For home & living makers
A shopper buys the corner she is imagining, and the piece is what makes it. Staging that corner for every piece and every drop is a shoot you do not have time for.
Upload up to nine photos of your real piece. Latent preserves its shape, colour, material and the words printed on its label, then generates a month of posts with captions for Instagram, Facebook and LinkedIn. Free while in beta, no card.
Reference photos
Prompt-only generation invents furniture and rewrites labels. It hands back a lamp nobody built and a weave nobody wove. Latent starts from your photos instead. Attach up to nine of the real piece, shot on your own shelf, and every picture is steered by them: same shape, same finish, same words on the label. Only the room around it changes.
How generation reads your photosThe looks
A room has a mood before it has a picture. Quiet luxury is the muted corner and the gift table. Cinematic is a low room and a long shadow. Retro is grain and an older shelf. Flat lay looks straight down at the mantel. The look changes the light, the surface and the season around the piece, and the reference photos hold the piece still through all of it.
What each look changesA drop at a time
This trade sells in drops: the shelf refresh, the restage, the new colourway. The feed has to be warm before each one lands, and the making does not stop while you write posts. Start from one prompt and the assistant drafts the run with you, scene by scene, on the days you do not know what to post.
What the assistant draftsEvery shape
A feed post, a grid tile and a story are three shapes of one photograph. Latent extends the frame outward instead of cropping into it, so the corner survives the crop: the mantel stays a mantel, and nothing is enlarged until the weave goes soft.
Captions and publishing
The caption arrives with the picture, written to match it and written again for each account. It names the room and what the piece does in it, rather than describing an object the reader can already see. Instagram, Facebook and LinkedIn each get their own words and their own shape. You read every one before it goes out, and nothing publishes without you.
Where the posts goInstead of the patchwork
Single-picture tools stop when the background is gone. The caption still has to be written, the shapes still have to be cut, and the drop still has to go out, each in its own tab.
Today
With Latent
One prompt makes the picture, the caption and the post. One browser tab, nothing to install.
Still images and captions, out to Instagram, Facebook and LinkedIn. No video and no Reels yet. More places to publish are the road from here.
Free beta
Make the pictures, fix the one wrong thing, and send the posts. Everything you make stays yours.
Questions
Yes. Latent takes up to nine reference photos per product and preserves logos and label text along with shape, colours, materials and finish. The piece keeps its shape and the label keeps its words.
No. The reference photos of the piece stay the same and the room changes around them. A bright shelf, a dark corner, a bare mantel: each drop gets its own scenes without a new shoot, and the captions come with them.
Rules differ by platform and they change, so check each platform's current policy before you post. On Latent's side the facts are these: images are generated from photos of your real product, you review every image and caption before publishing, and nothing goes out without you.
Only you. Reference photos go into your private library. There is no public gallery and no shared feed.
Yes. Latent is in beta and free to use. No plans, no prices, no card. And it asks before it spends anything.
No. Latent runs in the browser. Upload photos of the piece, type a prompt, review, publish.