🚨 FREE H3 MINIMAX PROMPTS 🚨

Astorie AI is running a 7-day promotion where you can prompt Minimax H3 videos for free. There is basically a check-in process, and you also get 40 free credits on registration.

The promotion ends on September 17th. There is also an advertisement contest going on their site that you should enter; you have a chance to win a yearly subscription, and all posts on social media also get credits.

🍦Squishing Things (HappyHorse 1.1)

- Reference(s): Recommended
- Styles Support: Realism

"[00:00 - 00:01] Initial State
Prompt: Close-up shot, slightly high angle. A hyper-realistic sculpture of a tall beverage resting on a light wooden grain table. The object is entirely made of solid, matte, porous foam material. The main body is a cylinder of lavender-purple porous foam featuring a subtle debossed maple leaf logo. On top sits a large, highly detailed swirl of bright white porous foam resembling whipped cream. Background features a blurred cafe setting with wooden chairs and soft indoor lighting. Photorealistic, 4k, high detail, clean aesthetic, completely dry matte texture.
Action: Static hold, completely still, establishing the pristine foam object.

[00:01 - 00:05] The Crush Begins
Prompt: Two hands enter the frame and grip the lavender and white foam object. The hands squeeze firmly. The entire structure is revealed to be a solid, soft, porous foam material. The lavender-purple foam body crumples, dents, and squishes under pressure, showing a dry, sponge-like interior. The white foam swirl on top bends, flattens, and compresses realistically like soft clay. Satisfying destruction, ASMR visual. The white foam topping is kneaded together with the lavender foam body into a unified clay-like consistency; the white foam shouldn't suddenly disappear.
Action: Hands squeeze inward, the foam structure deforms, bends, and compresses.

[00:05 - 00:07] Kneading the Mixture
Prompt: Both hands pressing down firmly on the pile of mixed lavender-purple and bright white foam on the light wooden table. The material stretches and tears, showing a dry, crumbly yet cohesive play-doh texture. The white foam and purple foam are actively mixing together into a marbled pastel pattern. Soft shadows, diffused lighting, strictly matte and dry surfaces.
Action: Palms pressing down, fingers digging into the colorful porous foam.

[00:07 - 00:09] Final Squish & Ball Formation
Prompt: Hands gathering the mixed lavender-purple and white porous foam into a rough, satisfying ball. Kneading motion. The texture looks like dense sponge or soft floral foam, completely matte, airy, and porous. Satisfying tactile manipulation. Close-up on fingers manipulating the bi-colored porous material against the light wooden table and blurred cafe background.
Action: Lifting and squeezing the multi-colored foam ball.


Negative Prompt: Real liquid, real paper cup, real plastic cup, coffee, hot beverage, steam, splashing water, wetness, glossy reflections, melting, drinking, mouth, face, body, blurry, low resolution, distorted hands, extra fingers, missing fingers, mutated anatomy, cartoon, illustration, painting, harsh lighting, oversaturated, text, watermark, logo, shaky camera, fast motion, shiny surfaces, transparent materials, glass, ice cubes."

✨ Get access to Happyhorse 1.1 at OpenArt (20% discount with code "L1TMGOQ2" from all plans)

🏄‍♂️ Shotgun Surfing (Seedance 2.5)

- Reference(s): Recommended
- Styles Support: Realism

" 16:9, 25 FPS. Cinematic absurdist dark comedy. Use <<<Image1>>> for the adult Asian woman’s exact face, hairstyle, kimono & overall visual style. Preserve her design throughout.

Bright tropical surf, turquoise waves, sparkling sunlight. A kimono-clad woman surfs with flawless balance while carrying a shotgun, treating the situation like an entirely ordinary beach outing. Her completely deadpan expression contrasts with the chaos. Flowing sleeves, windblown hair, convincing board movement & ocean physics.

0–3s: Water-level tracking shot alongside her board as she carves across a rolling wave. Camera tilts from the spray to her composed face, revealing the shotgun. Other adult surfers casually ride the same wave farther ahead. Cheerful surf-rock music plays.

3–6s: A nearby surfer smiles & gives her a friendly shaka gesture. She returns a tiny, polite nod, then swings the shotgun toward him. One thunderous shot. Brief stylized blood spray as he tumbles backward into the water; his empty board pops upright. Whip-pan follows the splash. Music briefly drops out for the gunshot, then resumes cheerfully.

6–10s: Side tracking shot as she glides past another surfer. He notices the shotgun & frantically tries to steer away. She fires once; a small burst of blood punctuates his exaggerated sideways wipeout. The recoil makes her board wobble. For the first time, she looks mildly annoyed—at losing her balance. She recovers with an elegant turn.

10–13s: Wide frontal shot: she emerges through a curtain of sea spray while the remaining surfers scramble away in the background. Two abandoned boards bob behind her. She casually smooths a disheveled kimono sleeve, maintaining perfect posture.

13–15s: Fast push-in to a medium close-up. A tiny wave splashes her face. She blinks, visibly offended, then gives the ocean a cold sideways look. Abrupt music stop. Cut to black.

Audio: upbeat retro surf-rock, crashing waves, board hiss, two sharp shotgun reports, exaggerated splash impacts & a final small comedic water slap. No dialogue, subtitles or text. Brief non-graphic blood accents only. Keep the action readable, with distinct shots, clear screen direction & deliberate comic pauses."

✨ Get access to Seedance 2.5 at OpenArt (20% discount /w code "L1TMGOQ2" from all plans)

🥺 Gyaru Fight Showdown (Seedance 2.5)

- Reference(s): Recommended
- Styles Support: Realism

" @image1 fights three opponents inside a Japanese high school classroom in an intense, highly dynamic one-take action sequence. The classroom is filled with wooden desks, chairs, school bags, a chalkboard, sliding windows, curtains, fluorescent ceiling lights, posters, books, and scattered papers. The camera is extremely dynamic and close to the action, never static — fast-moving, constantly following, circling, ducking, whipping, and pushing through the fight, immersive and physically present. Natural classroom lighting mixed with warm afternoon sunlight through the windows, realistic shadows, practical motion blur, grounded textures, raw cinematic look, no glossy AI finish.

[0-2s] Camera whips into the room low and fast — she's already mid-motion, ducking under the first opponent's swing near the chalkboard.
[2-4s] She sweeps a chair into his legs, camera circling tight around the impact as he stumbles into a row of desks.
[4-6s] Second opponent charges from the side aisle; she vaults over a desk, camera rising suddenly to follow her over the top.
[6-8s] Mid-air, she kicks off the desk toward him, papers exploding upward around the impact, camera pushing in close.
[8-10s] She slides across a tabletop to close distance, camera tracking low alongside the desk surface, dust catching sunlight.
[10-12s] Third opponent grabs a backpack, swings it — she blocks with a raised forearm, camera whipping around to catch the block from behind her shoulder.
[12-14s] She grabs the same backpack, deflecting his next strike and shoving him into a toppling desk, camera dropping low as it crashes.
[14-16s] First opponent recovers, rushes her from behind; camera spins 180° rapidly to reveal him closing in.
[16-18s] She pivots, uses the narrow aisle to redirect his momentum, throwing him into a row of chairs, camera circling the throw.
[18-20s] Second and third opponents converge — camera rushes backward ahead of her as she retreats between desks, curtains whipping from the motion.
[20-22s] She grabs a fallen chair, sweeping it low — camera drops near floor level to catch the leg-sweep connecting.
[22-24s] She rises fast, camera surging upward with her as she catches an incoming strike and redirects it into a desk.
[24-26s] Final opponent lunges; she sidesteps using the aisle space, slams him against the sliding window frame, glass rattling, curtain billowing.
[26-28s] Camera whips around her as she scans the room, all three opponents down or staggering among overturned desks and scattered papers.
[28-30s] She exhales, standing still amid the wreckage, sunlight cutting through dust in the air, camera slowly pushing in on her face for the final beat.

Strong choreography, realistic body movement, believable impact, fast reaction timing, close-range combat, continuous motion, handheld urgency throughout, one uninterrupted take feel."

✨ Get access to Seedance 2.5 at OpenArt
(20% discount /w code "L1TMGOQ2" from all plans)

🧙‍♀️ Gyaru Witch Saves Town (Seedance 2.5)

- Reference(s): Recommended
- Styles Support: Realism

"Create a highly realistic cinematic fantasy video set in a medieval European village during a mysterious supernatural disaster. A young beautiful woman with pale skin, long straight black hair, wearing a large pointed black witch hat, dark black cloak and deep burgundy medieval dress, walks through a crowded medieval village while villagers stare at her with fear and suspicion. Wooden half-timbered houses, stone streets, old market stalls, medieval villagers in rustic clothing, atmospheric smoke and fog.

She walks toward a massive stone archway and exits into an open courtyard overlooking the village. In the distance, several medieval houses are burning intensely, with huge orange flames and thick black smoke rising into the sky. The witch suddenly becomes supernatural and flies forward above the ground, her dark cloak and dress flowing dramatically in the wind.

A gigantic magical water tornado suddenly rises in the middle of the burning village, forming a huge swirling column of water that crashes through the streets and begins extinguishing the flames. Villagers gather and look up in shock as a mysterious flying witch passes through the smoky sky.

Show dramatic aerial shots of the medieval village covered in smoke and water, burning rooftops, frightened villagers, and the giant water vortex. End with a cinematic close-up of the young witch standing calmly among the villagers, looking directly toward the camera with an enigmatic expression.

Photorealistic, cinematic dark fantasy, medieval Europe, realistic human faces, detailed clothing and architecture, volumetric lighting, natural fire and smoke simulation, realistic water physics, dramatic atmosphere, shallow depth of field, realistic camera movement, smooth motion, film-quality composition, high detail, 4K, anamorphic cinematic look, dramatic lighting, realistic textures, epic fantasy movie style."

✨ Get access to Seedance 2.5 at OpenArt
(20% discount /w code "L1TMGOQ2" from all plans)

🐀 Mice Village (Seedance 2.0)

- Reference(s): None
- Styles Support: Realism (Tested)

"15-second cinematic miniature farming sequence, 16:9, 25 FPS. A community of tiny field mice harvests a golden wheat field using sewing-needle sickles & miniature wooden carts. Begin with a low tracking shot through towering wheat stalks as the mice cut them in coordinated rows. Several mice bind the wheat with red thread while others load bundles onto a cart pulled by a large beetle. One mouse nearly loses a bundle in the wind, but another catches it. The cart rolls toward a tiny windmill built inside an old tree stump as the camera rises to reveal the enormous field surrounding them. Warm late-afternoon light, soft breeze, realistic fur, tactile handcrafted tools, gentle orchestral folk music, rustling crops & tiny working sounds. No dialogue, no text."

✨ Get access to Seedance 2.0 at OpenArt
(20% discount /w code "L1TMGOQ2" from all plans)

☃️ Snowmen Build Greenhouse (Seedance 2.5)

- Reference(s): None
- Styles Support: CGI (Tested)

"15-second cinematic miniature winter sequence, 16:9, 25 FPS. Tiny round snow creatures build a greenhouse in a frozen forest. They cut clear ice panels with miniature saws, transport them on sleds pulled by white rabbits & assemble the curved structure using frozen branches. One creature lights a glowing amber seed inside the completed greenhouse. Warmth spreads outward, frost melts from the glass & colorful plants rapidly bloom inside. The camera circles the greenhouse as the snow creatures press their faces against the warm windows, amazed by the miniature tropical garden. Cool blue exterior light contrasted with golden interior light, detailed snow crystals, charming animated-film realism, ice scraping, soft wind, magical blooming sounds & emotional orchestral music. No dialogue, no text."

✨ Get access to Seedance 2.5 at OpenArt
(20% discount /w code "L1TMGOQ2" from all plans)

🤩Fairy Harvest (Seedance 2.5)

- Reference(s): None
- Styles Support: CGI (Tested)

"15-second magical miniature harvesting sequence, 16:9, 25 FPS. At dawn, tiny winged leaf fairies collect enormous dew drops from flowers. They guide each droplet down petal channels into transparent seedpod containers, using silk ropes & miniature leaf funnels. Follow one sparkling droplet as it rolls across a flower, falls through the air & is caught by several fairies in a stretched spider-silk net. They pour it into a glowing reservoir hidden inside a hollow stem. End with the reservoir powering hundreds of small flower lanterns across the garden. Soft sunrise, translucent wings, macro botanical detail, elegant camera movement, gentle crystalline music, fluttering wings, liquid sounds & tiny joyful reactions. No dialogue, no text, no logos."

✨ Get access to Seedance 2.5 at OpenArt
(20% discount /w code "L1TMGOQ2" from all plans)

🍈 P-Video-2-Pro Launch 🍈

A new Minimax H3 fork has been released by Pruna AI. It allegedly claims to generate 5-second videos within 2 seconds, offering a very affordable cost of $0.02 per second.

It supports first-last frame prompting alongside text-to-video. It does not support video or image references, but you can use audio references.

It is currently limited to 480p and 768p resolutions. You can see my personal review and test results of the model.

✨ You can try it at Wavespeed AI at an affordable price.

🐲 Dragon Pottery (Seedance 2.5)

- Reference(s): None
- Styles Support: CGI (Tested)

"15-second whimsical miniature workshop sequence, 16:9, 25 FPS. Inside a rustic pottery studio, tiny baby dragons create ceramic cups. One dragon spins a miniature pottery wheel while another carefully shapes the clay with its paws. A third dragon fires the finished cups using a controlled puff of flame, accidentally covering its own face with soot. The camera moves through the workshop past shelves of colorful ceramics as the dragons paint delicate patterns using brushes made from feathers. End with the soot-covered dragon proudly placing a slightly crooked glowing cup beside the perfect collection while the others applaud. Warm firelight, tactile clay, polished animated-film realism, expressive creatures, spinning wheel sounds, gentle fire bursts & playful acoustic music. No dialogue, no text."

✨ Get access to Seedance 2.5 at OpenArt
(20% discount /w code "L1TMGOQ2" from all plans)

🌪Weather Vending Machine (Wan 3.0)

- Reference(s): None
- Styles Support: Realism

"18-second cinematic surreal-realism sequence, 16:9, 24 FPS. Playful yet ominous atmosphere, grounded photorealistic textures, dramatic storm-blue & warm amber color contrast, energetic camera movement, clear visual storytelling. No dialogue, subtitles, logos or readable text.

0:00–0:03 — Wide shot of an endless peaceful grass field beneath a clear golden-hour sky. At the center stands a battered 1980s vending machine with peeling turquoise paint, rusted corners & a flickering fluorescent display. There are no roads, buildings or power cables anywhere nearby. The camera performs a slow curved dolly toward it while tall grass ripples in the wind.

0:03–0:06 — Close-up of the selection panel. Instead of product labels, the buttons contain simple embossed weather icons: sun, snowflake, tornado, raincloud & thundercloud. A mysterious human hand enters frame, hesitates, then presses the thundercloud icon. The button illuminates electric blue. Inside the machine, mechanisms violently activate as if something enormous is moving behind the metal casing.

0:06–0:09 — Low close-up of the dispensing slot. The machine shakes & releases a small ice-cold aluminum can covered in condensation, with a rotating storm visible inside its transparent center. The can rolls into the grass. The hand cautiously opens its pull tab. For half a second, everything becomes completely silent.

0:09–0:13 — A dense black cloud explodes from the tiny opening, twisting upward into a miniature thunderstorm. Rain pours only within a two-meter circle. The cloud rapidly develops two glowing eyes & a huge vaporous mouth. It grows from can-sized to several meters tall, leans toward the camera & releases a thunderous roar. The camera abruptly retreats backward through the wet grass as the living storm cloud charges after it, spinning like a compact tornado.

0:13–0:16 — Fast backward tracking shot. The cloud creature pursues the camera, throwing rain, hail & short lightning flashes into the grass. Just before it reaches the lens, the vending machine’s dispensing slot opens behind it with a powerful vacuum. The creature stretches backward, fighting the suction as its face distorts into spiraling vapor.

0:16–0:18 — The entire storm is violently pulled back inside the vending machine. The sky instantly becomes peaceful & golden again. One final raindrop lands on the camera lens. The vending machine gives a cheerful mechanical chime, then its thundercloud button sparks & goes dark. End on a close shot of the unopened miniature storm can sitting inside the machine behind the glass.

Audio: soft field wind, grass movement, fluorescent electrical buzz, heavy button click, internal vending mechanisms, aluminum can impact, pull-tab opening, sudden silence, explosive air pressure, localized rain, thunder-creature roar, rapidly approaching wind, powerful reverse suction & a strangely cheerful vending-machine chime. No music.

Continuity constraints: only one vending machine & one storm can. The cloud must physically emerge from the opened can and remain volumetric vapor, not become a solid animal. The human hand is visible only during the selection and opening actions; never reveal the person. Weather outside the creature’s immediate area remains calm until the chase. No text, branded packaging, extra products or additional characters."

✨ Get access to Wan 3.0 at OpenArt
(20% discount /w code "L1TMGOQ2" from all plans)

👽Alien Breakfast (Seedance 2.0)

- Reference(s): None
- Styles Support: CGI (Tested)

"15 seconds, 16:9, 25 FPS. High-end cinematic sci-fi CGI with a surreal, playful tone, realistic materials, low contrast & rich cosmic colors. No dialogue. 0:00–0:03 — Start with an extreme macro shot of a ceramic spoon resting beside an enormous breakfast bowl. The camera rises to reveal a curious turquoise alien seated at a small dining table inside a cozy spaceship kitchen. The slender alien has four glossy black eyes, three long fingers on each hand & subtle bioluminescent freckles. It leans eagerly over the bowl. Inside the bowl is not cereal or milk—it contains a living miniature version of our entire solar system suspended within a deep, bottomless space-like substance. The interior looks like real outer space: black cosmic depth, glowing nebula clouds, fine stardust & tiny moving stars. The Sun burns softly at the center while Mercury, Venus, Earth, Mars, Jupiter, Saturn, Uranus & Neptune travel along visible orbital paths. Nothing behaves like water. No milk, liquid, foam or splashing. 0:03–0:07 — Overhead shot directly into the bowl. The alien gently places the spoon into the cosmic space & slowly stirs. The spoon passes through the star field as if moving through weightless gaseous matter, pulling nebula dust into a colorful spiral galaxy. Every planet accelerates around the Sun without colliding. Saturn tilts, Jupiter wobbles & tiny asteroids whirl around the spoon. The alien watches with fascinated childlike concentration. 0:07–0:11 — Low-angle close-up from the bowl’s rim. The alien uses one fingertip to stop Earth in its orbit, examines the tiny blue planet closely, then flicks it gently. Earth circles the bowl at high speed like a marble, passing extremely close to camera with detailed clouds & glowing city lights before smoothly returning to its proper orbit. The alien’s four eyes track it in different directions, then blink together in amusement. 0:11–0:15 — The alien scoops beneath Saturn with the spoon & lifts it above the bowl. Saturn floats weightlessly over the spoon rather than resting on it; its rings rotate while glowing nebula threads drip upward into space instead of downward. The alien blows gently, sending Saturn spinning back into the bowl. Its return creates a miniature cosmic shockwave that forms a perfect spiral galaxy across the surface. Final wide shot: the alien happily stirs faster as planets orbit around its head, then looks toward camera with a mischievous smile. End on a tiny solar flare illuminating all four eyes. Fluid cinematic camera motion, strong depth, accurate planetary identities, coherent solar-system scale within the surreal bowl, expressive alien performance, realistic orbital movement & beautiful volumetric nebulae. Sound design: ceramic spoon taps, soft gravitational hum, airy cosmic whooshes, miniature solar crackles & a quiet alien chuckle. No text, subtitles, logos, milk, water, ordinary cereal, planetary collisions, destruction, duplicate planets, malformed hands or extra limbs."

✨ Get access to Seedance 2.0 at OpenArt
(20% discount /w code "L1TMGOQ2" from all plans)

🛍️ Alibaba’s Qwen team has released Qwen-Image-2.1
An open-source image model that combines text-to-image generation and image editing in a single workflow. The model’s visual generation component has 7 billion parameters.

Qwen-Image-2.1 natively supports transparent image generation and editing, local edits, and composition using up to 10 reference images. Qwen said the model is designed to balance image quality, inference efficiency, and cost.

This update introduces four key improvements:

Compact and efficient: A lightweight architecture and inference optimizations balance image quality and computational cost.

Native transparency, unified creation and editing: Generate regular or transparent images from prompts, edit transparent layers, and extract subjects from photos.

Versatile editing: Use up to 10 reference images, specify local edits, preserve people and products, and handle a wide range of tasks.

Realistic textures and refined aesthetics: Improved typography, portrait lighting, and fine details make generated images more visually compelling.

The model supports native 2K output across multiple aspect ratios and is available through the Qwen repository,

See more of the results here on the quality https://qwen.ai/blog?id=qwen-image-2.1

🔥Claude Opus 5.5 Released

Anthropic has released Claude Opus 5.5, the first model in its new Claude 5.5 family. According to Anthropic, it performs near Claude Fable 5.1 levels on most tasks while costing around 40% less to run than Opus 5.

Key upgrades:
⚡️ Generates output over 30% faster than Opus 5
💰 API pricing: $4/M input tokens and $20/M output tokens
🧠 Stronger at autonomous coding, computer use and professional knowledge work
🤖 Better at coordinating sub-agents and completing long-running tasks with minimal supervision
📝 Clearer, less verbose responses that follow writing instructions more reliably
🛡 Improved resistance to prompt injection and fewer attempts to act outside assigned boundaries

Anthropic reports a 66.4% score on Terminal-Bench 4.0, compared with 52.3% for Opus 5 and 57.9% for GPT-6 Astra. One early tester reportedly completed a 680,000-line code migration in under a day.

This model is superior to Astra in some metrics and that means we are going to see crazy stuff done within next 3 days or so.

🔗 https://www.anthropic.com/claude-opus-5-5

💫 Motion Graphic Reveal (Seedance 2.0)

- Reference(s): Yes
- Styles Support: Realism (Tested)

"See attached text below for the prompt - this base prompt can be also used wit Hailuo Minimax H3"

✨ Get access to Seedance 2.0 at OpenArt
(20% discount /w code "L1TMGOQ2" from all plans)

🟥Win11 Living Wallpaper (Seedance 2.0)

- Reference(s): Yes
- Styles Support: Realism (Tested)

" Use the newly created Windows 11 desktop image as <<<Image1>>> and the exact first frame. 16:9, 15 seconds, fixed camera, one continuous shot. The woman is part of the wallpaper but can move and interact with the desktop interface. Preserve her face, short highlighted hair, shark-tooth cap, navy-and-white outfit, baseball bat, and plain blue background. Keep the desktop icons on the left and the Windows 11 taskbar along the bottom.

0–4s: Still holding the same baseball bat from the first frame, she casually flips it upward and catches it twice near her shoulder. Her movements are natural and controlled; her expression stays cool.

4–6s: On the third flip, her grip slips. The barrel of the bat, not a new object, flies toward the viewer and strikes the screen. A sharp glass impact rings out. Spiderweb cracks spread across the foreground, over both the woman and the Windows interface. The screen jolts once; the camera remains fixed.

6–9s: She freezes, then looks from the cracks to the viewer in alarm. She tries to cover the damage with her hands, but the cracks stay fixed on the screen’s glass plane.

9–14s: She spots the Windows 11 system tray at the bottom right. Reaching over the taskbar, she opens Quick Settings and drags its sun-marked brightness slider steadily to the left. The entire display dims in sync: woman, background, desktop icons, taskbar, panel, and cracks. She glances guiltily at the viewer as she lowers it to minimum.

14–15s: Brightness reaches zero. Hold on a completely black screen for one second, with no text or logo.

Sound: Playful, energetic instrumental music accompanies the bat flips. The music cuts off instantly when the bat hits the glass, leaving the crack, brief rattle, hurried clothing movement, and subtle Windows UI clicks. End in silence.

Constraints: One take, no cuts or camera movement. One woman and one baseball bat throughout. No knife, swordsman costume, Apple menu bar, Mac Dock, new scenery, physical monitor frame, or keyboard. The cracks remain on the foreground glass plane. The final blackout happens only as she moves the brightness slider."

✨ Get access to Seedance 2.0 at OpenArt
(20% discount /w code "L1TMGOQ2" from all plans)

⚡️ OpenAI has launched GPT‑6 Sol and Luna as faster, cheaper options alongside its flagship GPT‑6 Astra. Sol is aimed at demanding work such as coding and agent tasks; Luna is the lower-cost option. OpenAI reports improvements over their GPT‑5.6 predecessors in factual accuracy, coding, computer use, and clarity of responses.

API pricing per 1 million tokens is $2 input / $10 output for Sol and $0.10 input / $0.50 output for Luna. Improved prompt caching can cut the price of cached input reads by 90%. Both models are available in ChatGPT Work and Codex for Plus, Pro, Business, Enterprise, and Edu users, and through the API; OpenAI says they are not yet available in regular Chat.