tiny footer interaction tip left: hover follows the text... area right: hover follows the whole row same spacing, no dead zones fast in, slow out 1 prompt fix on client's websiteshow more

Hailuo MiniMax Design MiniMax Design (H3) MiniMax (official) Another... Prototype Another Test - PASSED SOLESHIFT° A playful footwear e-commerce concept where every cursor hover transforms the shoe, typography, colors and motion graphics. No single text error or inaccuracy throughout all the video. The model passed the followings successfully - Animated Shape Layers - Kinetic Typography - Cursor Hover Update - Bounce Effects - Wiggle Effects - Live Background - Micro Text Renders - Ease in Ease out Keyframes Tip: Use Visual Hierarchy - One of the most essential core design principle. Prompt & Workflow belowshow more

Well, that escalated quickly 😅 I started experimenting with... Spline and Omma AI Studio and Canvas, and somehow ended up with an interactive 3D robot that follows your cursor. Hover over the icons, and each idea behind the logo appears on its face. No idea where else I’d use this, but for presenting the logo of an innovation store, it feels just right!show more

Two suspected highway thieves were arrested two nights ago... by members of the public in connection with a series of vehicle break-ins and phone-snatching incidents around the Achimota Forest and Overhead area. The arrest follows a string of targeted attacks on slow-moving vehicles caught in traffic, carried out by criminals who operate within the vicinity.show more

004/100 Buttons. A bit of the process on building... an animation. When looking at a finished animation or in this example a finished button, it can look quite complex inside the CSS. But when building it, it’s more like a lot of simple steps, one after another. Here I had the idea to make some kind of text animation like the footer logo on the Osmo site. I try to add the base animation with no complex easing, for example transition: translate 0.4s ease. Starting with just moving the one text from bottom to top and the other text to top. Adding a stagger, play around with it. Searching for a way to make it more circular. On the research I found the sin() function inside CSS which can build a more smooth non linear curve for the stagger which creates this circular effect. And step by step adding more complexity like, different easing for hover/hover-out, opacity, 3D transform and more. I use also the sin() function to rotate the letters, so the middle ones are getting more rotated than the outer ones. Another thing which helps is to add a small delay on hover, for example 0.05s or 0.1s, you don’t really see the difference, but when you hover pretty fast on and out it doesn’t get that jumpy. I’m using here GSAP’s SplitText to split every char into spans. And then I’m adding a CSS index variable to every span, starting from the center. SplitText can provide CSS index variables, but you cannot tell it from which direction. For the sin() it’s also important to have a max length, so I add another CSS variable with the max char number on it. Crafting 100 Buttons with Osmo ⏳ Total time: 63hshow more

Working with animation styles in Runway I love how... it generated two completely different shots off the same prompt. On the left, we get a nice zoom out and a change in focus. On the right, it expands the world in front of the character. H/t Curious Refuge for the prompt: animation shot, cute girl with amazed expression, looking around in a magical candy land.show more

Hey All! Thanks for all the new follows and... such. I realized today that a lot of people thought I was dead or retired lol but NO!! 1) I still have a YouTube! (making videos, but solo reactions simmered a long time ago.) 2) I’m still in Japan. 15 years, 10 years same company!show more

Every website you’ve ever used is broken in a... way you never noticed and it’s been this way for 30 years... A Midjourney engineer finally just fixed it. It’s called Pretext: A tiny library that lets websites lay out text the way magazines and newspapers do, with text flowing around images, wrapping into columns, and fitting perfectly into any shape, all at 120fps. This has been basically impossible on the web for 30 years. Every website you’ve ever used relies on the same clunky system from the 90s to figure out where text goes on screen. Pretext bypasses it entirely. 500x faster. The demos look like they shouldn’t be possible in a browser. Go look.show more

Split-screen test on Flux 3! Prompt : Split-screen video... showing the same real-time action from two different camera angles. The screen is divided vertically into two equal halves. On the left side, show a static, wide overhead view from a ceiling-mounted camera in the back corner of the room. The full room layout is visible: a couch, coffee table, rug, bookshelves, and a tall shelf near the wall. The cat is perched on top of the shelf. At the 2-second mark, it suddenly jumps, flips mid-air above the furniture, and lands gracefully on the coffee table. On the right side, show the same action in perfect sync from a side, eye-level camera placed low beside the couch. The view includes the shelf, the space between, and the coffee table. The camera follows the cat’s leap, capturing body motion, twist, and landing.Both sides must be precisely synchronized, showing the exact same event from different angles with consistent lighting, physics, and timing.show more

I improved the prompt 👇 { "archetype": "Artistic /... Fashion / Conceptual", "duration": "15s", "prompt": { "concept": { "title": "Ink Smoke Art – Kinetic Title Sequence", "description": "Continuous 15s one-take black ink-smoke motion graphics. Five characters form from living smoke on pure white void, each performing a characteristic motion while smoke stays alive. Formation direction alternates every 3s. Characters dissolve smoothly through smoke into the next. Kinetic uppercase text emerges from smoke on the complementary side. Final invitation text at the end. Always fluid, never static.", "duration": "15s", "rhythm_structure": { "0-3s": "[image1] forms right-to-left + characteristic motion, text left", "3-6s": "Morph to [image3] left-to-right + characteristic motion, text right", "6-9s": "Morph to [image2] right-to-left + characteristic motion, text left", "9-12s": "Morph to [image4] left-to-right + characteristic motion, text right", "12-15s": "Morph to [image5] right-to-left + characteristic motion + final invitation text" } }, "camera_direction": { "shot_type": "Strict continuous one-take, locked or micro-drift", "forbidden": ["No cuts", "No teleportation", "No hidden transitions", "No freeze frames"], "camera_journey": "Centered medium-wide on pure white void. Locked or extremely slow drift. All energy from living smoke and character motion." }, "typography": { "allowed_words": [ "INK SMOKE ART", "MOTION GRAPHICS", "MIDJOURNEY + H3", "PROMPTS by TechHalla", "MAKE IT YOURS" ], "treatment": { "not_flat_overlay": true, "required_properties": [ "Formed from dense black smoke particles and tendrils", "Physical volumetric depth", "Smoke occlusion and interaction", "Subtle continuous warping", "Bold uppercase condensed sans-serif", "Kinetic emergence synchronized to morphs and directional flow" ] } }, "visual_style": { "overall": "Black ink-smoke art, ultra high-contrast monochrome, pure white void, volumetric living smoke with dense cores and wispy filaments", "inspired_by": [ "[image1]– exact silhouette, long hair, armor, smoke density", "[image2]– exact suit, gun, coat edges, frontal presence", "[image3]– exact spiky hair, martial pose, wristbands, full-body mass", "[image4]– exact cowl, cape flow, dramatic profile", "[image5]– exact straw hat, back view, coat tails, dynamic stance" ], "color_palette": ["pure black", "deep charcoal smoke", "pure white void"], "materials_and_texture": "Living ink smoke, variable density, continuous filament motion, soft volumetric edges, constant micro-turbulence" }, "motion_language": { "follows_music": false, "core_behavior": "Never static. Smoke always swirls. Characters form while performing characteristic motion. Morphs only through smoke densifying and reforming. Direction alternates every beat. Visible smoke motion in every frame." }, "storyboard": { "total_beats": 5, "beat_duration": "3 seconds each", "beats": [ { "id": "01", "time": "0.0–3.0", "description": "Pure white void. Black smoke enters from right, flows left, coalesces into [image1]. Smoke lives on hair, armor and cloak while figure performs slow head turn and shoulder roll, long hair and cloak billowing as if scanning the horizon. Text “INK SMOKE ART” forms left from arriving tendrils into bold uppercase interacting with smoke. End of beat: form smoothly dissolves into swirling smoke." }, { "id": "02", "time": "3.0–6.0", "description": "Smoke reverses, enters from left, flows right, reforms into [image3]. Smoke swirls on limbs and spiky hair while figure performs slight crouch into charged fighting stance, fists clenching, body vibrating with residual energy. Previous text dissolves; “MOTION GRAPHICS” emerges right from arriving smoke into bold uppercase. End of beat: form smoothly dissolves into smoke." }, { "id": "03", "time": "6.0–9.0", "description": "Smoke reverses, enters from right, flows left, reforms into [image32. Smoke lives on suit edges and coat while figure performs slow raise of gun-holding arm into low ready position, coat flaring, determined forward lean. Text “MIDJOURNEY + H3” forms left from rising particles into bold uppercase. End of beat: form smoothly dissolves into smoke." }, { "id": "04", "time": "9.0–12.0", "description": "Smoke reverses, enters from left, flows right, reforms into [image4]. Smoke billows on long cape while figure performs dramatic cape sweep and subtle crouch, head tilting under cowl as if listening. Text “PROMPTS by TechHalla” emerges right from trailing cape smoke into bold uppercase. End of beat: form smoothly dissolves into smoke." }, { "id": "05", "time": "12.0–15.0", "description": "Smoke reverses, enters from right, flows left, reforms into [image5]. Smoke rises and trails on coat tails and hat while figure performs confident stance shift, straw hat tilting, coat tails whipping backward, one arm slightly extending forward. Previous text dissolves; residual smoke briefly reforms titles, then “MAKE IT YOURS” emerges centered from final smoke into bold uppercase as smoke slowly dissipates into white void, never fully static until end frame." } ] } } } Check out the previous one along with the Midjourney prompt for the images!show more

Traders have been asking us: please add analyst ratings... directly on Finviz charts. Today, that feature is live. This adds a powerful new layer of clarity: 1. Track how often Wall Street analysts are late, early, right or completely wrong 2. Compare Wall Street ratings directly against your own technical and fundamental analysis. Every stock chart on Finviz now displays Wall Street analyst rating markers. Hover over a marker to instantly see the firm name, rating action, date, and price target all in context of the chart. Check it outshow more

gemini omniflash is actually f*cking cracked. you can animate/edit... any video with a text prompt. character swaps, object transforms, full environment changes without regenerating/rotoscoping. everyone using AI to to animate and edit videos right now hits the same wall. the clip comes out 90% right and you regenerate from scratch hoping the 10% fixes itself. it never does. the fix is using your video as the input. omniflash edits what's already there instead of rolling the dice again. here's what's in the system: > the two-layer premiere trick: generate the same shot twice (one with background removed), stack them, cut at one frame, instant scene change > character swap with a single reference image (plus the one line you need or the model keeps the original's features) > object transforms that leave the rest of the frame untouched: stone into glowing sphere, candles into flowers > style transfer from an image reference instead of text, way more accurate > why stacking edits in one prompt breaks everything and the exact step order that doesn't > the audio limitation nobody mentions and how to work around it i packaged every prompt, the edit sequence, and the premiere layering setup. RT + reply "OMNI" and i'll send it over.show more

Step 3: Seedance prompt Here is the core prompt... I used: First-person broom-riding POV, cinematic ultra-fast one-take chase. Strictly follow the red flight path in the image. The Golden Snitch stays ahead as the main chase target, but it should not stay fixed in the center. It moves left, right, up, and down during the flight, making the chase feel more alive. Only show the broom handle, gloved hands, and red sleeves. Never show the rider’s face. Chase through the stadium, around the towers, over Black Lake, through the bridge arch, and back to the pitch for the final catch. No red lines, no arrows, no broken broom, no duplicate faces, no jump cuts. Tip: you can also add useful refs, like a Golden Snitch ref or a first-person POV keyframe, to make the target and camera angle more stable. Thanks for watching. More AI video workflows at Larus Canus ⚡show more

Created on seedance 2.0 Prompt: Create a 15-second cinematic... sci-fi action sequence in a modern city during an overcast day. A fearless young woman in a sleek black futuristic combat suit sprints through empty streets as a massive explosion erupts behind her, sending smoke, debris, and sparks into the air. The handheld camera follows with dynamic tracking shots, dramatic slow motion, and fast action cuts. As she runs, glowing red mechanical wings deploy from her back, unfolding with illuminated energy lines and metallic detail. She accelerates toward a towering alien monster invading the city. The two collide in an intense mid-street battle with powerful punches, aerial dodges, shockwaves, flying debris, and cinematic camera movements. End with the winged warrior landing in a powerful hero pose in the middle of the destroyed road, wings fully extended, smoke drifting around her. Ultra-realistic, blockbuster VFX, volumetric lighting, HDR, realistic physics, motion blur, shallow depth of field, Unreal Engine 5 quality, 4K cinematic, no text, no watermark, 16:9.show more

NO MERCY FOR TERRORISTS: Russia systematically dismantles Kiev's military... hubs in a massive wave of justice! As Zakharova fiercely corrected the narrative, Russia's historic retaliatory strikes are strictly wiping out military-industrial centers. This crushing response follows Kiev's desperate, horrific terrorist attacks on civilians—massacring student athletes in Bryansk, bombing dorms in Lugansk, and killing a 6-month-old baby in Moscow. As Putin stated, Ukraine is collapsing on all fronts and has nothing left but terror. 🇷🇺💪show more

A new split-screen prompt experiment. Prompt : Sweeping romantic... harbor festival at sunset with lanterns, sea wind, warm amber glow, and crowds moving through music and laughter. Split screen vertically for the full sequence. On the left side, follow her with a soft floating camera weaving through dancers and market stalls as she suddenly notices him across the harbor square. On the right side, show the same instant from his perspective, a slow push through lantern light and passing couples as he spots her at exactly the same moment. Both halves mirror the same event but with different emotional emphasis, her side showing hesitation and vulnerability, his side showing disbelief and hope. The camera on each half circles slightly as they begin moving toward one another through the crowd, with near misses, shifting eyelines, and people crossing frame in sync. Climax: both sides reach the seawall at the same time, and the split screen collapses visually in spirit as their hands meet. Ending: hold the split for a few seconds longer even in the embrace, showing each face from the other’s point of view as lanterns rise behind them.show more

"Scene 1: a blond 20-year-old girl lying on her... bed, whining and rolling around as if she’s ‘dying’ without sugar. Add funny, over-the-top expressions like a parody. Scene 2: text overlay Day 1 without sugar. Scene 3: quick flash to Day 30 → same girl now full of energy, glowing skin, smiling, with happy vibe. Style: humorous transformation, fast cuts, meme energy." those telling me "ai slop" in the comments of my previous sora videos ... really don't understand the new paradigm we're in right nowshow more

omni motion control is f*cking cracked the left clip... is the original. the right is 100% ai, same video, one prompt i grabbed a weight loss transformation off tiktok, gave omni a single image of a totally different girl, and it rebuilt the whole clip around her. she copies the original move for move, down to the dumbbells and the timing. and she doesnt exist and i barely lifted a finger. this was the entire prompt, word for word: "replace the person in the video attached with the person attached in the image, make sure the weight loss transformation is exactly the same from fat to fit" gpt image 2 made the character and omni did the rest. thats it brands pay creators to reshoot the same winning ad with different people just to split test. now you film it once and swap the face for cents. one video turns into 50 i wrote up the full setup: > the prompt method that transfers motion without breaking > how to find reference videos that work > how to batch this out at scale comment "MOTION" and ill send it overshow more

Step 1 : input your char reference, poster and... your product into GPT Image 2 and then put the prompt : Use the woman on image 1 as the main subject. create a vertical poster ad inspired by the reference poster style. show the image 1 woman holding the kimchi jar with her left hand, while the right hand eating kimchi to her mouth. with framing wide lens, low angle from the reference poster. This step is where you lock the visual direction. Step 2 : take the generated image into Seedance 2.0 and convert it into motion. Set it to 1080p if your design includes a lot of typography, this helps preserve text clarity. You can also strengthen your prompt by adding keywords like: “dynamic motion design commercial advertisement” to push the result closer to a polished ad style. Important note : If your design contains heavy typography, expect some inconsistencies in text rendering. The best approach is to generate multiple variations and select the cleanest result. For this sample, I generated it 4 times before landing on the final version.show more

"It's not left vs right, it's all of us... vs the 1%!" No, it's left vs. right, BECAUSE of the 1%. The left has no theory of mind for the 3rd world. They think that illiterate savages are going to come here on a plane and magic-poof into baseball-pie american heroes overnight. The left thinks: "anyone who is a good guy thinks like me, and anyone who doesn't think like me is a bad guy." Then, they assume the best of the 3rd world masses and the worst of their own countrymen. After all, "they don't think like me, so they must be BAD! And brown people are ALWAYS GOOD, so they MUST think like me!" Leftists are lost, confused children who can never figure out how real life works. Even as their precious, diverse allies attack them in the streets, they keep saying: "Stop! We're on the same side! Against the NAZIS!" You don't get to pick which side you're on, bruv. Your enemies pick for you. Your skin is your side.show more

🎉 The official mint link for the Beaver Builder... NFT collection on Linea.eth is live! 🎉 🚀 But note: Minting will take place on the NFTs2Me ⧫ NFT Toolkit for Creators and starts at 6 PM UTC. ⏰ Mint Schedule: 6 PM UTC: Mint starts for WL 1 7 PM UTC: Mint starts for WL 2 8 PM UTC: Public mint opens Rules: WL 1 and WL 2: Limited to 1 mint per wallet Public mint: Limited to 2 mints per wallet Cost: 0.01 ETH for everyone (in a Valocracy, everyone follows the same rules!) 🦫 NFT Utility: Owning a Beaver Builder NFT unlocks exclusive access to the Beaver DAM, an innovative model for building DAOs in Web3! 🦫 Pro Tip: Ensure your wallet is connected, and your funds are ready to avoid missing out! 👉 Official Link: 🛡️ Reminder: Be cautious of suspicious links. Minting happens exclusively on the official NFT2ME platform. 💡 It's time to redefine the future of Web3 communities!show more