Konic

现在的游戏好像没那么好玩了

Son used Ai to turn his mother’s old photos Into a 60th birthday gift 💝

This Dragon Ball Z Live Action Cast Is Hilarious

Multiple vehicles transform simultaneously into combat mechs in a city battle, opening on a wide shot of chaos, camera weaving between transforming units as parts shift and lock, then transitioning into a fast-paced tracking shot following one mech engaging enemies, explosions chaining across the environment, ending with a massive coordinated attack. BY @PixVerse_ Prompt by @CharaspowerAI

@maxescu SD2 or GPT?

Prompt: A photorealistic 16:9 in-game screenshot of a fictional next-gen open-world RPG titled "BULK: A Members-Only Adventure". Third-person over-the-shoulder camera following the player character — a tired suburban mom in yoga pants pushing an oversized flatbed cart down the aisle of a Costco warehouse store. Scene captures hyper-realistic warehouse lighting, towering pallet stacks, a free sample station ahead with an NPC in a hairnet glowing with a yellow exclamation mark above her head. Game HUD overlay: top-left mini-map showing aisle layout with quest markers; top-right stamina bar labeled "PATIENCE" three-quarters full; bottom-left compass with objective text "PRIMARY: Locate Kirkland Almond Butter (Aisle 11)" and below "SECONDARY: Sample 3/5 cocktail meatballs"; bottom-right item quick-slots showing membership card, car keys, snack bar; center crosshair with subtle interaction prompt "[E] Take Sample". Cinematic depth of field, slight chromatic aberration, photo-mode quality. All UI text crisp and legible. Realistic Costco signage in background spelled correctly. No watermark, no real Costco logo (use generic warehouse-club aesthetic).

Costco, the game Prompt below:

You must try this. GPT Image-2 can do PALM reading and I’m so here for it. Full prompt below ⤵️

The bigger Titan 😱🔥

ChatGPT just made images look TOO real I tried ChatGPT Images 2.0… and now I don’t trust the internet anymore this is not photography this is AI 10 scary good real life examples: 1. 4x4 grid of chaotic college dorm moments

Let's go on Adventure with Seedance 2.0 🔥✨ on @higgsfield Prompt: Subject: Downhill Kart Race Style: Hyper-realistic, Action Adventure, GoPro Aesthetic Action: A fast downhill race following a lead pack of kids on go-karts. They speed down a grassy slope, drifting through uneven terrain with dust and grass clippings flying. The "insane" twist: As the karts reach the edge of the valley, the lead racer pulls a hidden lever. Suddenly, the karts deploy makeshift, rocket-powered thrusters and makeshift gliders. The karts don't stop at the cliff’s edge; they launch into the air, soaring over the village below as the engines roar and blue flames erupt from the exhaust. Camera Movement: Dynamic Chase Cam. The camera moves forward rapidly, weaving between racers. As they hit the cliff edge, the camera performs a seamless transition into a dizzying free-fall perspective, tilting downward to show the massive drop before leveling out to follow the karts gliding through the air. Environment: Sunny rural landscape, vibrant greens and blues. The peaceful valley floor is now a mile below, with the village looking like a miniature model set. Details: Motion blur on the edges, intense vibration of the karts. New details: Heat haze shimmering from the rocket thrusters, lens flares as the sun hits the metallic gliders, and the visible shock on the racers' faces through their goggles as they break the sound of wind with a sudden sonic pop. @HFcollaborators

Hairstyle Analysis by ChatGPT Image 2.0 Prompt: Create a hairstyle analysis graphic using this portrait. Show side-by-side hairstyles comparisons to highlight which hairstyles suit the subject best Make it visual-first, with short labels only and no paragraphs.

Seedance 2 ile dans videosu yapmak artık çok kolay 💃 1. Referans choreography sheet’i yükle 📄 2. Dansçı görselini yükle 👠 3. Koreografiyi tek promptla akıt 🎬 16 adımlık hareket planı ➜ kesintisiz dans videosu 🔥 Prompt takibi gerçekten başka seviye 🚀 Prompt: (thanks to @Ciri_ai ) 👇 Create a seamless 15-second dance choreography video based on the uploaded reference image. Use the female dancer from the reference image as the main character

📢Face Anything: 4D Face Reconstruction from Any Image Sequence Transformer model for 4D face reconstruction and dense tracking: - predict canonical facial coordinates per pixel - tracking as reconstruction in canonical space - geometry + correspondences in one forward pass Key idea: a shared canonical space across frames - correspondences as nearest neighbors - no motion or deformation estimation Stable geometry and tracking, even under large expressions and viewpoint changes - check out our results! 🌐 kocasariumut.github.io/FaceAnything ▶️ youtu.be/wSGHpAscp0Y Great work by @UmutKocasa4344, @SGiebenhain, @richard_o_shaw

Create a Fight Sheet and use it for your Scene!!!

A high-speed FPV drone shot tracking a thundering cavalry charge in a medieval valley. Mud splashes onto the lens as horses gallop at full speed. Intense motion blur, sunlight flickering through dust clouds, cinematic lighting, ultra-realistic 8k. #Seedance2 @floraai 🎬

This is my work.👌 GPT- image 2➕Seedance 2.0

啊！生成了挺好的分镜提示词，但是视频跑不出来！ 有大佬帮我看看吗？求求🥺 提示词： A cinematic 3x3 storyboard grid showing a dramatic action sequence inside a modern convenience store at night. The style is dark, moody, high-end film stills, realistic lighting, slight teal-green color grading, shallow depth of field, motion blur in action shots. Each of the 9 panels should be separated by thin black borders, forming a clean storyboard layout. VERY IMPORTANT: Each panel has small white text in the top-left corner showing: Shot number (SHOT 1–9) Camera type (e.g. ARRI Alexa Mini LF) Lens (e.g. 35mm, 50mm, 85mm) Subtle cinematic subtitles in English at the bottom of each frame describing the action Maintain consistent character appearance: a young athletic Asian woman, energetic and physically strong, toned body, lively yet intense expression, wearing a pink spaghetti-strap sports top and a pink sporty mini skirt, with practical athletic styling suited for fast movement ⸻ Scene breakdown (must follow composition closely): SHOT 1 – Medium shot, 35mm A young athletic woman standing in a convenience store aisle, casually looking at a snack package. She wears a pink spaghetti-strap sports top and a pink sporty mini skirt. Fluorescent lighting, calm atmosphere. SHOT 2 – Wide shot, 24mm Store doors burst open violently. A large group of heavily armed tactical soldiers rush in. SHOT 3 – Over-the-shoulder shot, 50mm From behind the woman, facing a line of soldiers aiming rifles directly at her. SHOT 4 – Extreme close-up, 85mm The woman’s eyes sharpen with focus, showing intense determination and explosive energy. Background slightly blurred. Subtle tension builds. SHOT 5 – Motion blur tracking shot, 35mm The woman suddenly dashes forward at superhuman speed. Her pink athletic outfit flows dynamically with the motion. Soldiers appear blurred. SHOT 6 – Wide action shot, 28mm She strikes multiple soldiers mid-air, dynamic combat pose, powerful athletic movement, debris flying. SHOT 7 – Low angle shot, 35mm Close combat: the woman overpowering soldiers on the ground, fast brutal movements, showcasing strength, agility, and control. SHOT 8 – Wide aftermath shot, 24mm All soldiers are down. The woman stands in the center of the store, surrounded by fallen bodies, breathing steadily, calm and dominant. SHOT 9 – Medium wide shot, 35mm The woman stands calmly in the destroyed store, untouched. Shelves messy, silence after chaos. Her pink sports outfit contrasts sharply with the dark cinematic environment. ⸻ Style keywords: cinematic, film stills, ultra realistic, dramatic lighting, teal color grade, shallow depth of field, motion blur, high detail, 8k, storyboard layout, grid composition, professional filmmaking, ARRI Alexa look

今回いちばん苦戦したのは、生成映像に「腕を修理している」と理解させることでした。 そもそも腕が壊れていない。 瓦礫が集まらずに急に腕が生える。 このパターンが多かった。 seedance2.0の次バージョンに期待。 ロボット映画は作れます！

This is beyond my expectation

転売ヤーを制圧して秩序を守るゲームのプレイ映像。 GPT Image 2 × Seedance 2.0で作る架空ゲーム動画、なかなか楽しい。