Square product photo to a 4:1 banner: reference plus aspect_ratio
Turn a 1:1 photo into a 4:1 banner with Nano Banana 2.1 on Sume: input_references plus an explicit aspect_ratio of 4:1, not auto. $0.10 at 1K. Body and gotchas.

To turn a square product photo into a wide banner, send the photo in input_references and set aspect_ratio to 4:1 yourself. auto is for matching the reference shape, so on this job it would give you the square back. On Sume the call costs $0.10 at 1K and $0.15 at 2K with Nano Banana 2.1.
The rule from the docs
On edit and image-to-image calls, Sume's docs say to use aspect_ratio: "auto" to match the reference, and that omitting the field is not the same as auto. For a different shape, name the ratio. Nano Banana 2.1 lists 4:1, so it is accepted.
| You send | What it asks for | Use it when |
|---|---|---|
| auto | Match the reference shape | You want a same-shape edit |
| omitted | Not the same as auto | Avoid on edits |
| 4:1 | A 4:1 output | You want a banner from a square photo |
Request
Reference URLs must be public HTTPS. Sume rejects localhost, private-network and non-HTTPS URLs before submission.
import os, requests
body = {
"model": "google/nano-banana-2.1",
"prompt": "Extend this product photo into a wide banner: keep the product, add soft studio background left and right",
"aspect_ratio": "4:1",
"resolution": "1K",
"input_references": [{"type": "image_url", "image_url": {"url": "https://example.com/product-square.jpg"}}],
}
r = requests.post(
"https://api.sume.com/v1/images",
headers={"Authorization": f"Bearer {os.environ['SUME_API_KEY']}"},
json=body, timeout=60,
)
print(r.status_code) # 200 = image body, 202 = job envelope
if r.status_code == 200:
out = r.json()
print(out["data"][0]["url"], out["usage"]["cost"])What it costs
| Resolution | Price per image | Ten banners |
|---|---|---|
| 0.5K | $0.075 | $0.75 |
| 1K | $0.10 | $1.00 |
| 2K | $0.15 | $1.50 |
| 4K | $0.20 | $2.00 |
Gotchas
- Check the product edges: the model fills the new left and right space, and may alter fine print on the product, so compare against the source.
- The reference does not make a model that lacks
4:1take it: Nano Banana Pro does not list the ratio. - If the descriptor for
input_referencesshowsmax: 0the model is text-only; Nano Banana 2.1 takes references.
Sources
Related posts
More in Use cases
- Support answer video with an avatar: 25 seconds with a product shot
A 25-second support answer video costs $4.60 on Standard, $6.125 on Plus and $13.75 on Max. A product image adds a small per-second premium.
- Swap a Product in an Existing Clip With Omni Flash Video Edit: Cost
Edit a finished clip instead of regenerating it with Gemini Omni Flash 1.1 video-to-video on Sume: what you send, what you cannot, and prices for 3, 5 and 10 s.
- Talking Still Testimonial: VEED Fabric 1.0 or H3 Max Lip Sync, Priced
Make a 14.8-second talking-head clip from a still and a TTS line on Sume: Fabric at 720p versus MiniMax H3 Max Lip Sync at 768p, with each price multiplied out.
- 30 voice-over variants for an ad test cost $0.171 on Sume TTS
Six hooks, five voices, 120 characters each: 3,600 characters is $0.171 at Sume's $0.0475 per 1,000. MAI-Voice-2.1-Flash lists the same text at $0.054.
Written by Sume