-
Notifications
You must be signed in to change notification settings - Fork 2.9k
AionUi Image Generation Tool Model Configuration Guide
This guide shows how to enable AionUi's image generation tool and pick a backend model. AionUi can drive image generation through several platforms โ both chat-completion-style (Gemini, OpenRouter) and dedicated images APIs (OpenAI, Stability AI, DashScope, Together AI).
AionUi's image tool supports two API shapes and routes each provider to the right adapter automatically:
| Shape | Used by | Endpoint |
|---|---|---|
| Chat Completion (multimodal) | Gemini, Gemini (Vertex AI), OpenRouter, AntigravityTools | OpenAI-compatible /v1/chat/completions returning image parts |
| Dedicated Images API | OpenAI, Stability AI, Alibaba DashScope, Together AI |
/v1/images/* returning b64_json
|
Only models that AionUi's allowlist recognizes will appear in the picker โ this prevents accidentally selecting a text-only model. The allowlist matches both the platform (or base URL) and the model name pattern (image, dall-e, flux, stable, sd<n>, wanx, imagen, banana, imagine, etc.).
๐ก If your platform has no allowlisted image model yet, AionUi auto-injects a sensible default (see below) so the feature still works out of the box.
The fastest, cheapest, and easiest setup.
- Visit https://aistudio.google.com/
- Sign in with your Google account
- Create a new API Key
- Settings โ Models โ Add Model
- Select Gemini
- Paste your API Key, save

- Settings โ Tools โ Image Generation
- Toggle on
- From the model dropdown pick
gemini-2.5-flash-image-preview(auto-injected if Gemini has no other image model in your config) - Save

OpenRouter aggregates many image-gen models. Most are paid; AionUi auto-adds a free Gemini option as a fallback.
- Sign in at https://openrouter.ai/
- Create a key at https://openrouter.ai/keys โ copy it (shown only once)

- Settings โ Models โ Add Model
- Select OpenRouter, paste the key, save
- Settings โ Tools โ Image Generation
- Pick any allowlisted OpenRouter model in the dropdown
- Default fallback:
google/gemini-2.5-flash-image-preview(free)
๐ธ Most non-Gemini OpenRouter image models are paid โ check pricing on OpenRouter before committing.
These work the same way: add the platform under Settings โ Models, then pick an allowlisted model in Settings โ Tools โ Image Generation.
| Platform | API shape | Recognized model patterns | Notes |
|---|---|---|---|
| Gemini | Chat |
*-image-*, gemini-*image*
|
Default: gemini-2.5-flash-image-preview
|
| Gemini (Vertex AI) | Chat | same as Gemini | Enterprise variant |
| OpenRouter | Chat |
image, dall-e, flux, stable, etc. |
Default: google/gemini-2.5-flash-image-preview
|
| AntigravityTools | Chat | image-capable models | Default: gemini-3-pro-image-1x1
|
| OpenAI | Images API |
gpt-image-*, dall-e-*
|
Requires images-API access |
| Stability AI | Images API |
stable-*, sd<n>, ultra, core
|
Requires Stability key |
| Alibaba DashScope | Images API |
wanx-*, image-*
|
Requires DashScope key |
| Together AI | Images API | flux-* |
Requires Together key |
-
Open a conversation with any tool-capable model
-
Ask "what tools do you have?" โ
image-generationshould appear in the list
-
Try a generation prompt, e.g.:
Generate a 1024ร1024 blue neon cyberpunk city nightscape

A: gemini-2.5-flash-image-preview โ fast, free with a Gemini API key, decent quality.
A: AionUi only lists allowlisted image models. Either the model name doesn't match the pattern (e.g., image, flux, dall-e, stable, sd<n>, wanx) or the platform/base URL isn't recognized. Rename the model entry to include a recognized keyword, or use one of the supported platforms above.
A: Make sure (1) image generation is toggled on in Settings โ Tools, (2) a model is selected and saved, (3) you start a fresh conversation after saving.
A: Check the key is copied without whitespace and that the corresponding platform account is active and has billing/quota set up where required.
A: Usually a network timeout, expired token, or quota exhaustion on the upstream platform. Check the platform's dashboard.
A: Settings โ Tools โ Image Generation โ Model โ dropdown lists every allowlisted model from your configured platforms.
- OpenRouter: https://openrouter.ai/ ยท models https://openrouter.ai/models
- Google AI Studio: https://aistudio.google.com/
- Stability AI: https://platform.stability.ai/
- Alibaba DashScope: https://dashscope.console.aliyun.com/
- Together AI: https://www.together.ai/
Need Help?
- ๐ Report Issues
- ๐ฌ Community Discussions
- ๐ Complete Documentation
Welcome to the comprehensive AionUi documentation! Find everything you need to configure, use, and master AionUi.
- โ๏ธ LLM Configuration
- ๐ค Multi-Agent Mode Setup
- ๐จ Image Generation Setup
- ๐งฉ Assistant Configuration
- ๐ MCP Configuration
- ๐ป WebUI Configuration
- ๐ Remote Internet Access
- ๐ค DingTalk Bot Setup
- โฐ Scheduled Tasks Guide
- ๐ ๏ธ AI Assistants & Skills Ecosystem
- ๐ Preview Panel Guide
- ๐ File Management
- ๐ Excel Smart Processing
- ๐ Smart Information Gathering
- ๐ Local Knowledge Base Application
- โ AI Learning Assistant
- โ๏ธ Writing & Content Creation
- ๐ Getting Started
- โ๏ธ LLM Configuration
- ๐ค Multi-Agent Mode Setup
- ๐งฉ Assistant Configuration
- ๐จ Image Generation
- ๐ MCP Configuration
- ๐ WebUI Configuration
- โฐ Scheduled Tasks
- ๐ ๏ธ AI Assistants & Skills
- ๐ Preview Panel
- โ FAQ