Image Generation

Generate an Image

POST/v1/images/generations

Generate an image following instructions given by the prompt.

Compatible with OpenAI Image Generation API with some limitations (cf column "support" in the Request Body table).

---

Request

curl -X POST https://api.ig1.ai/v1/images/generations \
  -H "Authorization: Bearer $IG1AI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "qwen-image",
    "prompt": "An image of an Iguana in the street of Paris, Neon theme.",
    "quality": "low",
    "size": "1280x720",
    "output_format": "png"
  }'

Request body

Parameter	Type	Required	Support	Description
prompt	string	✅	✅ Full	Input prompt
model	string	✅	✅ Full	qwen-image or qwen-image-pe
output_format	string		✅ Full	png, jpeg, or webp
quality	string		✅ Full	low, medium, standard (=medium), high, hd (=high), auto (=medium)
size	string		✅ Full	Any resolution up to 2 Megapixels (e.g. 1024x1024, 1920x1080)
n	integer		⚠️ Partial	Only 1 accepted (0 mapped to 1)
response_format	string		⚠️ Partial	Only b64_json supported. url not supported
background			❌ Ignored
moderation			❌ Ignored
output_compression			❌ Ignored
partial_images			❌ Ignored
stream			❌ Ignored
style			❌ Ignored
user			❌ Ignored

---

Response

{
  "created": 1773677269,
  "data": [
    {
      "b64_json": "<BASE64_ENCODED_IMAGE_DATA>"
    }
  ],
  usage": {
    "total_tokens": 0,
    "input_tokens": 0,
    "output_tokens": 31457280,
    "input_tokens_details": {
      "text_tokens": 0,
      "image_tokens": 0
    }
  },
  "output_format": "png",
  "quality": "low",
  "size": "1280x720"
}

---

Prompt Enhancement

Use model qwen-image-pe to automatically refine your prompt via Qwen3.5-397B-A17B before generation. Prompt enhancement override your prompt with more details and elements that fit perfectly with model's expectations to generate a better image.

info

Prompt enhancement tokens are charged under the Qwen3.5-397B-A17B model.