Image generation API
Imagen / Google
Google's Imagen 3/4 and Gemini native image generation — state-of-the-art photorealism and text rendering.
Provider: Google6 models
Available models
| Model key | Display name | Capability | Atlas Cloud slug |
|---|---|---|---|
imagen_4_ultra | Imagen 4 Ultra | text-to-image | google/imagen4-ultra |
imagen_4 | Imagen 4 | text-to-image | google/imagen4 |
imagen_4_fast | Imagen 4 Fast | text-to-image | google/imagen4-fast |
imagen | Imagen 3 | text-to-image | google/imagen3 |
imagen_2 | Imagen 3 Fast | text-to-image | google/imagen3-fast |
gemini_img | Gemini Image | text-to-image | gemini-3.1-flash-image |
Endpoint
POST /api/generateRequest body
| Parameter | Type | Required | Description |
|---|---|---|---|
modelKey | string | ✓ | One of the model keys listed above |
prompt | string | ✓ | Text description of the image to generate |
inputUrl | string | Input image URL (for edit/i2i models) | |
aspectRatio | string | "1:1", "16:9", "9:16", etc. | |
imageQuality | string | "Low", "Medium", "High" | |
styleRef | string | string[] | Style reference image URL(s) | |
charRef | string | string[] | Character reference image URL(s) | |
brandId | string | Brand 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": "imagen_4",
"prompt": "A cozy Japanese izakaya interior with warm lantern light, steam rising from ramen bowls"
}'Response
{
"success": true,
"predictionId": "pred_abc123...",
"status": "processing",
"model": "google/imagen4-ultra",
"creditCost": 5
}Imagen 4 Ultra delivers the highest quality. Imagen 4 Fast is optimized for speed. Gemini Image uses Gemini's native multimodal generation.

