Topaz Gigapixel API reference
Faithful, generative or transparent upscales to 2K, 4K or 8K
Call Topaz Gigapixel from your own code with one PopNow API key. Below are the exact model IDs to send, every input field the model accepts, what each request costs in USD, and a request you can paste into a terminal.
At a glance
- Made by
- Topaz Labs
- Output
- Image
- From
- $0.12 USD per image
- Typical time
- about 21 s
- Model IDs
Prices are in USD, charged to your separate API wallet. A task reserves the maximum possible charge when accepted and settles actual usage on completion; any remainder is released. Failed tasks are not charged. Call POST /api/v1/jobs/quote for an exact quote before running.
Upscale Image
topaz/gigapixel/upscale
Price
| Option | USD |
|---|---|
preset = cgi, resolution = 2k | $0.12 per image |
preset = cgi, resolution = 4k | $0.12 per image |
preset = detail, resolution = 2k | $0.12 per image |
preset = detail, resolution = 4k | $0.12 per image |
preset = high_fidelity_v3, resolution = 2k | $0.12 per image |
preset = high_fidelity_v3, resolution = 4k | $0.12 per image |
preset = low_resolution_v2, resolution = 2k | $0.12 per image |
preset = low_resolution_v2, resolution = 4k | $0.12 per image |
preset = standard_v2, resolution = 2k | $0.12 per image |
preset = standard_v2, resolution = 4k | $0.12 per image |
preset = text_refine, resolution = 2k | $0.12 per image |
preset = text_refine, resolution = 4k | $0.12 per image |
preset = transparent, resolution = 2k | $0.12 per image |
preset = transparent, resolution = 4k | $0.12 per image |
preset = wonder_3_5, resolution = 2k | $0.12 per image |
preset = wonder_4, resolution = 2k | $0.12 per image |
preset = recover_3, resolution = 2k | $0.24 per image |
preset = redefine, resolution = 2k | $0.24 per image |
preset = standard_max, resolution = 2k | $0.24 per image |
preset = cgi, resolution = 8k | $0.36 per image |
preset = detail, resolution = 8k | $0.36 per image |
preset = high_fidelity_v3, resolution = 8k | $0.36 per image |
preset = low_resolution_v2, resolution = 8k | $0.36 per image |
preset = standard_v2, resolution = 8k | $0.36 per image |
preset = text_refine, resolution = 8k | $0.36 per image |
preset = transparent, resolution = 8k | $0.36 per image |
preset = wonder_3_5, resolution = 4k | $0.36 per image |
preset = wonder_4, resolution = 4k | $0.36 per image |
preset = recover_3, resolution = 4k | $0.6 per image |
preset = redefine, resolution = 4k | $0.6 per image |
preset = standard_max, resolution = 4k | $0.6 per image |
preset = wonder_3_5, resolution = 8k | $1.08 per image |
preset = wonder_4, resolution = 8k | $1.08 per image |
preset = recover_3, resolution = 8k | $2.04 per image |
preset = redefine, resolution = 8k | $2.04 per image |
preset = standard_max, resolution = 8k | $2.04 per image |
Parameters
| Field | Type | Default | Allowed | What it does |
|---|---|---|---|---|
image_urlRequired | string | — | — | The image to enlarge: JPEG, PNG or WebP. Framing and aspect ratio are kept; only the pixel count goes up. Use a PNG with an alpha channel for the transparent preset. |
presetOptional | string | standard_v2 | standard_v2, high_fidelity_v3, low_resolution_v2, cgi, text_refine, wonder_4, wonder_3_5, recover_3, standard_max, redefine, detail, transparent | Which Topaz Gigapixel model to run. Precise presets enlarge without inventing content: standard_v2 (general photos), high_fidelity_v3 (already sharp, high-resolution sources), low_resolution_v2 (small or heavily compressed images), cgi (illustrations and renders), text_refine (text, logos and graphics). Generative presets rebuild detail and cost more: wonder_4 (all-purpose enhancement), wonder_3_5, recover_3 (badly degraded photos), standard_max, redefine (adds new detail) and detail (realistic skin and faces in AI images). transparent enlarges a PNG while keeping its alpha channel and always returns PNG. |
resolutionOptional | string | 4k | 2k, 4k, 8k | Output size: a pixel budget of about 4 MP (2k), 16.8 MP (4k) or 67 MP (8k) with the source aspect ratio kept. The price depends on this tier and the preset. |
output_formatOptional | string | jpeg | jpeg, png | File type of the returned image. png avoids another round of lossy compression but is several times larger. The format does not change the price. |
Example request
This request runs as it is; any field you leave out uses its default. Put your key in POPNOW_API_KEY first.
The example uses PopNow sample files in image_url. Replace them with your own public HTTPS links, uploads or saved assets.
curl -X POST "https://api.popnow.ai/api/v1/jobs/createTask?wait=60" \
-H "Authorization: Bearer $POPNOW_API_KEY" \
-H "Content-Type: application/json" \
-H "Idempotency-Key: $(uuidgen)" \
-d '{
"model": "topaz/gigapixel/upscale",
"input": {
"image_url": "https://media.popnow.ai/influencer/examples/marco.webp",
"resolution": "4k",
"preset": "standard_v2"
}
}'The response carries a taskId straight away. Read the result with GET /api/v1/jobs/recordInfo, or add callBackUrl to be notified.
curl "https://api.popnow.ai/api/v1/jobs/recordInfo?taskId=TASK_ID_FROM_CREATE_TASK" \
-H "Authorization: Bearer $POPNOW_API_KEY"