Place one portrait inside an original fluorescent liminal corridor, then animate a slow look-around video with a ready TripoSplat Halloween workflow online.
A restrained liminal-horror scene for the backrooms trend. It avoids jump scares and creature imagery, relying on empty architecture, fluorescent light, and the person’s stillness.
Long corridors, damp beige carpet, stained ceiling panels, and distant doorways create the environment. A flashlight rim and realistic wide-angle distortion keep the person grounded inside it.
Copy the exact recipe or open the editor with it already filled in. The instructions separate identity, costume, scene, light, and failure cases so a retry changes one variable at a time.
Use the uploaded portrait as the identity reference. Preserve the subject's recognizable face, skin tone, facial proportions, age, pose, and natural anatomy. Place the same person in an original eerie liminal-space photograph: long empty corridors with damp beige carpet, fluorescent ceiling panels, faint water stains, and distant doorways. Keep the person clearly visible and grounded in the scene. Add a subtle flashlight rim, cool shadow detail, and restrained haze without showing gore or a creature. Use a wide-angle cinematic composition with realistic lens distortion and believable textures. Keep the same number of people as the uploaded photo. Avoid altered identity, extra people, text, signs, logos, watermarks, and jump-scare imagery.
Use the provided image as the exact first frame and reference. Create a five-second uneventful liminal-horror animation. Preserve the person's face, clothing, pose, environment, framing, and lighting. The subject slowly looks over one shoulder while a fluorescent light above flickers once. Haze drifts through the corridor and the camera performs a very slow forward move. Keep the motion subtle, anatomy stable, and continuity clean. Do not zoom into a face, add creatures, chase scenes, gore, text, or watermarks.
Prompts stay in English because the image and video models follow English instructions most reliably. You can edit them after the editor opens.
Open the look that matches the subject you have: one person, a pet, a couple, or a scene.
Use a sharp, well-lit photo you have the right to edit. The prompt protects identity before it changes the styling.
Run GPT Image 2 in the image editor, then copy the same result into the video workspace for a short animation.
The public workspaces keep provider selection behind one generation contract. KIE image routes are live today; the same job can move through fal, Replicate, WaveSpeed, or SeeAPI when those routes are configured.
Low-cost image and image-to-video routes when this provider is configured.
Relay route for supported image and video models when configured.
Primary 3D and motion route; configured media jobs can use it as a fallback.
Queued image and video fallback for supported models when configured.
Active image route for GPT Image 2, Nano Banana 2, Seedream, Flux, and related models.
Provider availability and price follow the runtime configuration. The page never promises a route that the current deployment cannot execute.
Start with one look, then create a matching portrait, pet edit, or short video with the same visual language.
A dark fairytale portrait built from this season’s mascot-horror energy, without recreating a film character. One face stays recognizable while the costume, mane, horn, forest, and light become a complete editorial scene.
An editorial hair-and-wardrobe transformation for anyone who wants the braided-cosplay trend without a salon appointment. The face and pose stay familiar while the styling becomes a complete gothic fashion story.
A glowing fantasy portrait for people who want the cosmic-princess trend with original fashion direction. The model keeps the face and body believable while building a complete observatory scene.
Place one portrait inside an original fluorescent liminal corridor, then animate a slow look-around video with a ready TripoSplat Halloween workflow online.
No. The recipe stays with empty architecture, fluorescent light, fog, and a subtle flicker. It deliberately avoids heads, creatures, chases, and gore.
Yes. The video prompt adds one light flicker, drifting haze, and a very slow forward camera move while keeping the person and environment stable.
