0crUpgrade

Image generation API

Tencent Vega Image

Tencent WAND Vega Image 1.5 Pro: text-to-image and editing at 1K, 2K or 4K, in 1:1, 16:9, 9:16, 3:4 or 4:3.

Provider: Tencent2 models

Available models

Model keyDisplay nameCapabilityAtlas Cloud slug
vega_1_5_pro_t2iVega Image 1.5 Pro T2Itext-to-imagetencent/vega-image-1.5-pro/text-to-image
vega_1_5_pro_editVega Image 1.5 Pro Editedittencent/vega-image-1.5-pro/edit

Endpoint

POST /api/generate

Request body

ParameterTypeRequiredDescription
modelKeystringOne of the model keys listed above
promptstringText description of the image to generate
inputUrlstringInput image URL (for edit/i2i models)
aspectRatiostring"1:1", "16:9", "9:16", etc.
imageQualitystring"Low", "Medium", "High"
styleRefstring | string[]Style reference image URL(s)
charRefstring | string[]Character reference image URL(s)
brandIdstringBrand DNA ID for brand-consistent generation

Code example

curl -X POST https://api.oyefilmy.com/api/generate \
  -H "Authorization: Bearer of_live_YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "modelKey": "vega_1_5_pro_t2i",
    "prompt": "A solitary penguin inside a gigantic brutalist concrete structure in an endless white desert, sharp sunlight, minimalist architectural photography"
  }'

Response

{
  "success": true,
  "predictionId": "pred_abc123...",
  "status": "processing",
  "model": "tencent/vega-image-1.5-pro/text-to-image",
  "creditCost": 5
}

Set resolution to 1K, 2K or 4K. Edit takes the picture to edit as inputUrl or the first of refImageUrls, and more pictures as references; every picture sent adds to the price. Tencent does not accept photos of real people as references.

Related