GUIDE

The Custom Photo Prompt Gallery on Sloane

AI companion photos usually collapse into the same "portrait of a woman in warm lighting" template — safe, generic, forgettable. The Custom Photo Inspiration gallery flips that by seeding a catalog of specific, evocative scenes: a boat deck at sunset, an oversized dress shirt on the couch, a Mets jersey at the stadium. Tap a tile and she generates that exact scene, using her actual face.

What the gallery is

The Custom Photo Inspiration modal on Sloane. Category filter chips (All, Action, Beach, Cosplay, Cultural, Everyday, Festival, Group, Intimate, Loungewear) run across the top. Below is a grid of photo tiles, each showing a preview render, a heart icon in the top-right corner, the prompt text below the preview, and a "Generate — 5 credits" button.
The Custom Photo Inspiration modal — filter chips up top, tiles below. Each tile shows a preview render of the scene, the exact prompt beneath it, a heart to save, and a Generate button that fires the img2img call.

Open the skills menu in any chat and tap Custom Photo Inspiration. What loads is a grid of hand-picked photo ideas across categories — loungewear, beach, morning, undressing, sports fandom, cosplay, group shots, and everyday moments. Each tile shows a preview render of the scene plus the exact prompt beneath it, so you can see what you're getting before you commit.

Why specific beats generic

Default AI photos feel same-y because the underlying prompt is same-y. "Portrait of a woman in a cozy setting, warm lighting, cinematic" produces one narrow band of results across every generation. The catalog approach flips it: instead of the model picking the scene, the operator has hand-picked dozens of scenes with real detail — "sitting on the edge of the bed pulling her hair up," "on a rooftop pool deck in a linen wrap dress," "reaching back to unzip her dress." Specific inputs produce specific outputs.

How the render actually works

The preview render on the tile the user tapped — a woman taking a mirror selfie in a fitting room wearing a black leather biker jacket with the price tags still visible. Portrait framing, sharp focus, natural light.
The preview on the tile — a stand-in persona in the composition the prompt describes.
The generated photo delivered in chat: a mirror selfie of Monique (a plus-size Black woman with long dark curly hair and burgundy lipstick) in the same fitting room, wearing the same black leather biker jacket with price tags visible. The composition matches the preview but the identity is Monique — her face, hair, and body.
The result — Monique's actual face, hair, and body rendered in the same scene. Not a stand-in; her identity locks from her avatar.

When you tap a tile, Sloane fires an image-to-image call to Grok Imagine using your companion's avatar as the identity reference. The tile's prompt drives the scene; the reference locks her face, hair color and texture, eye color, skin tone, and body type. The output is that scene rendered with HER identity — not a stand-in, not a random face, actually her.

The two shots below show it end-to-end. Left: the preview on the tile the user tapped — the composition rendered against a stand-in persona so you can see what the scene will look like. Right: the actual delivered photo, Monique in the same fitting room, the same biker jacket, but her identity throughout. Same scene, her face.

Categories in the gallery today

The current catalog spans loungewear (boyfriend-shirt, cotton pajamas, silk robe), beach (boat deck, linen sundress at a beach bar, walking barefoot on wet sand), morning (bathroom doorway with damp hair, edge of the bed pulling her hair up), undressing (unzipping her dress, loosening her tie, sliding one strap off her shoulder), sports fandom (team jersey at the stadium, courtside at a game), cosplay (Lara Croft in a jungle temple, Chun-Li mid-kick, Wonder Woman full costume), group shots (sorority composite, bachelorette in Vegas, bridesmaid line-up), and everyday moments (making pancakes in a band tee, reading in a window seat). Each category has multiple tested prompts.

Cost and gating

Custom Photo Inspiration is a Plus feature. Each generation costs 5 credits — the same as any custom photo request in chat. Free accounts can browse the gallery and preview any tile; generating with your companion's actual face requires Plus. Tap a tile as a Free user and you get the full preview plus a one-tap upgrade path.

What happens when a prompt gets blocked

Grok Imagine's moderation is stochastic on borderline scenes — the same prompt may pass on one attempt and get blocked on the next. Sloane retries up to three times before giving up. If all three attempts get moderated, you see a friendly note ("Our photo model vendor blocked this scene — no credits charged") and can pick a different tile. Credits are only deducted after a photo actually lands in your chat; a moderated request costs nothing.

How prompts get chosen for the catalog

The catalog is operator-curated. Each prompt is tested against multiple companions before being approved — different body types and skin tones can trigger the moderator differently, so anything unreliable gets pulled. The prompts on the live gallery are the ones that passed testing across at least three diverse companions on the first try. This means the failure rate you see in practice is low: most of the moderator-blocked wording has already been filtered out during curation.

START CHATTING

Free to browse · Plus to generate · 5 credits per photo

FREQUENTLY ASKED

Questions people ask

What kinds of photos can I get from the custom photo gallery on Sloane?

The gallery covers dozens of hand-picked scenes across categories: loungewear (boyfriend-shirt, cotton pajamas, silk robe), beach (boat deck at sunset, linen sundress at a beach bar, walking barefoot on wet sand), morning (damp hair in the bathroom doorway, edge of the bed pulling her hair up), undressing (unzipping her dress, loosening her tie, sliding one strap off her shoulder), sports fandom (team jersey at the stadium, courtside at a game), cosplay (Lara Croft, Chun-Li, Wonder Woman), group shots (sorority composite, bachelorette party), and everyday moments (making pancakes, reading by the window). Each tile shows a preview so you know what you're getting before generating.

Does the custom photo actually use my AI companion's face?

Yes. The render is an image-to-image call that uses her avatar as the identity reference — her face, hair color and texture, eye color, skin tone, and body type are locked from the avatar. The prompt on the tile drives the rest — outfit, setting, pose, composition. The preview on the tile is generated against a rotating stand-in persona so you can eyeball the scene before committing; your generation swaps in your companion's reference.

How much does each custom photo cost on Sloane?

5 credits per photo — the same as any custom photo request in chat. Custom Photo Inspiration is a Plus feature; Free accounts can browse and preview the gallery but generating with your companion's face requires Plus.

What happens if the photo prompt gets blocked by moderation?

Sloane retries up to three times if Grok Imagine rejects the first attempt. Moderation is stochastic on borderline scenes, so a second or third try often lands cleanly. If all three attempts get blocked, you get a friendly note ("Our photo model vendor blocked this scene — no credits charged") and can pick a different tile. Credits are only deducted after a photo actually lands in your chat.

Can I write my own custom photo prompt instead of picking from the gallery?

Not from the Custom Photo Inspiration gallery itself — that's a curated set. But you can always ask your companion for a specific photo directly in chat ("send me a shot of you at the beach in a linen dress"), which fires the same custom photo pipeline. The gallery is the shortcut for when you want a specific pre-tested scene without having to describe it in words.

Who picks the prompts in the gallery?

The catalog is operator-curated. Each prompt is tested against multiple companions before being approved to make sure it works reliably across the roster — different body types and skin tones can trigger the moderator differently, so anything unreliable gets pulled. Only prompts that passed testing across at least three diverse companions on the first try make it to the live gallery.

KEEP READING

Characters

Comparisons

Guides

Recently shipped