Cinel AI
Prompts
All promptsBrowse the full libraryPortrait & HeadshotProduct & E-commercePosters, Logos & Graphic DesignInfographics & UI3D Characters & FigurinesFood & DrinkIllustration & AnimeCreative Scenes
AI Image
Free AI Image GeneratorCreate images from text promptsText to Image GeneratorCreate images from text promptsAI Image to Image GeneratorGenerate from reference imagesAI Image EditorEdit existing images with textBackground RemoverRemove backgrounds instantlyImage UpscalerUpscale images 2x or 4xAI UncropExpand images beyond their borders
AI Video
AI Video GeneratorOpen the video generation workspaceText to Video GeneratorCreate videos from text promptsImage to VideoAnimate reference images
AI Models

Image models

KolorsFree Kolors image creation with prompt and reference support.Z-Image TurboFast photoreal generation with bilingual text accuracy.Seedream 4.0Cost-efficient 1K, 2K and 4K visuals with multi-reference editing.Seedream 4.54K generation, text rendering and reference editing.Seedream 5.0 LiteCinematic 3K realism with multi-reference creative direction.Seedream 5 Pro1K fast, 1.5K lightweight, or 2K professional visuals with text and references.GPT Image 2Precise prompts, clean text and polished product shots.GPT Image 2.5Faster GPT Image generation with sharper, consistent edits.Nano Banana 2 LiteFast 1K generation and editing for high-volume iteration.Nano Banana 2Multi-reference edits with fast style control.Nano Banana Pro4K renders and advanced image editing.Nano BananaLightweight Gemini edits for quick changes.

Video models

Seedance 1.0 TurboFast video generation with smooth motion, up to 1080p.Seedance 2.54–30 second video with synchronized audio, 480p or 720p.Seedance 2.0 MiniLower-cost 4–15 second video with synchronized audio, 480p or 720p.Seedance 2.04–15 second video with Fast or Standard mode, up to 1080p.MiniMax H3High-fidelity 4–15 second video with image and reference support.Kling 3.0Strong motion, camera moves and optional sound, up to 4K.Kling 3.0 TurboFaster 3–15 second video at 720p or 1080p, with first-frame input.Kling O1Kling O1 image-to-video with first and optional last frame input.Kling O3Kling O3 text-to-video and first/end-frame generation up to 4K.Grok Imagine Video 1.06–30 second beta video with Fun, Normal and Spicy style modes.Grok Imagine Video 1.51–15 second video with native audio and up to 7 image references.Wan 2.55–10 second text or single-image video with native audio.Wan 2.62–15 second multi-shot video with native audio at 720p or 1080p.Wan 2.72–15 second video with text, first/end frames and up to three image references.Veo 3.1 FastStable Fast Veo 3.1 with 4–8 second video, audio and frame input.Veo 3.1 ProStable Pro Veo 3.1 with 4–8 second video, audio and frame input.Veo 3.1 Fast BetaFast Beta 8-second video with first/end-frame or three-image reference input.Veo 3.1 Pro BetaPro Beta fixed 8-second video with first/end-frame input.Sora 24–12 second video with synchronized audio and one optional first-frame image.
Pricing
-50%Upgrade
  1. Prompts
  2. Portrait & Headshot
  3. Candid Blurry Smartphone Night Snapshot Prompt

Accidental Smartphone Snapshot: Caught Mid-Step at Night

Reference image (AI-generated by cinel, fictional)
Ultra-realistic candid smartphone photograph, 9:16 vertical.
Use the  only as a strong visual inspiration for general facial proportions and vibe,
while ensuring the generated subject remains fully original, non-identifiable, and not a face copy.
Scene
Nighttime on a quiet Tokyo city sidewalk beside a building with white ceramic tile walls.
The subject is walking past the camera, partially side-on, captured mid-step in a rushed, accidental moment.
 (combined naturally)
The subject reacts instinctively to being photographed:
turning her head back mid-walk as if surprised,
raising one hand close to the lens to partially block the camera,
shy, restrained smile forming as she suppresses laughter,
body angled in half-profile while continuing to walk forward,
motion carries her slightly out of frame, imperfect framing.
Expressions are subtle and spontaneous — embarrassed, playful, fleeting — never posed.
Camera & Motion
Shot on a modern smartphone, handheld, rushed capture. Strong uncontrolled camera shake. Heavy directional motion blur across the raised hand, hair, and face. Facial features appear smeared and streaked by movement, faintly recognizable but distorted. Partial ghosting around the body. Imperfect framing, subject nearly leaving the frame.
Lighting
Flash-only lighting fired mid-motion. Harsh flash highlights on skin and hand. Deep surrounding darkness. Uneven exposure, blown highlights, hard shadows typical of hurried night phone photography.
Background
White ceramic tile wall stretches into streaked light bands due to motion blur. Street surroundings fade into darkness with minimal readable detail.
Mood
Candid, shy, slightly playful. Feels intrusive, raw, imperfect, and authentic — like a fleeting memory accidentally captured and never meant to be perfect.
Image Quality
Extremely noisy. Heavily blurred. Raw smartphone look. Not cinematic. Not editorial. Not polished.
Negative Prompt
anime, illustration, painting, stylized,
studio lighting, beauty lighting, soft portrait,
sharp focus, clean face, perfect anatomy, smooth skin,
fashion editorial, posed portrait, cinematic grading, film still,
tripod shot, professional photography,
identity match, face copy, real person replication

9 credits at 1K. Ratio 9:16. You will need to upload your own reference image.

PhotorealCinematicEditorialArchitectureCityratio 9x16needs reference

Details

CategoryPortrait & Headshot
Aspect ratio9:16
InputNeeds a reference image
Example generated withGPT Image 2.5
Recommended modelsNano Banana Pro, Nano Banana 2, GPT Image 2.5
Original author@HustleXR · Original post on X
Original modelnanobanana

Why this prompt works

Everything here is designed to look unplanned, which is harder to prompt than perfection. The author lists combined reactions (head turned back, a hand rising to block the lens, a suppressed laugh), then deliberately degrades the capture with uncontrolled shake, smeared features, ghosting and a subject almost leaving the frame. It also tells the model to treat the reference only as loose inspiration so the face stays original. Our run, from a fictional reference, delivers a convincingly accidental frame: a blurred hand in front of white tiles and a half-hidden smile. Use it for social content that needs to feel real, and keep the blur instructions; without them it turns into a posed photo.

How to adapt it

VariableWhat it changesExamples
attached imageloose inspiration for face and vibean AI-generated portrait, your own selfie
Tokyo city sidewalk… white ceramic tile wallslocationa rainy Seoul alley, a neon-lit subway exit
Poses & Gesturesthe spontaneous reactionscovering mouth while laughing, waving the camera away

Tips

  • Keep 'strong uncontrolled camera shake'; it is the line that sells the accident.
  • Use 9:16, because the vertical phone frame is part of the illusion.
  • Only use photos of yourself or consenting people as the reference.

Related prompts

Long-Exposure Crowd Street Portrait Prompt1:1Long-Exposure Crowd Street Portrait Prompt@Taaruk_
Chinese New Year Nine-Grid Greeting Portrait Prompt1:1Chinese New Year Nine-Grid Greeting Portrait Prompt@wanerfu
Monochrome Men's Fashion Editorial TriptychReference1:1Monochrome Men's Fashion Editorial Triptych@harboriis
Luxury Wellness Lifestyle Four-Photo Series Prompt1:1Luxury Wellness Lifestyle Four-Photo Series Prompt@xmliisu
Color Box Room Fashion Editorial from Your PhotoReference1:1Color Box Room Fashion Editorial from Your Photo@Samann_ai
Olive Velvet Saree High-Fashion Studio Portrait1:1Olive Velvet Saree High-Fashion Studio Portrait@Flora_Janer8
Museum-Style Chinese Heritage Breakdown Infographic1:1Museum-Style Chinese Heritage Breakdown Infographic@MrLarus
3D Fictional World Map Guide Poster Prompt4:53D Fictional World Map Guide Poster Prompt@TechieBySA
Restaurant Brand Identity Mockup Board Prompt9:16Restaurant Brand Identity Mockup Board Prompt@MrLarus
Pistachio Baklava Four-Module Dessert Ad Prompt3:4Pistachio Baklava Four-Module Dessert Ad Prompt@kaanakz
Paper Fragment Grid Portrait Poster Prompt1:1Paper Fragment Grid Portrait Poster Prompt@Arminn_Ai
Exploded View Product Ad with Inner Mechanics1:1Exploded View Product Ad with Inner Mechanics@azed_ai
← PreviousLong-Exposure Crowd Street Portrait PromptNext →Monochrome Men's Fashion Editorial Triptych
Cinel AI

Cinel AI is a free, unlimited AI text-to-image generator with prompt-based editing and AI image-to-video tools. Create images without signing up, edit with GPT Image 2, Seedream 5 Pro, and Nano Banana 2, then turn still frames into video with Seedance 2.5, Veo 3.1, and Kling 3.0.

ProductsFree AI Image GeneratorAI Video GeneratorImage TemplatesWorkspaceText to Image GeneratorImage to ImageText to Video GeneratorImage to VideoAI Image EditorBackground Remover
PromptsAll promptsPortrait & HeadshotProduct & E-commercePosters, Logos & Graphic DesignInfographics & UI3D Characters & FigurinesFood & DrinkIllustration & AnimeCreative ScenesGPT Image 2.5 promptsSources and takedown

AI Image Models

KolorsZ-Image TurboSeedream 4.0Seedream 4.5Seedream 5.0 LiteSeedream 5 ProGPT Image 2GPT Image 2.5Nano Banana 2 LiteNano Banana 2Nano Banana ProNano Banana

AI Video Models

Seedance 1.0 TurboSeedance 2.5Seedance 2.0 MiniSeedance 2.0MiniMax H3Kling 3.0Kling 3.0 TurboKling O1Kling O3Grok Imagine Video 1.0Grok Imagine Video 1.5Wan 2.5Wan 2.6Wan 2.7Veo 3.1 FastVeo 3.1 ProVeo 3.1 Fast BetaVeo 3.1 Pro BetaSora 2
CompanyPricingAboutContactsupport@cinel.aiPrivacyTermsAcceptable Use
© 2026 Cinel AI. All rights reserved.