Remove Passersby

Remove all people and human figures from the background of this image while  keeping the main subject completely unchanged. The background scene —  architecture, landscape, street, objects, environment — should remain intact,  only the unwanted people are removed and the space behind them is naturally  filled in. The result should look as if no one else was in the frame. Do NOT change the main subject's appearance, pose, expression, clothing,  or position. Do NOT alter the background scenery, lighting, or composition.

Use Template
arrow

More From VIVAGO AI

Baby Milestone AI effects generated image

Baby Milestone

"Portrait restoration: facial feature ratio, face contour, hair texture and color, basic hairstyle shape 1:1 replicate the reference portrait uploaded by the user, the appearance is exactly the same as the reference picture, no feature offset Styling retention: the character's hair is sectioned and rolled with colorful hair curlers, the overall composition, character posture, and prop position fully match the reference picture Vertical bust close-up portrait, young pregnant woman facing the camera frontally, playful smile with raised corners of the mouth, smile at the end of the eyes, eyes gently looking to the front left of the frame, smart and natural Hair is sectioned based on the original hairstyle, rolled with multiple macaron color hair curlers, including mint green, light pink, light purple, cream white, arranged in a scattered order, fluffy hair roots Wearing three layers of stacked matte gold thin necklaces around the neck, the bottom layer with a small round zircon pendant Hands entering the frame on the left and right sides: the left hand holds a short fleece gray elephant plush doll, fingertips pinch a white silicone baby pacifier, natural hand posture; the right hand thumb and index finger pinch the upper right corner of the vertical ultrasound photo strip, the photo strip evenly arranges 3 clear fetal B-ultrasound images, the content is real and natural Light milk tea color matte solid background, clean and clutter-free Warm soft light layout, even front fill light, side with light pink-orange ambient light, soft light and shadow transition, transparent and glossy skin, slight retro film texture Low saturation warm tone, soft and unified color, realistic maternity portrait, baby reveal announcement style, 8K HD, rich details, delicate picture quality"

Coffe Master AI effects generated image

Coffe Master

A 3D rendered surreal photograph, shot from a frontal view (full-face orientation), evoking a whimsical micro-world scale effect. THE CENTRAL FOCAL POINT IS THE EXACT UNMODIFIED SUBJECT FROM THE UPLOADED REFERENCE IMAGE, ENLARGED AND CLOSER IN THE FRAME, PRESERVING EVERY DETAIL of their face, age, and most importantly, their exact clothing, textures, colors, and features (whether they are a specific human or an animal). The subject maintains their precise expression from the uploaded image and faces the camera directly. Crucially, the subject is interacting with giant everyday items: they are standing on a large wooden tabletop, using both hands/paws to hold a giant, oversized silver serving spoon and actively stirring a massive, giant white ceramic teacup filled with steaming tea. The background is a dense, beautifully detailed micro-environment of a bakery or afternoon tea, featuring huge, towering stacks of assorted fresh-baked bread, large biscuits, and pastries. Scattered across the wooden tabletop and the saucer around the massive cup are giant individual roasted coffee beans, oversized cinnamon sticks, and loose cookies, all meticulously scaled. Warm, soft, sunlit daylight filtering from a window. Whimsical, creative, and high-quality artistic composition.

Vogue Star AI effects generated image

Vogue Star

Recreate the reference as a glamorous VOGUE pet magazine cover. The uploaded dog is centered in a formal fashion portrait, wearing layered pearl necklaces and a plush taupe faux-fur wrap around the shoulders, looking gently at camera. Warm gray-beige backdrop, gold large masthead 'VOGUE' at the top, left cover lines reading 'FASHION'S NEW STAR', 'DOG OF THE YEAR', 'THE INSPIRING STORY OF POKI', and lower signature text 'Poki'; right cover lines including 'THE BEST IN PET HAUTE COUTURE' and 'INSIDE THIS SEASON'S PAW-FECT TRENDS'. Premium glossy magazine print, elegant editorial lighting. Preserve the uploaded pet's actual species, breed, coat color, markings, ear shape, eye color, muzzle and facial structure. Do not assume a fixed breed, color, or species from the reference image; adapt the exact gameplay to the uploaded pet. Actively change pose, facial expression, gaze direction, camera angle, wardrobe and styling to match the gameplay reference. Match the gameplay reference very closely in composition, crop, texture, lighting, visible pet angle, props, background, graphic layout and image quality. Vertical 3:4. Keep only the text explicitly requested in the prompt; do not add unrelated logos, watermarks or random words.

Mona Lisa Dog AI effects generated image

Mona Lisa Dog

Recreate a Renaissance museum portrait with the uploaded pet seated in three-quarter pose, front paws folded gently, dark formal robe, subtle calm expression and hazy winding landscape behind. Soft sfumato, muted green-brown palette, aged oil paint and fine craquelure. The subject remains an animal throughout. No people or human hands. No real character names, celebrity names, brands, logos, watermarks or readable text. Accurately preserve the uploaded pet's species, breed, coat color and markings, ear shape, muzzle and face structure, eye color, body proportions and tail. Keep it instantly recognisable as the same animal; change only pose, scene, costume and art treatment. Match the reference composition closely. Vertical 3:4, crisp detail, the pet is the unmistakable main subject.

Pet Samba

"Medium shot close-up: In the uploaded photo (while maintaining the facial features, gender, age and species of the person in the uploaded image, and setting the background as a beach scene in Brazil), the main figure presents a super cute anthropomorphic standing posture (with the front two paws raised and the back two legs standing). Accessories: Beach attire in the style of the Brazilian Carnival: Wearing a cute bikini top and a short skirt, with a colorful feather headdress on the head (green and yellow), and a garland around the neck (yellow hibiscus and white flowers); Scene: The scene of a tropical Brazilian beach: - Underfoot is the golden fine sand, the azure waves gently lapping against the shore. In the distance, the palm trees sway in the gentle breeze. Soft white clouds float in the blue sky. In the warm afternoon, the golden sunlight gently falls on the river otters and the beach. Style and lighting: Vivid and cheerful color combination (main colors are yellow, green, blue, and orange), 8K high resolution, highlighting the main subject, shallow depth of field to blur the background of the beach; Composition: Medium shot. The main figure is centered in the frame, wearing small slippers on their feet, which match the color scheme of the clothing."

Bali Queen AI effects generated image

Bali Queen

Strictly lock the facial features of the uploaded portrait (preserve facial contours, native Indonesian skin tone, hairstyle and age). Half-body portrait photography, the subject is centered in the frame, not positioned too low, hyper-realistic style, 4K ultra-high definition, soft warm tropical daylight, authentic Balinese wedding cultural atmosphere | A young Indonesian Balinese woman with a poised, elegant expression, standing front-facing in a traditional Balinese bridal outfit. She wears an extremely elaborate, oversized golden beaded and embroidered ceremonial headdress (Bali crown) adorned with intricate floral and gem details, a matching golden beaded and embroidered short-sleeve top, and a deep maroon batik-patterned sarong skirt with gold trim. She accessorizes with layered golden necklaces, bracelets, and a ceremonial handpiece, with her hands gracefully clasped in front of her torso. The background is a softly blurred authentic Balinese wedding ceremony setting: a sacred bamboo and palm-frond ceremonial pavilion (bale agung) decorated with vibrant tropical flowers (frangipani, orchids, and jasmine), a carved wooden altar adorned with traditional offerings, and lush green tropical foliage, creating a romantic and culturally immersive wedding atmosphere. Focus on the intricate details of the golden beadwork, the ornate headdress, and the timeless cultural elegance of the Balinese wedding tradition, with warm diffused sunlight enhancing the opulence of the bridal attire

Pagode Pet

[Animal character in the reference image], original appearance and facial features remain completely unchanged, thick and lush full fur with vigorous hair state; chibi design with big head and small body, possessing realistic texture and natural light and shadow details, whole picture presented in Pagode art style; wearing trendy costumes matching the style tone with elegant and well-proportioned cut, neat and proper dressing; the character wears a sweet toothless smile with lovely and vivid expression; standing steadily and naturally on both feet with relaxed posture; placed in exotic Rio-style scene that matches the overall artistic style; displayed with cinematic warm tone, warm and comforting picture atmosphere; 8K ultra high definition image quality, delicate three-dimensional fur and clothing texture, mild and rich light and shadow layers, soft depth of field, exquisite and premium overall visual texture.

Wizard Chess AI effects generated image

Wizard Chess

"Full-bleed vertical 3:4 photorealistic fantasy wizard chess scene. The uploaded reference image is the exact pet identity and MUST be preserved. Highest priority: keep the same black-and-white cat from the reference photo: same asymmetric black-and-white facial mask, same white muzzle, same pink nose, same eye color and gaze, same ear shape, same head proportions and fur markings. Do not replace it with another cat, do not simplify or invent a different face. Only transform costume, pose, and environment. Scene: wizard chess gameplay reference style: the cat leans over a wooden chessboard in a dim ancient library hall, arched windows, old books, oil lamp, candles, flying parchment papers, warm magical atmosphere, cinematic retro film texture. The cat wears a plain black wizard robe and a soft tall black pointed wizard hat. Scarf must match the chess reference: a knitted school scarf with HORIZONTAL STRIPES ONLY. It is not plaid, not checkerboard, not tartan, not crisscross. Colors are deep burgundy red and golden yellow, repeated horizontal bands around the neck, visible ribbed wool knit texture, soft knitted fabric. No readable text, no logos, no watermark, "

Apocalypse Chill AI effects generated image

Apocalypse Chill

"Use the uploaded image as the only identity reference. Create a cinematic apocalyptic portrait of the subject sitting inside a car, facing the camera more frontally. Strictly preserve the subject’s identity, facial features, hairstyle, clothing style, and overall recognizability from the uploaded image. The subject is wearing stylish slim black sunglasses. The pose is clear and cinematic: one hand is lightly touching the edge of the sunglasses, the head is slightly lowered, and the subject looks toward the camera from above the sunglasses. The gaze should feel cool, confident, sharp, and unbothered. The expression should not be blank or stiff. Give the subject a subtle smirk, relaxed lips, slightly raised eyebrows, and a fearless attitude, as if the apocalypse outside does not affect them at all. The subject sits inside the car while an end-of-the-world disaster unfolds outside the car window: explosions, burning vehicles, police cars, smoke, falling debris, cracked glass, emergency lights, and a chaotic ruined city or highway scene. The contrast should be strong: the subject looks stylish, calm, and completely in control inside the car, while the outside world is collapsing into chaos. Cinematic photorealistic style, dramatic lighting, realistic car interior, warm fire glow mixed with cool shadows, high detail, intense apocalyptic atmosphere, action movie still, vertical composition. No cigarette, no smoking, no blank expression, no stiff pose, no awkward hands, no text, no logo, no watermark."

Load more

Next-Gen Multi-Model AI Video Architecture

Vivago AI isn't just one engine—it’s a unified hub for the world’s most advanced video AI. Whether you need cinematic realism or high-speed social content, we provide the right model for your creative vision.

Free Generate

Beauty and Dolphins

Vacation Time

Stellar Tear

Fish Tank Supervisor

Cinematic Quality & Precision Control

Enables 4K resolution with multi-lens motion control, generating delicate scene via text prompts for customized cinematography.​

TRY NOW

Dynamic AV Sync

Auto-generates original audio to avoid copyright issues. Build 3D immersive environments through layered sound design automatically.

TRY NOW

OpenAI Sora 2

​Advanced visual storytelling with unparalleled physics and consistency.

TRY NOW

Kling v2.6 Pro

Industry-leading cinematic image animation and motion control.

TRY NOW

Google Veo 3 & 3.1

Ultra-fast generation with enhanced realism for creative workflows.

TRY NOW

Vivago AI 2.0

Our proprietary model optimized for efficiency, speed, and cost-effective generation.

TRY NOW

Users' Voice

We listen carefully to the opinions of every user.
Free Generate
Contact Us
I tried the Lip Sync feature inside Vivago.ai’s AI Video Generator for my educational podcast, and the results were stunning! The avatar's lip movements perfectly matched my audio recording, creating a professional AI-generated video without complex editing. Compared with tools like OpenAI Sora 2 and Google Veo 3.1, Vivago Image-to-Video delivers fast, studio-quality results online. It saved me hours of post-production work.
ElenaM (Spain)
Vivago’s Image-to-Video AI transformed my marketing workflow. I uploaded a product image and described the launch scene in text, and it generated a 10-second cinematic AI video with background music and dynamic visuals. The output quality rivals Kling v2.6 Pro and Google Veo 3 Fast. It’s now my go-to AI video generator for social media ads and product campaigns.
KenjiT (Japan)
As a digital artist, I use Vivago.ai 2.0 daily for Image-to-Image and AI Image-to-Video creation. The e-book covers and animated visuals I generate for clients look cinematic and professional. Unlike many standalone AI tools, Vivago integrates multiple leading models into one platform, making it easier to create copyright-safe AI images and videos for publishing.
ChenL (China)
I tried the Lip Sync feature inside Vivago.ai’s AI Video Generator for my educational podcast, and the results were stunning! The avatar's lip movements perfectly matched my audio recording, creating a professional AI-generated video without complex editing. Compared with tools like OpenAI Sora 2 and Google Veo 3.1, Vivago Image-to-Video delivers fast, studio-quality results online. It saved me hours of post-production work.
ElenaM (Spain)
Vivago’s Image-to-Video AI transformed my marketing workflow. I uploaded a product image and described the launch scene in text, and it generated a 10-second cinematic AI video with background music and dynamic visuals. The output quality rivals Kling v2.6 Pro and Google Veo 3 Fast. It’s now my go-to AI video generator for social media ads and product campaigns.
KenjiT (Japan)
As a digital artist, I use Vivago.ai 2.0 daily for Image-to-Image and AI Image-to-Video creation. The e-book covers and animated visuals I generate for clients look cinematic and professional. Unlike many standalone AI tools, Vivago integrates multiple leading models into one platform, making it easier to create copyright-safe AI images and videos for publishing.
ChenL (China)
I absolutely love Vivago’s AI Image-to-Video Generator. As a travel blogger, static images often fail to capture real atmosphere, but Vivago helps me turn photos into vivid cinematic AI videos with motion effects. It feels comparable to OpenAI Sora 2 and Google Veo 3.1, but more accessible and faster for creators who need high-quality AI videos online.
LiamK (Australia)
I tried the Lip Sync feature inside Vivago.ai’s AI Video Generator for my educational podcast, and the results were stunning! The avatar's lip movements perfectly matched my audio recording, creating a professional AI-generated video without complex editing. Compared with tools like OpenAI Sora 2 and Google Veo 3.1, Vivago Image-to-Video delivers fast, studio-quality results online. It saved me hours of post-production work.
ElenaM (Spain)
Vivago’s Image-to-Video AI transformed my marketing workflow. I uploaded a product image and described the launch scene in text, and it generated a 10-second cinematic AI video with background music and dynamic visuals. The output quality rivals Kling v2.6 Pro and Google Veo 3 Fast. It’s now my go-to AI video generator for social media ads and product campaigns.
KenjiT (Japan)
As a digital artist, I use Vivago.ai 2.0 daily for Image-to-Image and AI Image-to-Video creation. The e-book covers and animated visuals I generate for clients look cinematic and professional. Unlike many standalone AI tools, Vivago integrates multiple leading models into one platform, making it easier to create copyright-safe AI images and videos for publishing.
ChenL (China)
I absolutely love Vivago’s AI Image-to-Video Generator. As a travel blogger, static images often fail to capture real atmosphere, but Vivago helps me turn photos into vivid cinematic AI videos with motion effects. It feels comparable to OpenAI Sora 2 and Google Veo 3.1, but more accessible and faster for creators who need high-quality AI videos online.
LiamK (Australia)
Using Vivago.ai’s Image-to-Video AI has greatly enhanced my classroom teaching. I transform textbook notes into historical AI videos with cinematic filters and dynamic animations. Compared with tools like Kling v2.6 Pro and Google Veo 3 Fast, Vivago offers faster generation and easier parameter control for educators who need reliable AI video creation.
RajivG (India)
I frequently create AI videos on Vivago and publish them on TikTok and YouTube Shorts. The AI video templates and trending content ideas help me produce viral-ready clips quickly. With Vivago’s integrated models—including advanced video engines similar to OpenAI Sora 2—I can generate anime-style and cinematic social media videos that drive high engagement.
MarieJ (Spain)
What attracts me most about Vivago.ai is not only the powerful AI Video Generator but also the active AIGC creator community. It combines AI Image-to-Video, Text-to-Video, and leading model integrations like Google Veo 3.1 into one creative platform.
TomW (India)
At first, I was hesitant about using AI video tools. But after trying Vivago Image-to-Video, I realized how easy it is to create professional AI-generated videos online. I just upload an image, add a short prompt, and adjust a few settings. The results are cinematic and copyright-safe, which is essential for commercial projects.
HectorC (Mexico)
Using Vivago.ai’s Image-to-Video AI has greatly enhanced my classroom teaching. I transform textbook notes into historical AI videos with cinematic filters and dynamic animations. Compared with tools like Kling v2.6 Pro and Google Veo 3 Fast, Vivago offers faster generation and easier parameter control for educators who need reliable AI video creation.
RajivG (India)
I frequently create AI videos on Vivago and publish them on TikTok and YouTube Shorts. The AI video templates and trending content ideas help me produce viral-ready clips quickly. With Vivago’s integrated models—including advanced video engines similar to OpenAI Sora 2—I can generate anime-style and cinematic social media videos that drive high engagement.
MarieJ (Spain)
What attracts me most about Vivago.ai is not only the powerful AI Video Generator but also the active AIGC creator community. It combines AI Image-to-Video, Text-to-Video, and leading model integrations like Google Veo 3.1 into one creative platform.
TomW (India)
At first, I was hesitant about using AI video tools. But after trying Vivago Image-to-Video, I realized how easy it is to create professional AI-generated videos online. I just upload an image, add a short prompt, and adjust a few settings. The results are cinematic and copyright-safe, which is essential for commercial projects.
HectorC (Mexico)