Goku Prompt Hub

Curated Prompt Vault

Street Misunderstanding Comedy Twist

SD2_03173 2026-06-29 x Entertainment
street comedyhandheld footagemisunderstanding

Unedited iPhone handheld footage is presented in authentic video style, with all camera settings automatic, with no post-processing color grading or special ef…

Full Prompt

⚡Generate
Unedited iPhone handheld footage is presented in authentic video style, with all camera settings automatic, with no post-processing color grading or special effects. The footage shows real handheld slight shake and the breathing sensation of the operator (passerby); the camera naturally sinks or tilts due to street movement and then quickly returns to center. Autofocus occasionally experiences search, delay, and brief out-of-focus moments, especially when following action or hand movements. Automatic white balance naturally switches between warm and cool tones as the street's natural light and tree shadows change. The overall image is flat, preserving optical imperfections such as true lens flares, slight chromatic aberration at edges, and motion blur. Simulation of CCD sensor shooting with slight vertical smear, color overflow, grain noise, and purple-green fringes with high contrast edges. Only natural environment sounds within the painting are used, including street traffic, footsteps, and wind rustling leaves; microphones may have slight distortion when speaking. It uses a third-person street passerby/bystander perspective (handheld shooting by nearby passersby), with camera movements completely following the passerby's instinctive reactions (slight following, turning their heads) on the character
, 100% of the reference images are preserved for the model's age, facial features, bone structure, eye distance, jaw geometry, temperament, skin tone, and hairstyle. No skin smoothing, no excessive softening, no deviation toward an average face. 15-second timeline (full conception: misunderstanding the phone call→ woman awkwardly turns around thinking she was being told → → another misunderstanding reversal, third-person bystander perspective): At 0 seconds, the camera shifts slightly from a third-person bystander to focus on a golden phoenix tree street: a slender, long-haired woman
(Wear a mask, wear it
Image_20260608230651_1029_183(1)
) walked toward her with a mannequin stride, with a man in a black jacket standing on her right
hf_20260612_104941_0727cb10-f615-43bf-8c49-2202835900bc
Making a call. Traffic and pedestrian ambient sounds are natural. Autofocus is locked on the interaction between two people, with slightly overexposed images and visible CCD grain noise. After 1-3 seconds, the woman continued to approach, and the man held his phone and shouted, "You dare to go out dressed like that?" ”。 The woman suddenly stopped, turning to the side and glaring angrily at the man. The man looked at the woman with an innocent expression and showed the phone call interface. The passerby lens slightly follows, autofocus briefly searches for out-of-focus before pulling back, and the CCD shows obvious vertical tailing. The microphone captures the sound of clothes rubbing and the man's voice (slightly distorted). Between 4-7 seconds, the woman appeared embarrassed and waved her hand to apologize. She awkwardly responded ("Oh, sorry"), lowered her head, and continued walking. The man turned his head and continued talking loudly on the phone. The passerby camera naturally follows the woman; the frame shifts slightly due to walking and compositional imperfections, with automatic white balance drifting with the shadows of the trees. The microphone captured the sound of high heels tapping on the road and the man's follow-up speech ("You wear it so little all day, how dignified is that!" ”)。 Between 8 and 11 seconds, the woman walked away a few steps, then suddenly turned around and quickly walked back to the man, raising her hand as if to hit him. The man once again looked confused, raising his phone to show it, and the two stood in the center of the frame. When pedestrians quickly turn their heads to follow, autofocus shows noticeable delay, background pedestrians briefly block the view, hand shake intensifies, CCD tailing and granular noise permeate the scene. The microphone captured the woman's angry voice ("You still said you didn't say about me!" ) and the man helplessly explained ("Miss, I'm really on the phone"), adding a slightly funny ambient sound effect. Between 12 and 15 seconds, the woman finally awkwardly waved her hand and left, while the man continued making the call. The passerby shot slightly lowers and then lifts (shifting center of gravity), with slightly imperfect composition. The woman's lower body is briefly cropped at the edge, with faint fingerprint oil stains visible at the edges. Auto white balance switches again, street ambient sounds persist, and the overall look is like an unedited handheld video. The visuals present a realistic, unedited handheld video texture, documentary-level natural imperfections, with no post-production color grading or special effects. All camera actions match the physical characteristics of iPhone/phone automatic shooting, with CCD sensor effects running throughout, perfectly recreating street misunderstandings and funny interactions from a passerby's perspective.