Generate Images

POST /v1/ai/image

Generate images from text prompts using AI models. This page covers all generation options and model-specific features.

Basic Generation

curl

curl -X POST https://api.vidiking.com/v1/ai/image \
  -H "Authorization: Bearer $VIDIKING_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "A sleek electric car in a showroom with dramatic lighting",
    "model": "flux",
    "width": 1920,
    "height": 1080
  }'

Node.js

const image = await client.ai.generateImage({
  prompt: 'A sleek electric car in a showroom with dramatic lighting',
  model: 'flux',
  width: 1920,
  height: 1080,
});

console.log(image.url);

Python

image = client.ai.generate_image(
    prompt="A sleek electric car in a showroom with dramatic lighting",
    model="flux",
    width=1920,
    height=1080,
)
print(image.url)

Response

{
  "id": "img_abc123",
  "url": "https://cdn.vidiking.com/ai/img_abc123.png",
  "model": "flux",
  "width": 1920,
  "height": 1080,
  "credits_used": 5,
  "created_at": "2025-01-15T10:30:00Z"
}

DALL-E 3

Best for photorealistic scenes and text in images. Cost: $0.18.

curl -X POST https://api.vidiking.com/v1/ai/image \
  -H "Authorization: Bearer $VIDIKING_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "A coffee shop interior with a chalkboard menu that reads DAILY SPECIALS, warm ambient lighting",
    "model": "dall-e-3",
    "width": 1024,
    "height": 1024,
    "style": "vivid"
  }'

DALL-E 3 specific options:

Option	Values	Description
style	natural, vivid	vivid produces more saturated, dramatic images

Flux

Best general-purpose model. Fast and cost-effective. Cost: $0.14.

curl -X POST https://api.vidiking.com/v1/ai/image \
  -H "Authorization: Bearer $VIDIKING_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "Flat lay product photography of skincare bottles on marble surface with dried flowers",
    "model": "flux",
    "width": 1080,
    "height": 1080,
    "style": "natural"
  }'

Stable Diffusion

Best for artistic styles and illustrations. Supports negative prompts. Cost: 4 credits.

curl -X POST https://api.vidiking.com/v1/ai/image \
  -H "Authorization: Bearer $VIDIKING_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "Digital illustration of a fantasy castle on a floating island, concept art style, detailed",
    "model": "stable-diffusion",
    "width": 1024,
    "height": 1024,
    "style": "artistic",
    "negative_prompt": "blurry, low quality, watermark, text"
  }'

Stable Diffusion specific options:

Option	Values	Description
negative_prompt	string	Things to exclude from the image
style	natural, artistic	Guides the overall aesthetic
steps	20-50	Inference steps (higher = more detail, slower)

Supported Sizes

Aspect Ratio	Dimensions	Use Case
1:1	512x512, 1024x1024	Social media, profile images
16:9	1024x576, 1920x1080	Video backgrounds, thumbnails
9:16	576x1024, 1080x1920	Stories, vertical content
4:3	1024x768	Presentations
3:4	768x1024	Portrait-oriented content

Batch Generation

Generate multiple images in a single request. See Bulk Images for details.

Using in Video Timelines

Generated images can be used directly as assets in video timelines:

const bg = await client.ai.generateImage({
  prompt: 'Abstract gradient background',
  width: 1920,
  height: 1080,
});

await client.render({
  timeline: {
    tracks: [{
      clips: [{
        asset: { type: 'image', src: bg.url },
        start: 0,
        length: 10,
      }],
    }],
  },
  output: { format: 'mp4', resolution: 'hd' },
});

Rate Limits

Model	Requests/min
flux	30
stable-diffusion	30
dall-e-3	15