Printful print file requirements and what to ask Sume for
Printful's print-file page: PNG or JPEG, 300 DPI ideal, 75 DPI minimum, sRGB, full bleed. The Sume Image API settings that fit.

What print file does Printful require?
Printful's print-file page, written for posters and canvas wall art, asks for a PNG or JPEG in the sRGB IEC61966-2.1 color profile, full-bleed over the whole print area. It calls 300 DPI the ideal resolution, accepts a minimum of 75 DPI, and says the Design Maker default is 150 DPI.
The page does not give maximum file sizes or exact pixel dimensions; it says to check the file guidelines on the product page and download the print file template. Those product-level numbers are therefore not stated here.
The page's specification
The page describes PNG for designs with transparency or detailed graphics and JPEG for simpler graphics.
| Item | What the page says |
|---|---|
| Formats | PNG or JPEG |
| Ideal resolution | 300 DPI |
| Minimum accepted | 75 DPI, though 300 is strongly recommended |
| Design Maker default | 150 DPI |
| Color profile | sRGB IEC61966-2.1 |
| Coverage | Full-bleed over the entire print area |
| Orientation | Horizontal or vertical |
| Exact dimensions | See the product page and print file template |
Turning DPI into pixels
Pixels equal print inches times DPI. A product that prints 10 by 8 inches would need 3000 by 2400 pixels at 300 DPI and 1500 by 1200 at 150 DPI; take the real inches from Printful's template, not from this example.
On ChatGPT Image 2.5, custom sizes are capped at a 3840 maximum edge and 8,294,400 total pixels, and 3000 by 2400 is 7,200,000, which fits. Larger prints exceed that ceiling, so plan for upscaling outside the generation call or a lower DPI. The Sume docs describe Nano Banana 2 tiers of 0.5K, 1K, 2K and 4K without listing pixel counts on the Image API page, so measure what you get.
What to ask Sume for
Ask for a PNG, the aspect ratio of the print area, and the highest resolution tier the model lists. For an artwork with a cutout design, ChatGPT Image 2.5 can return a transparent background with background: transparent. Sume's output formats are png, jpeg, webp and svg, matching Printful's PNG and JPEG.
``json
{
"model": "google/nano-banana-2",
"prompt": "Poster artwork, full bleed, no border, no text",
"aspect_ratio": "4:5",
"resolution": "4K",
"output_format": "png"
}
``
Tagging the file as sRGB and setting DPI are not request fields on the Image API; do both in your export step and compare with the template. The existing guide AI image for print at 300 DPI covers the same workflow in more depth.
Sources
Related posts
More in Use cases
- Product Hunt launch video: the YouTube link and gallery images
Product Hunt takes video only as a YouTube link and wants 2+ gallery images near 1270x760. Make the video with Sume Timeline and images at a size GPT accepts.
- Product launch week content budget: hero video, 5 Reels, 3 carousels
A launch week with research, one 30 s hero video, five 15 s Reels and three carousels costs about $32 on Sume. Itemised, with the levers that move it.
- Product review Shorts per SKU: vary the focus, not just the name
YouTube allows a review channel when each video has a distinct focus and rejects minimal variation. How to plan a batch of per-product Shorts for that test.
- QA every episode's cliffhanger line with a video inspect transcript
Before you post episode 5, transcribe the render with POST /v1/video-inspect and check the last sentence. $0.01 per audio minute, plus a short Python gate.
Written by Sume