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. People Walking on Glass, Shot from Below

Worm's-Eye View of People Walking on Invisible Glass

View from under a plane of completely transparent plexiglass. We are looking straight up.  are walking on the plexiglass. In the background is a . No buildings visible. No edges or separations in the plexiglass. It’s as if the plexiglass isn’t even there. We are very close to the people. The people are in the process of walking. The people are walking generally . The soles of their shoes are very close to the foreground.

9 credits at 1K. Ratio 1:1.

text only

Details

CategoryPortrait & Headshot
Aspect ratio1:1
InputText only
Example generated withGPT Image 2.5
Recommended modelsNano Banana Pro, Seedream 5 Pro, Z-Image Turbo, Kolors
Original author@cfryant · Original post on X
Original modelnanobanana

Why this prompt works

The trick here is subtraction: the prompt keeps removing anything that would explain the scene, with no buildings, no edges and no seams in the plexiglass, 'as if the plexiglass isn't even there'. What remains is a sky full of people seemingly walking on air, with shoe soles almost touching the lens. Specifying that they walk 'generally from left to right' gives the crowd a direction, so it feels like a moment rather than a collage. Our result has five people in jeans and sneakers striding overhead, worn rubber soles in sharp focus, against a clean blue sky. It's a striking frame for footwear brands, urban festivals or concept covers. Try a sunset sky.

How to adapt it

VariableWhat it changesExamples
Many peoplewho walks overheada group of dancers, commuters with umbrellas
pure blue skybackgroundsunset sky, starry night sky
from left to rightwalking directiontoward the camera, in a circle

Tips

  • Keep all the 'no edges, no buildings' lines; they create the floating illusion.
  • For a sneaker ad, describe one pair of shoes in detail and place it closest to the lens.
  • Add 'wide-angle lens' for more dramatic perspective.

Related prompts

Night Train Platform Portrait with Chibi DoodlesReference1:1Night Train Platform Portrait with Chibi Doodles@harboriis
Multi-Arm Professional Studio Portrait PromptReference4:5Multi-Arm Professional Studio Portrait Prompt@Samann_ai
Chiaroscuro Windswept Hair Close-Up Portrait1:1Chiaroscuro Windswept Hair Close-Up Portrait@Naiknelofar788
Coastal Cliff Menswear Diptych Portrait Prompt1:1Coastal Cliff Menswear Diptych Portrait Prompt@2abhisheknaks
1970s Autumn Café Steps Fashion Portrait Prompt1:11970s Autumn Café Steps Fashion Portrait Prompt@2abhisheknaks
3x3 Headphone Lifestyle Storyboard Grid Prompt1:13x3 Headphone Lifestyle Storyboard Grid Prompt@oggii_0
Graphic-Novel Eyes Strip Cinematic Poster PromptReference1:1Graphic-Novel Eyes Strip Cinematic Poster Prompt@Abhiew_
Skincare Bottle on Stone and Mirror, Sunlit1:1Skincare Bottle on Stone and Mirror, Sunlit@Kerroudjm
Japanese Summer Soda Bottle Ad Prompt3:4Japanese Summer Soda Bottle Ad Prompt@old_pgmrs_will
Floating Taco Cinematic Food Action Shot2:3Floating Taco Cinematic Food Action Shot@meng_dagg695
Woman Bursting from a Phone Pouring Cola Prompt1:1Woman Bursting from a Phone Pouring Cola Prompt@meng_dagg695
Radial Exploded View Product Teardown Prompt1:1Radial Exploded View Product Teardown Prompt@AllaAisling
← PreviousMulti-Arm Professional Studio Portrait PromptNext →Night Train Platform Portrait with Chibi Doodles
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.