Generate images based on text prompts
Authenticate using Bearer token. Get your API Key from the WeryAI Console.
Example: Authorization: Bearer sk-xxxxxxxxxxxxxxxx
Model Key. Supported models for text-to-image:
| Model Name | Model Key |
|---|---|
| WeryAI 123 Image 2.0 | WERYAI_IMAGE_2_0 |
| WeryAI Image 1.0 | WERYAI_IMAGE_1_0 |
| Nano Banana Pro | CHATBOT_GEMINI_3_PRO_IMAGE_PREVIEW |
| Nano-banana | GEMINI_2_5_FLASH |
| GPT Image 1.5 | GPT_IMAGE_1_5 |
| Seedream 4.5 | SEEDREAM_4_5 |
| Seedream 4.0 | SEEDREAM_4 |
| Wan2.6 | WAN_2_6 |
| Wan2.5 | WAN_2_5 |
| Dreamina 4.0 | DREAMINA_4 |
| Dreamina 3.1 | DREAMINA |
| Dreamina 3.0 | DREAMINA_3 |
| Qwen Image | QWEN |
| Flux | FLUX |
| Gpt Image Mini | GPT_IMAGE_1_MINI |
| Grok 2 Image | GROK_2_IMAGE |
| Imagen4 | IMAGE4 |
"WERYAI_IMAGE_2_0"
Positive text prompt
1 - 2000"A beautiful sunset over the ocean"
Image aspect ratio (e.g., 9:16, 1:1, 16:9, etc.)
"16:9"
Negative text prompt (exclude unwanted elements)
1000"blurry, low quality"
Number of images to generate
x >= 11
Resolution
"1080p"
Whether to use web search to enhance prompts
Callback URL where results will be sent when task completes
"https://your-server.com/webhook"
Caller ID (for business association)