Gooseworks field notes: ai product photos for ads
product photosai photographyad creative

AI product photos for ads and product pages

Turn the product images you already have into studio, lifestyle and on-model photos that keep the product accurate, then approve the ones you want to use in ads.

Gooseworks
Gooseworks · 1 min read

Ads and product pages need more photos than most brands have. AI product photography can turn the images you already own into studio shots, lifestyle scenes and on-model looks. The risk is a product that drifts from the real thing. This is how to keep it accurate.

Start from real product images

Every shoot starts from a product. In Goose's Product Photos you can import one from:

  • A URL: a Shopify store, a product page or a direct image URL. Goose fetches the product, and for a store its catalog, and re-hosts the images.
  • An image upload: drop in a photo and name the product.

Shoot it

  1. Pick the source images. The first is the main reference. Add other angles for a truer result.
  2. Choose the look: the setting, whether the product appears alone or with a model, the framing and the lighting. Defaults are set per product category.
  3. Add a prompt if you want to steer the shot.
  4. Pick how many photos and the quality, then generate.

Each photo is judged for product fidelity (silhouette, materials, logo, colorway) and retried automatically if it misses. Retries are free, and you are billed only for photos that pass.

Approve before use

Nothing is used in an ad until you approve it. Approving links a photo to its product and adds it to your brand kit. Archived photos are never used in ads.

Add a per-product note

If the AI keeps repeating a mistake on a product (for example, leaving the cap off), add a creative note to that product in the Brand Kit, such as "always show the cap on."

Check before you publish

  • Compare against the real product: shape, label text, colors.
  • Look at hands, reflections and small print, where AI errors tend to hide.
  • Check low-resolution warnings on the source images.
  • Software and app brands: upload real screenshots as product images, not a mascot or illustration.

Try it

Product Photos is at make.gooseworks.ai/product-photos. Approved photos are available to every ad you make, as described in how to make AI ad creative that stays on brand.

Keep reading

Skills used in this post

Goose Product Photos

Make product photos (studio, lifestyle or on a model) of a brand's real products with GooseWorks in this chat. Start brand work with brand_knowledge_browse and follow the next_step in every answer.

Render 3d Product Showcase

Assemble a premium 3D product-showcase ad from a config — four beat clips (an orbiting hero rotation, a macro push-in, a physics reveal, a typographic close) normalized to the chosen backdrop colour, hard-concatenated in order, closed on a deterministic Playwright brand end card, and mixed under one instrumental bed at loudnorm I=-16 (music-only, no VO). Ships the runnable build_endcard.py + build_masters.py; the rotation/macro clips are create-video-fal i2v seeded on a create-image-fal styled hero, the reveal is Veo3 i2v, and the bed is create-music-elevenlabs. Use for the 3d-product-showcase format.

Render Food Product Sizzle

Assemble a wordless macro-tabletop food-product sizzle ad from a config — normalize fps and SAR across ~4 photorealistic macro clips (hands tearing, flat lay, bite, box hero), concat them, apply a global anti-AI grain pass (eq plus hqdn3d plus noise), composite the audio (a non-diegetic instrumental music bed plus a couple of short diegetic SFX like a snap and a tear placed at measured cue points, loudnorm), composite a STATIC end card entirely in PIL (real logo PNG plus real product PNG plus a serif heritage headline plus a CTA — never AI-rendered text), and burn optional serif stat-callout pills at beats. This is the FREE deterministic assembly stage (normalized concat plus grain plus music and SFX mix plus PIL end card plus callouts); the macro keyframes, i2v clips, and music bed come from create-image-fal, create-video-fal, and create-music-elevenlabs. Use for the food-product-sizzle format.