AI Outdoor and Camping Gear Photography API — Scene Variants
A camping gear brand has one clean studio photo of a new tent — pitched on a white backdrop under even lighting — and the product page needs it shown on a mountain ridge at sunset, in a misty forest clearing, and in light rain, to match the three environment clips already planned for paid social. Sending a photographer and the tent itself to three different locations for one product shot costs more than most outdoor brands spend shooting an entire seasonal line, and retailers need the listing photos before a location crew could even be booked. Generating the environment variants from the existing studio photo via API answers "what does this look like on a real trail" without leaving the studio.
Direct answer: a reference-guided image generation API takes the existing studio product photo as input plus a prompt describing the new environment, lighting, or season, and returns a new image that holds the product's shape, color, and material fixed while changing only the surrounding scene — no location shoot, no rebooking a crew per environment.
How Does an API Generate Outdoor Scene Variants From One Studio Shot?
Reference-guided generation anchors the output to the product's fixed geometry and material — the tent's poles, rainfly color, seam placement — then renders the described environment around it. This differs from plain text-to-image generation, which has no source product to match and would produce a plausible-looking tent rather than the exact SKU shipping to retailers, a real risk when a listing photo needs to match the unit a customer receives.
As of October 2026, GenRelay exposes three image models through one endpoint for this workflow:
| Model | Best for | 1K price | 4K price | Editing support |
|---|---|---|---|---|
| Nano Banana Pro | Reference-guided scene changes (environment, lighting, season swap) | $0.030 | $0.042 | Yes, strong consistency |
| Nano Banana 2 | Faster batch variants, slightly lower consistency | $0.020 | $0.036 | Yes |
| GPT-image-2 | Instruction-based edits (remove backdrop, add a logo patch) | $0.014/image | $0.014/image | Yes, instruction-driven |
Nano Banana Pro holds product geometry most reliably across a full environment swap, which matters when a tent's pole structure or a backpack's strap layout needs to stay recognizable against a changing background. GPT-image-2 fits small, targeted edits — removing a studio backdrop seam or adding a brand patch — better than a full scene restyle.
How Do I Call the API to Generate an Environment Variant?
Authenticate with a bearer token and send the source photo plus a prompt describing the environment change. Here's a minimal working request using Nano Banana Pro:
import requests
API_KEY = "YOUR_KEY"
BASE = "https://genrelay.ai/v1"
with open("tent_studio.jpg", "rb") as f:
r = requests.post(
f"{BASE}/images/generations",
headers={"Authorization": f"Bearer {API_KEY}"},
files={"reference_image": f},
data={
"model": "nano-banana-pro",
"prompt": (
"Same tent, same shape and rainfly color, pitched on a "
"mountain ridge at sunset, warm golden light, distant "
"peaks in the background, slight wind texture on fabric."
),
"resolution": "2k",
},
)
job = r.json()
image_url = job["data"][0]["url"]
For a product line with several environments to cover before a seasonal launch, batch the same reference image against a list of prompts rather than calling the endpoint one at a time:
import concurrent.futures
environments = [
"mountain ridge at sunset, golden light, distant peaks",
"misty forest clearing at dawn, soft diffused light",
"light rain, water beading on the rainfly, overcast sky",
]
def generate(prompt):
with open("tent_studio.jpg", "rb") as f:
r = requests.post(
f"{BASE}/images/generations",
headers={"Authorization": f"Bearer {API_KEY}"},
files={"reference_image": f},
data={"model": "nano-banana-pro", "prompt": prompt, "resolution": "2k"},
)
return r.json()["data"][0]["url"]
with concurrent.futures.ThreadPoolExecutor(max_workers=3) as pool:
results = list(pool.map(generate, environments))
Both calls are synchronous — image generation returns a URL directly in the response rather than requiring a polling loop, unlike video generation jobs.
What Does a Full Seasonal Catalog Cost?
Cost scales with resolution and image count, not with how different each environment looks from the studio original. A camping brand with 10 products needing 3 environment variants each — 30 images total — at Nano Banana Pro's 2K price of $0.030 per image costs $0.90 for the full set. Running the same 30 images at 4K for print catalog use costs $1.26 at $0.042 per image. A retailer generating 5 environment options across 6 hero products for a seasonal lookbook — 30 images — costs $0.90 at 2K.
| Scope | Images | Model/resolution | Total cost |
|---|---|---|---|
| Single product, 3 environments | 3 | Nano Banana Pro, 2K | $0.09 |
| 10-product catalog, 3 environments each | 30 | Nano Banana Pro, 2K | $0.90 |
| Same set, print-quality | 30 | Nano Banana Pro, 4K | $1.26 |
| 6 hero products × 5 environments | 30 | Nano Banana Pro, 2K | $0.90 |
At this price point, generating a full environment lineup for a catalog costs less than a single studio lighting setup change, which is why most outdoor brands generate several options rather than committing a location shoot budget to one guess.
How Do I Keep the Product Recognizable Across Variants?
Keep every prompt change scoped to environment, lighting, season, or weather — never the product's shape, color, or material — since those are exactly the elements reference-guided generation is designed to hold fixed. If a variant starts drifting (a pole bends wrong, a fabric color shifts), the fix is almost always a prompt that's too aggressive about "reimagining" the product rather than relocating it; rephrase toward "same product, same shape and color, change only the surrounding scene."
FAQ
Does the API support video, not just photos, for outdoor product showcases?
Yes — GenRelay's video models (Veo 3.1 Lite, Grok Imagine) can turn a still product photo into a short environment clip with camera motion. See the outdoor and camping gear video API guide for pricing and code.
Can I edit a specific detail instead of restyling the whole scene?
Yes — GPT-image-2 handles instruction-based edits like "remove the studio backdrop" or "add a brand patch to the strap" at $0.014 per image, cheaper than a full Nano Banana Pro restyle when the change is small.
Will the generated image pass as a real field photo to a customer comparing it to the product they receive?
It should match the product's real shape, color, and material closely enough for marketing use, but disclose AI-generated marketing images per your local advertising rules — this is a legal, not technical, requirement.
What image formats does the API accept as a reference?
JPEG and PNG, up to 10MB. Larger source files should be downsized before upload; resolution of the output is controlled by the resolution parameter, not the input file size.
Is there a rate limit on reference-guided generation calls?
Yes, scoped per API key — check response headers for your current limit, and use a thread pool with a small max_workers count (3–5) for batch jobs rather than firing all requests simultaneously.
Explore the Nano Banana Pro model page for full parameter docs, or read the AI image editing API guide for more on GPT-image-2's instruction-based edits.