GIVON AI
← All models

Topaz Astra 2

Astra 2 creatively restores AI video and generates new detail. Its optional prompt limits the source to 450 measured frames. Astra selects output resolution itself, typically 4K; the preliminary quote conservatively uses the 4K rate. Quotes and creation with a spending limit require a previously imported source asset:// URI. Creation without a spending limit also supports secure URL import.

Cost

from 2.4 tokens/frame

VideoProvider: Topaz

Try Topaz Astra 2 in Givon AI

Open a working project for regular creation, or use Playground to inspect the model parameters.

Create in a projectOpen in playgroundUse through API

Use through API

Request fields, constraints, and ready-to-use examples for developers. The user workflow starts above.

Run generation
IDEMPOTENCY_KEY="${IDEMPOTENCY_KEY:-$(uuidgen)}"
curl -X POST https://api.givon.ai/api/v1/generations \
  -H "Authorization: Bearer $GIVON_API_KEY" \
  -H "Idempotency-Key: $IDEMPOTENCY_KEY" \
  -H "Content-Type: application/json" \
  -d '{"type":"video","model":"topaz-astra-2","input":{"prompt":"cinematic drone shot over a city at night","aspectRatio":"auto","sourceVideo":"asset://asset_..."}}'

Input fields

* required
promptprompt

Generation prompt describing the scene, action and direction.

Type
string
Default
—
Allowed
up to 1024 chars
aspectRatioaspectRatio
Type
string
Default
auto
Allowed
auto
Source video*sourceVideo

Asset input for the sourceVideo slot.

Type
string
Default
—
Allowed
video · asset, https, data
providerOptionsproviderOptions
Type
object
Default
—
Allowed
object

Cost

from 2.4 tokens/frame

Quote required; price depends on the source and selected processing settings.

Capabilities

Modesvideo_upscale
Asset slotssourceVideo:video*
Get API key

Where to use this model

AI video generatorImage to video