

---

3. Verify Configuration Success

1. Return to chat, select LLM that supports tool calling to start new conversation.
2. Input "What tools do you have?" should show tool list including image-generation.
3. Try sending image generation command, e.g.: "Generate a 1024×1024 blue neon cyberpunk city nightscape" to verify.

---

4. Frequently Asked Questions

4.1 Model Selection Recommendations

In image generation tool settings, you need to select an image model. Choose appropriate model based on your needs:

By Quality:

• High Quality: Recommend gemini-2.5-flash-image-preview (Gemini official, free)
• Professional Grade: Choose commercial models like DALL-E series, Midjourney, etc. (paid)
• Open Source: Choose open-source models like Stable Diffusion, Flux series, etc.

By Speed:

• Fast Generation: Choose Gemini image models, Flux series, etc.
• Standard Speed: Most commercial image generation models

By Cost:

• Free Options: gemini-2.5-flash-image-preview (Gemini official) or google/gemini-2.5-flash-image-preview (OpenRouter)
• Sufficient Budget: Choose commercial image generation models for best quality (DALL-E, Midjourney, etc.)
• Balanced Cost-Performance: Choose cost-effective image generation models (Flux, Stable Diffusion, etc.)

4.2 Configuration Issues

• Invalid API Key: Check if key is correctly copied and activated
• Model Unavailable: Confirm model name is correct and platform configuration is correct
• Generation Failed: Check network connection and ensure sufficient account balance

4.3 Usage Issues

• Tools Not Showing: Confirm image model is correctly configured, restart AionUi and retry
• Poor Generation Quality: Try adjusting prompt descriptions or switch to other image models
• Slow Generation Speed: Choose models with faster generation speed or check network connection

4.4 Platform Support Information

Currently Supported Platforms:

• Gemini: Official Gemini platform, supports image models like gemini-2.5-flash-image-preview
• OpenRouter: Supports various image generation models (DALL-E, Midjourney, Flux, Stable Diffusion, etc.)
• New API: If New API gateway provides image generation models, they can also be used
• Custom Platform: Any model configured through custom platform with image generation keywords in model name can be used

Supported Image Model Keywords: The system automatically recognizes model names containing these keywords: flux, diffusion, stabilityai, sd-, dall, cogview, janus, midjourney, mj-, imagen, image, etc.

Auto-Add Mechanism:

• Gemini platform: If no image models exist, system automatically adds gemini-2.5-flash-image-preview
• OpenRouter platform: If no image models exist, system automatically adds google/gemini-2.5-flash-image-preview as free option

We are continuously developing support for more platforms, including ModelScope, Hugging Face and other open-source model platforms. Stay tuned!

---

5. Reference Links

• OpenRouter: https://openrouter.ai/ | https://openrouter.ai/models
• Google AI Studio: https://aistudio.google.com/
• AionUi Official Documentation: Check latest configuration instructions