Template

Manifest

Upload an image to start your template-based generation.

More
Manifest

Upload Image

Manifest

Manifest
Credits Required:10

Easily Recreate the Same Look with Manifest

Copy Manifest prompts in one click and quickly recreate the same look in your images and videos, without starting from scratch.

Manifest

AI Prompt

{Dim}{Noise: 3.0}{Based on the main facial features of the subject in the original image: 1.6} Generate a vertical 3:4 composition, with motion blur in both the foreground and background, {Camera tilt: 1.6}. Low‑pixel‑style, high‑ISO camera snapshot—narrow vertical black-and-white documentary photography. The subject stands amid a crowded event scene, captured in a tight medium‑closeup, slightly low‑angle shot—from just above the head down to around the waist. Positioned slightly lower than center, roughly at 40% of the frame’s vertical height; the figure must not fill the entire frame. The upper portion retains ample space for blurred crowds and lighting. The camera is placed directly in front of the subject, slightly to the left, near shoulder level, using a medium‑telephoto lens to shoot through gaps in the dense crowd. The subject’s body faces mostly toward the camera, but the head is turned sharply to the left, presenting an almost three‑quarter profile; the chin is gently lowered, eyes glance diagonally leftward, avoiding direct eye contact. Lips are closed, corners of the mouth straight, eyebrows and eyes conveying alertness, detachment, and contemplation—no smile, no teeth shown. Hair is loose, with strands on either side lying flat against the cheeks and shoulders, long locks cascading naturally over the chest and back; ends are smooth, with only a slight natural curve. Do not specify hair color. The subject wears a pure black V‑neck slip dress, symmetrically cut. Small, delicate circular earrings adorn the ears; no necklace, hat, or other accessories are added. Makeup is cool-toned, high‑contrast, refined black-and-white: subtle, natural base makeup; well-defined brows; dark, close‑fitting eyeliner; slightly upturned outer corners; clear yet understated lashes; soft gray shading in the eye socket; faint contouring on the cheekbones; and rich, deep matte lipstick. Lip shape is distinct, skin texture gentle. The background is an extremely crowded indoor venue, with numerous figures swiftly passing in front of, behind, and to the sides of the subject. All figures behind the subject are noticeably out of focus, their forms streaked with lateral motion blur—only blurred heads, shoulders, arms, and faint silhouettes remain visible; no clear faces should appear. In the foreground on the left, right, and bottom, deeply blurred human shapes lie very close to the lens, partially obscuring parts of the subject’s shoulders and lower body, creating the visual effect of candidly capturing a moving crowd. At the top of the frame, the background is nearly black, dotted with a few faint horizontal streaks of light and blurred human outlines; do not render clear shop signs, pillars, counters, or large circular light boxes. Crowd density is high, making the subject seem stationary amidst the flowing mass. Shutter speed is slightly slow, producing noticeable lateral and diagonal motion blur in both background and foreground figures; the subject’s face remains relatively sharp, though edges still carry a subtle soft focus. Avoid rendering the subject overly crisp. The image exhibits mild high‑ISO noise and soft film grain, but the grain must not be coarse or obscure facial details. A pure black-and-white-gray palette, with overall exposure leaning toward darkness and a high proportion of shadows. Soft key lighting comes from the left‑front, illuminating the subject’s forehead, bridge of the nose, left cheek, and chin; the opposite side of the face is naturally shadowed. The black asymmetrical off‑shoulder top is nearly jet‑black, contrasting with the pale gray skin tone. The whole scene evokes a solitary, restrained, detached, cinematic black-and-white street‑photography mood. {Referencing the subject’s primary facial features, gender, hair color, hairstyle, and biometric traits as in the original image}, {Realism: 1.6}, with accurate human proportions. Aspect ratio 3:4.

GumaGuma

Guma is an AI video and image generator that turns text and images into cinematic videos in seconds, powered by leading models including Kling, Nano Banana, Seedance and more.

Language

© 2026 Guma. All rights reserved.