Image Generation
AI Supreme Council can generate images from text descriptions using AI image generation models. Describe what you want, and the model creates an image directly in your chat.
Supported Providers
| Provider | Model | Notes |
|---|---|---|
| OpenAI | DALL-E 3 | High quality, 1024x1024, revised prompts |
| xAI | Grok 2 Image | Fast generation, returns URL or base64 |
| OpenRouter | Various | Access to multiple image generation models |
You need an API key for the provider you want to use. Image generation is a paid feature -- free-tier models do not include image generation.
How It Works
The platform automatically detects image generation requests from your message text. You can trigger image generation in two ways:
1. Natural Language (Auto-Detection)
Simply describe what you want in a way that implies image creation:
- "Generate an image of a sunset over mountains"
- "Create an image of a futuristic city"
- "Draw a cat wearing a top hat"
The platform looks for phrases like "generate image", "create image", or "draw" at the start of your message.
2. The /image Command (Explicit Trigger)
Use the /image command followed by your description:
/image a serene Japanese garden with cherry blossoms in spring
This is the most reliable way to trigger image generation, especially for prompts that might not be auto-detected.
Trigger Patterns
The following patterns at the start of your message trigger image generation:
| Pattern | Example |
|---|---|
/image ... | /image a mountain landscape at dawn |
generate image of ... | generate an image of a robot |
create image of ... | create an image of a cozy cabin |
draw ... | draw a dragon flying over a castle |
If your message is not being detected as an image request, prefix it with /image to ensure it triggers image generation.
Generated Images
When an image is generated successfully:
- The image appears inline in the chat, embedded in the assistant's response
- If the provider returned a revised prompt (DALL-E 3 does this), it is displayed above the image so you can see how the model interpreted your request
- The image is stored in chat history and will appear when you reload the conversation
Downloading Images
Right-click (or long-press on mobile) the generated image and select "Save image as..." to download it to your device. Generated images are standard web images (PNG or JPEG) that can be saved like any other image.
Tips for Effective Prompts
- Be specific: "A golden retriever puppy playing in autumn leaves, warm sunlight, shallow depth of field" produces better results than "a dog"
- Specify style: Add art style descriptors like "oil painting", "watercolor", "photorealistic", "3D render", "pixel art"
- Include composition details: Mention lighting, angle, mood, and background
- Describe what you want, not what you don't want: Positive descriptions work better than "no X" or "without Y"
- Use the revised prompt: DALL-E 3 shows its revised interpretation -- use it to understand how to write better prompts
Provider Comparison
| Feature | DALL-E 3 (OpenAI) | Grok 2 Image (xAI) |
|---|---|---|
| Resolution | 1024x1024 | Varies |
| Revised Prompt | Yes (shown above image) | No |
| Speed | ~10-15 seconds | ~5-10 seconds |
| Text in Images | Good | Varies |
| Photorealism | Excellent | Good |
| API Key | OpenAI key required | xAI key required |
Error Handling
If image generation fails, an error message is displayed in the chat. Common issues:
- No API key: Set your API key for the selected provider in the config panel
- Unsupported provider: Switch to OpenAI, xAI, or OpenRouter -- not all providers support image generation
- Content policy: The provider rejected the prompt due to content policy violations
- Rate limiting: Wait a moment and try again
Image generation is only available when your bot's active provider supports it (OpenAI, xAI, or OpenRouter). If you are using Anthropic, Gemini, or Ollama, image generation commands will not work.