2000 artistes ont été mis au défi de créer une animation 3D de 5 secondes pour faire descendre une balle du haut vers le bas de l’écran.
Toutes les séquences ont ensuite été assemblées pour créer une gigantesque machine à billes collaborative.
GPT image 2 on ChatGPT
Use this prompt
Create a propaganda poster themed around the character “BLANKA” with a consistent and hierarchical main visual composition.
Poster structure:
Top (top half): Use the character’s head, facial features, mask, or half-body silhouette as the main large-sized visual element, forming an easily recognizable iconic image.
Middle to bottom: Place the full-length character as the second subject, with a stable standing pose or light movement, serving as the center of the visual composition.
Visual style:
Use double exposure and narrative collage techniques in and around the character’s large silhouette.
Combine various elements such as:
layered scenes
additional images
small character interactions
supporting elements
environmental backgrounds
all arranged in layers of clouds, ink, and white negative space.
Additional composition:
Place supporting elements on the left and right to create narrative tension and spatial variation.
Add a vertical flowing visual line connecting:
main character
internal collage elements
large silhouette at the top
to reinforce visual continuity.
Aesthetics:
Maintain the use of large amounts of negative space.
The edges are processed with the effects of:
ink diffusion
soft blur
visual fragmentation
to create a poetic and “breathing” Eastern aesthetic. Add more pop and striking colors
Overall style:
Consistent, premium, and refined.
Focus on:
visual layering
narrative
key visual impact
visual language of serial posters
Size: A4
AI video of fallen celebrities sparks debate on whether it’s a good thing or bad. Big names like Michael Jackson, Tupac Shakur, and Bob Marley spotted together at an awards show. Thoughts? 👀🤔
Google Gemini Nano Banana Pro
Prompt:
Ultra-high-quality hyper-realistic photo featuring a real human and a giant 3D Pixar-style version of THE SAME person — both strictly based on the uploaded reference image. The real person and the Pixar character must have identical facial structure, hairstyle, facial expression, body proportions, height, and clothing.
Both are wearing a knitted sweater with a gradient from light yellow to pink, high-waisted blue jeans, and white high-top sneakers.
The pose must exactly match the reference: the real person stands relaxed with a friendly smile, with their hand naturally resting on the shoulder of the Pixar character. The Pixar version stands slightly wider, arms confidently positioned near the pockets, with a playful sly smirk, one raised eyebrow, and expressive Pixar-style eyes.
The Pixar character should be proportionally larger, but anatomically identical to the real person. The facial expression, head tilt, posture, and body language must precisely replicate the reference image.
Clean gray-blue studio background, soft even studio lighting, realistic shadows, crisp fabric texture, smooth Pixar-style skin shading, cinematic sharpness.
DO NOT change the pose, reaction, clothing, or proportions. Strict adherence to the reference.
🚨PromptShare🚨
Okay… Banana 2 does not play
when it comes to exploded views.
Clean part separation. Accurate perspective.Full consistency.
PROMPT
product design, [object or vehicle with material accents], exploded view diagram, white background, three-dimensional, highly detailed internal components, studio lighting, product photography, best quality
I love experimental Nano Banana prompts. Am always surprised how well this style works.
2x2 grid, do this 4 famous manga <spatial_map>
[ OUT OF FOCUS LIBRARY BACKGROUND ]
[ VERTICAL MANGA PANEL ART ]
[ (Action Scene from Series) ] <--- Backplate
|
[ 3D [CHARACTER] JUMPING OUTWARD ] <--- Hero Object
[ (Mid-Air Pose, Dynamic Action) ]
|
[ OPEN BOOK / GRASS / DEBRIS BASE ] <--- Ground
[ (Infer based on [SERIES_NAME]) ]
[ TABLE SURFACE ]
</spatial_map>
INSTRUCTION:
1. Render as a high-end "Pop-Up Book" aesthetic.
2. The Background is flat paper. The Character is full 3D plastic/resin.
3. Lighting: "Toy Photography" style (Softbox, vibrant colors).
Seedance 2.0 continues to blow my mind. This is image to video. I love creating chase sequences but the way it understood this scene with superb prompt adherence is what really impresses me. If you want to create crazy chase sequences like this, Seedance 2.0 handles it very well!
I am part of @capcutapp CPP and we're allowed to post some more results. #Capcut @Seedance2
🟡Prompt: A cinematic and chaotic tracking shot with handheld camera motion and camera shake shows an explorer holding an ancient scarab artifact. They are running away from a giant pursuing mummy. Debris and dust clouds can be seen. The mummy is causing sections of the ancient wall to crumble. The explorer runs away frantically while occasionally looking back, you can hear her heavy breathing. She continues running until she narrowly escapes once the mummy almost grabs her but it hits a pillar causing it to fall on itself, the explorer then continues running into the entrance of a tomb.
Future of game graphics is INSANE
Completely photorealistic video games are just a few years away with AI. We are not going to be able to tell if the gameplay is real or not.
Look at how Nano Banana transformed this old, damaged image. It managed to make it look completely brand new 🔥
Nano Banana Pro on @GeminiApp
Prompt:
"Restore the image while preserving the exact facial identity of the subject and facial expression. Fix any tears, wrinkles and human artifact in the photograph itself. Restore the coloring perfectly, sharpen the image and make it full HDR. It should look like a Nikon DSLR camera took the photograph. Maintain the subjects exact facial features, expression and details. "
Convert yesterday’s faded film into today’s high-definition professional portraits.
Nano Banana Pro
Prompt:
Generate image based on reference images and prompt: ""Restore this old photo into professional portrait of DLSR - quality colour and detail, using an advanced upscaling algorithm comparable to the results from canon EOS R6 II. Ensure the restored the image looks natural, retains exact facial features, has great clarity......" "
Convert your Old and Dammage image in New Image 💫
Use Gemini Nano Banana Ai ☘️
Prompt:
"Ultra-realistic recreation of an old vintage photo, keeping the same original face (99% likeness, no alteration). Transform into a modern high-quality digital portrait with vibrant updated colors, smooth realistic skin textures, and natural lighting. The outfit and background should be upgraded into a clean, modern aesthetic while preserving the authenticity of the original pose and expression.