重启web3

[重启web3 @pwxsr3]

AI微短剧《BNB-4：觉醒》决战光明顶正式参赛。
从剧本到画面，从情绪到节奏，每一处细节都为社区而做。不是一个人创作，是我们共同的信仰与热爱。
为讲好属于我们的故事。社区是光，我们便是追光者。
@heyibinance 一姐@cz_binance CZ请审阅希望你能看到这份来自社区的用心与热爱。#币安AI短剧比赛

[Zayan @HustleXR]

Made with seedance 2.5

Prompt ⬇️

0:00–0:05: Lightning-Fast Entry & Airflow Evasion

Visual Details: The camera follows the female protagonist sprinting at full speed from behind. The massive greatsword of the Red-Faced Heavenly King sweeps horizontally from the right, its enormous blade covering half the sky.

Stylish Action: Instead of simply dodging, the woman performs a sideways ground-level slide while running at high speed. Friction between her body and the ground sends sparks flying. The sword edge passes dangerously close to her baseball bat with a deafening whoosh.

Attack: The instant the slide ends, she uses her momentum, plants one hand on the ground, spins up to her feet, and swings the baseball bat in a wide arc. She strikes the side of the passing sword with tremendous force, producing a crisp wood-against-steel impact, then uses the recoil to accelerate toward the left.

0:05–0:10: Midair Footwork & Precise Strike

Visual Details: The Green-Faced Heavenly King leans forward and drives his spear into the ground like a power drill.

Stylish Action: Instead of retreating, the woman advances. She runs vertically upward, taking three steps along the shaft of the spear embedded in the ground.

Attack: At the highest point, she flips through the air with a 360-degree rotation, grips the baseball bat with both hands, and puts her entire body weight into the strike.

Slow-Motion Impact: The baseball bat precisely strikes the Green-Faced Heavenly King's shin joint. The painted surface cracks apart, sending wood fragments and glowing “wood-spirit” particles bursting outward in a Black Myth-style visual effect.

0:10–0:18: Extreme Space & Elegant Spinning Evasion

Visual Details: The heavy weapons of the Blue-Faced and Black-Faced Heavenly Kings—a halberd and a vajra—close in from opposite directions, crossing over each other and trapping her in a narrow space.

Stylish Action: The woman demonstrates incredible agility within the tiny gap between the weapons, performing two rapid side flips followed by a backflip.

Attack: The instant she lands from the backflip, she thrusts the baseball bat forward like a short spear strike, using the end of the bat to precisely hit the descending vajra of the Black-Faced Heavenly King.

Using the impact for momentum, she slides backward several meters, leaving two deep, elegant grooves across the stone floor.

0:18–0:25: Combo Destruction & Execution Moment

Visual Details: The attack focuses on the already-damaged leg of the Green-Faced Heavenly King.

Stylish Action: The woman enters a high-speed movement state, becoming a blur as she circles around the giant's enormous pillar-like leg.

Attack Combo:

First Strike: She swings the bat directly into the damaged crack, knocking off a large chunk of wood.

Second Strike: She spins the bat once in her hand, switches to a reverse grip, and strikes the exact same point again.

Third Strike: She leaps high into the air, braces one knee against the statue's leg for leverage, then delivers a devastating downward strike.

Close-Up: In slow motion, the baseball bat is shown embedded deep inside the wood. Green and purple mineral pigments scatter through the air like snow as a chain reaction of fractures tears through the entire giant leg from the inside.

0:25–0:30: Devastating Finale & Iconic Ending

Visual Details: The 20-meter-tall Green-Faced Heavenly King begins to tilt and collapse.

Stylish Action: As the giant statue's fall creates violent tremors and powerful shockwaves, the woman keeps running forward without looking back. She parkours across the collapsing environment, pushes off a flying stone brick, and leaps into a safe area.

Ending Action: Behind her, the enormous wooden body crashes into the ground, creating a massive cloud of dust and destruction. After landing, the woman elegantly spins the baseball bat in her hand, resembling the final motion of sheathing a samurai sword, then casually rests the bat over her shoulder

[Glitter Gal @GlitterPixely]

Seedance 2.5 first test with Candy and Sakura. Their weapons got swapped, lol 😅

Motion seems cleaner and smoother. It is about to ruffle some feathers again!

[TechHalla @techhalla]

Seedance 2.5 frozen time + rewind effect prompt is below 👇

Photorealistic cinematic 1950s American diner, chrome stools, red vinyl, neon glow and checkerboard floor, shot with modern lived-in realism and soft natural window light. Subtle handheld texture, warm practicals, rich period detail, heavy film grain.

0-4s: [Medium Wide] A striking young woman in her early 20s sits alone at the counter, calm and slightly amused, slowly sipping a tall thick milkshake through a straw. Behind her a young waitress in classic uniform approaches with a tray of eggs and bacon in one hand and a full glass coffee pot in the other. An older lady starts rising from a nearby booth.

4-8s: [Dynamic Tracking] The older lady collides hard into the waitress. Tray, plate, eggs, bacon and coffee pot explode upward in chaotic slow motion. Coffee erupts into long liquid ribbons and perfect suspended droplets. Camera immediately begins a smooth continuous orbit around the impact. Time locks completely at the peak of the spill. Every face freezes in pure shock. Only the girl at the counter keeps moving, completely unfazed.

8-17s: [Slow 360° Orbital] Camera glides in a full elegant orbit through the frozen diner. Coffee hangs in mid-air as glassy ribbons and spheres with perfect volume and surface tension. Bacon strips, eggs and the spinning tray float weightlessly. Patrons and waitress remain locked in startled expressions. The girl at the counter takes one slow, deliberate sip, eyes half-lidded, almost bored, while the entire frozen world (except her) begins an elegant reverse: every droplet, every piece of food and every person rewinds smoothly back to the exact starting positions.

17-24s: [Medium Shot] Rewind lands perfectly. Waitress stands balanced again with tray and coffee pot. The girl lifts her eyes, raises two fingers in a small casual gesture and softly calls the waitress by name. The waitress turns toward her just before the older lady begins to stand, completely avoiding the collision. A tiny private smile crosses the girl’s face.

24-30s: [Extreme Close-Up] Hard cut to her face as she takes one last slow sip. Soft knowing smile, eyes almost closed in quiet satisfaction, like she has done this a hundred times. Shallow depth of field, creamy bokeh of the neon diner behind her.

Photorealistic, ultra-detailed fluid physics, perfect motion blur only on moving elements, stable characters, cinematic lighting, heavy natural film grain, no artifacts, movie-level temporal coherence, high rewatch value.

30 seconds long is the new AI standard! hope you like it 🫡

[WasifAI @doctorwasif]

Seednace 2.0 director mode on @capcutapp

Prompt:
**CAMERA:** Handheld DV 16mm camcorder, filmed entirely as Image 2's selfie/POV footage shaky, off-center, clumsy zooms, occasional partial framing. Camcorder itself never visible.

**SCENE:** Night at Gangneung Beach. Image 1 hugs Image 2 from the front, lifting him up, camera shot from his POV in her arms.

Image 1: "That confession earlier... real or not? Be honest."
Image 2: "Whyyy~~ Can't I joke~~?"

Image 1 suddenly sprints into the ocean, still carrying him.

Image 2: "Hey! Hey!! Don't!!!"

Camera shakes violently as they crash into the water video cuts out.

**LOOK:** Soft, blurry tape quality, subtle noise, bloomed highlights, muted low-contrast colors, natural skin tones, mild auto-exposure drift.

**AUDIO:** Nighttime waves, tape hiss, camcorder recording noise.

[LudovicCreator @LudovicCreator]

🎨 SEEDANCE 2 🎨

Prompt :

Pure first-person camera perspective, no visible drone, no cockpit, no aircraft visible. The camera flies at supersonic speed through an enormous desert canyon, hugging the terrain only inches above the rocks. Sonic booms echo through the cliffs while dust erupts behind every turn. The camera slices through impossibly narrow rock arches, skims over waterfalls, enters a dark canyon tunnel, then bursts back into daylight as multiple supersonic shockwaves ripple across the landscape. The final climb rockets vertically through thick clouds into the upper atmosphere with the Earth stretching across the horizon. Continuous one-take, authentic high-speed inertia, aggressive banking, cinematic motion blur, atmospheric distortion, volumetric dust, blockbuster Hollywood VFX, hyper-realistic.

Made in @dreamina_ai

#DreaminaCPP #DreaminaAI

[LudovicCreator @LudovicCreator]

🎨 SEEDANCE 2 🎨

Prompt :

First-person camera perspective only, no drone, no aircraft, no propellers, no visible vehicle. The camera launches through a volcanic cave, skimming above lava rivers, weaving between magma geysers, then diving into a gravity vortex at the crater’s core. Final reveal: the volcano opens into outer space, with molten rocks becoming newborn planets around a burning star. Continuous one-take, aggressive POV motion, Hollywood VFX, volumetric smoke, glowing particles, epic cinematic scale.

Made in @runwayml

[TSUBAKI @AI__TSUBAKI]

Seedance 2.0 on @SJinn_Agent

=======================

Prompt:

Style: 8K photorealistic — real phone-and-mirrorless vlog footage, no 3D render, no game engine, no anime.
Format: Modern K-pop idol YouTube behind-the-scenes vlog — handheld selfie energy, quick punchy cuts, whip-pans and snap-zooms between shots.
Lighting: Clean and flattering — vanity mirror bulb lights as key, soft white studio spill from the doorway, gentle bloom, K-beauty glow. High-key on the face, controlled elsewhere.
Color: Chic monochrome palette. 60:30:10 — soft warm gray / deep black wardrobe / soft pink accent pop.
Camera: Mix of front-facing phone selfie (slight wide-lens distortion, arm's-length) and handheld mirrorless. Natural micro-shake, quick reframes. 180-degree shutter motion blur.
Skin: Pore-level realism with dewy K-beauty finish — vellus hair, subtle blush flush, glossy lips, real catch-lights in the eyes.
Acting: Bubbly, natural idol-vlog energy — genuine smiles, playful micro-expressions, eye-contact with the lens, tiny laughs, chest rise from breathing. Never posed-frozen, always alive.
Physics: Gravity and inertia respected — long hair bounce and sway, pleated skirt movement, correct contact shadows. No floating props.
Composition: Centered selfie framing and rule-of-thirds handheld. Subject moving from frame one.
Continuity: Same idol RENA, same outfit, same makeup, same waiting room across every cut. No identity drift.
Technical: 24fps smooth motion, snappy vlog-paced editing, 8K detail, no jitter.
Audio: Upbeat cheerful room tone. RENA speaks short natural Korean one-liners as written in each cut — bright, youthful female voice, casual vlog delivery, accurate lip-sync. Light, bouncy vlog energy.

Characters:
RENA — 20 year old K-pop idol, 166cm, slim 7-head proportions. Adorable cute-type visual: soft round face with full cheeks, big round sparkling dark brown eyes with aegyo-sal, small nose, dewy glass skin, coral-pink gradient lips, tiny beauty mark on her left cheek. Very long straight black hair past her chest, center-parted with thin face-framing strands. Pearl-and-silver drop earrings in both ears. Outfit: black ribbed knit top with an oversized pleated collar and a black ribbon tie, white shirt collar peeking at the neckline, black micro pleated skirt with a side belt buckle, black crew socks, chunky black platform loafers.

Scene:
An idol waiting room at an MV shooting studio, daytime. A vanity mirror ringed with warm bulb lights sits camera-left; a rolling clothing rack of garment bags stands behind, a gray couch with her phone and a small pink standing fan camera-right. The door to the bright studio hallway is upstage. RENA is alone, fully in hair and makeup, killing time before her set call — filming a behind-the-scenes vlog on her phone. Fast, cheerful, handheld throughout.

CUT 1 (~2s) — Front-facing phone selfie, arm's length, slight wide-lens distortion:
RENA pops in close to the lens with a bright grin and a quick finger-heart — long black hair swinging in, eyes sparkling in the bulb light.
She says brightly: "하이 여러분~!" (Hi everyone~!)

CUT 2 (~2s) — Fast whip-pan across the waiting room, handheld POV:
Her hand flips the phone around — a whip across the bulb-lit vanity mirror, the rolling clothing rack of garment bags, the gray couch with the small pink standing fan. Whips back just as her face re-enters frame.
Her voice off-camera, playful: "여기는 대기실!" (This is the waiting room!)

CUT 3 (~2s) — Snap-zoom to the vanity mirror reflection, handheld:
She leans into the bulb-lit mirror, fixes one face-framing strand with two fingers, presses her coral lips together with a tiny satisfied nod.
She whispers to her reflection with a smile: "예쁘죠?" (Pretty, right?)

CUT 4 (~1.5s) — Macro insert, tight close-up, shallow focus:
Detail shot: her fingers straighten the black ribbon tie at the pleated collar, pearl-and-silver earring swaying in bokeh bulb light, white shirt collar crisp at the neckline. No dialogue — only soft fabric rustle.

CUT 5 (~2s) — Medium handheld, phone tracking her, center of the room:
She does one quick playful spin to show the MV outfit — micro pleated skirt flaring, long black hair fanning out — landing square to the lens with both hands framing her face.
She sings out as she lands: "짜잔~!" (Ta-da~!)

CUT 6 (~2s) — Snappy cut, handheld close on the couch:
She drops onto the gray couch, grabs a bottle of banana milk from the side table and sips through the straw, cheeks puffing slightly, eyebrows bouncing.
A happy little hum through the straw, then: "음~ 맛있어!" (Mmm~ so good!)

CUT 7 (~1.5s) — Quick punch-in, tight selfie from the couch:
She holds the banana milk bottle up beside her face like a commercial, taps it twice with one finger, flashes a cheeky closed-lip grin at the lens.
She says in a mock-CF voice: "이거 최고." (This one's the best.)

CUT 8 (~2s) — Arm's-length selfie sign-off:
A staff knock sounds off-screen — her eyes go wide with excitement. A fast wave, a big wink with a double finger-heart, and she springs up out of frame — camera holds on the bulb-lit mirror for a half-beat.
She calls out as she jumps up: "가자! 안녕~!" (Let's go! Bye~!)

[John @johnAGI168]

密室大闯关，微缩小人特效片（Miniature Tiny-Person FX）🎬

以后有趣好玩的视频都有可能是模板化的，设定好后，上传自己的图片，就能生成同款视频。

复制下面的提示词，上传自己的图片，也能生成同款视频。

prompt 👇

【风格】微缩小人特效片（Miniature Tiny-Person FX），真实摄影（Photorealistic），微距景深（Macro Depth of Field），日光浴室白净色调，8K超清，竖屏9:16，抖音爆款质感

【时长】12秒

【场景】现代家庭浴室，白色洗手台、银色花洒与水龙头、蓝色晾衣架、化妆品瓶阵、绿色鳄鱼咬手玩具、装满蓝色泡泡水的浴缸；主角为巴掌大的迷你人，与所有物件保持约1:15微缩比例

【角色】主角（迷你小人形态）

[00:00-00:02] 镜头1：花洒起跳+衣架云梯（Low-angle + Swing）

仰拍：迷你主角站在正在喷水的巨大银色花洒顶上，纵身跃起抓住上方不锈钢毛巾架横杆，随即像玩云梯（Monkey Bars）一样顺着挂在杆上的一排蓝色衣架逐个摆荡前进，衣架随摆动轻晃。

音效：水帘哗哗声+金属衣架碰撞声。

[00:02-00:04] 镜头2：落台跳瓶阵（Counter Parkour）

主角松手落到白色洗手台面，屈膝缓冲起身冲刺，在比人还高的化妆品瓶阵间连续跳跃：跃过棕色玻璃瓶、踩上乳白色皂液瓶顶、再跳向银色水龙头方向，落地翻滚。

微距镜头横向跟拍，背景虚化。

音效：连续脚步声+瓶身轻响。

[00:04-00:06] 镜头3：鱼跃入鳄口（Superman Dive）

主角沿台面全速冲刺，经过横放的肥皂块后朝台面尽头鱼跃飞扑，身体水平腾空，飞进一只绿色鳄鱼咬手玩具张开的血盆大口，稳稳落在红色舌头上。

侧面慢动作（Slow-mo）捕捉腾空瞬间。

音效：风声+落在塑料舌头上的闷响。

[00:06-00:08] 镜头4：鳄口狂奔（Mouth Tunnel Run）

镜头从鳄鱼嘴内向外拍：主角沿红色塑料舌头狂奔，两排白色大牙像隧道柱子在两侧掠过，鳄鱼嘴微微合拢制造紧迫感，他在嘴闭合前纵身跃出。

音效：急促脚步声+塑料咬合"咔哒"声。

[00:08-00:10] 镜头5：浴缸泳渡+骑鸭（Swim + Duck Ride）

主角一头扎进装满蓝色泡泡水的浴缸溅起水花，自由泳游向一只黄色橡皮鸭，抓住鸭背翻身骑上去，橡皮鸭在水面晃动下沉又回弹。

水面高度微距镜头跟拍。

音效：入水声+划水声+橡皮鸭"吱"声。

[00:10-00:12] 镜头6：登顶龙头+胜利定格（Faucet Summit Finale）

主角踩着鸭背借力起跳跃回台面边缘，徒手攀上银色水龙头，站上龙头顶端叉腰而立，龙头哗哗出水。

金色大字"闯关成功"带闪光粒子特效在画面上方弹出，主角挺胸抬头定格收尾。

音效：攀爬声+胜利音效+水流声。

[Oogie @oggii_0]

Crafted with GPT image 2 + Seedance 2.0 on @SocialSight

Prompt: Ultra-realistic cinematic WWII battlefield, single continuous tracking shot, 15 seconds, no cuts. Use the attached first frame as strict visual reference for environment, lighting, atmosphere, and composition. Remove all guide overlays: no blue route line, no numbers, no start/end text, no markers.

Camera begins handheld behind a soldier's shoulder as he charges through muddy trenches in driving rain. Smoke, debris, and bullet impacts throw mud into the air. He weaves past destroyed equipment and dives behind Czech hedgehog barricades alongside allied soldiers. Camera rotates around him briefly — revealing the full battlefield scale: WWII fighter planes crossing storm clouds, smoke columns, tanks advancing, thousands of soldiers pushing toward a massive concrete fortress wall. Camera returns behind him as he moves forward.

He sprints toward the armored line. Tanks roll past on both sides, cannons firing with huge muzzle flashes and shockwaves. Enemy fire from the wall sends sparks and concrete fragments flying. He jumps onto a moving tank, runs across its muddy hull, ducks under fire, leaps off toward the fortress base. Camera follows dynamically with low-angle running shots, controlled explosion shake, cinematic motion blur.

At the wall base, camera tilts upward showing the fortress height. He fires a grappling hook, climbs the wall — boots scraping concrete, dust falling from bullet impacts, sparks around him. As he reaches the top, camera rises over his shoulder revealing a massive hidden military complex beyond: endless rows of tanks, armored vehicles, supply trucks, bunkers, searchlights, fires, smoke columns stretching to the horizon. Final frame pulls to a wide aerial shot showing the true scale of war.

Cold gray-blue color grading, volumetric smoke, wet mud, rain, practical explosions, film-grain texture. No modern weapons, no fantasy elements, no text overlays, no cartoon style.

[Laraib Fatima‎ @AiwithLariab]

To One-Click 4K Restoration Prompt
Bring blurry, faded, and damaged photos back with natural colors and stunning clarity.

GPT IMAGE 2 on CHAT GPT:

PROMPT:
Restore and enhance an old damaged photo. Remove scratches, stains, and noise. Reconstruct faded or torn areas while preserving original details. Slightly sharpen the image for better clarity, but keep it realistic. Apply natural and era-appropriate colors to skin, hair, and clothing. Use a soft, balanced background color without being too striking. The final result should look like an old photo that has been realistically restored and colorized, while respecting its original appearance.

[TechHalla @techhalla]

Two cinematic prompts for Seedance 2.0 right here 👇

[STYLE + CAMERA + ATMOSPHERE]
Ultra-photorealistic cinematic 15-second action sequence from a grounded action thriller film. Nighttime at an abandoned industrial train yard. Old trains, rusted tracks, broken platforms and warehouses. Strong moonlight and industrial lighting. The visual language is gritty and realistic with hyper-realistic practical destruction. Camera is handheld-dynamic with urgent moves.

[IMAGE REFERENCES]
No reference images provided. Generate a fully consistent lead character: a male fugitive in his mid-30s, short hair, intense expression. He wears a dark jacket, jeans and boots. Maintain exact same appearance and clothing throughout the clip.

[TIMELINE SECOND BY SECOND]
0-3s: [Dynamic handheld tracking shot from side-rear] The man runs across the train yard as a freight train derails violently after hitting a collapsed section of track. Massive train cars tip over and crash into the ground, sending metal, wood and cargo flying. The camera tracks him urgently as the destruction spreads.

3-7s: [Slow continuous orbiting camera moving around the frozen destruction] At the peak of the derailment, everything freezes in perfect realistic physics. Huge train cars, twisted metal, wooden debris and clouds of dust hang motionless in the air with accurate weight and trajectories. The camera performs a smooth, continuous orbit through the frozen chaos, moving between large suspended train cars and passing close to sharp metal fragments while the man remains visible.

7-15s: [Dynamic tracking shot as time resumes] At the 7-second mark time snaps back to forward motion with a slight realistic temporal residue. Some outer debris shows a very subtle reverse lag before continuing. The man has used the frozen moment to dive behind a concrete barrier. When motion resumes, several large pieces of metal miss him. He stays low and runs toward an open warehouse as debris finally crashes down. The camera tracks with him through the dust.

[STYLE & QUALITY BOOSTERS]
Photorealistic 8K, hyper-realistic rigid body destruction with correct material properties (metal, wood, train parts), perfect frozen mid-air physics, seamless transition from freeze to resume, natural dust interaction, heavy cinematic motion blur on fast debris, stable character performance, movie-level practical destruction VFX quality.

[MayorkingAI @MayorKingAI]

Seedance 2.0 Dark fantasy prompt

Made in @magnific

[liana @Lianaalane]

Created on seedance 2.0

Prompt:
A cinematic, atmospheric scene in a dimly lit, empty underground parking garage at night. A young East Asian woman with long dark hair, wearing an olive-green oversized jacket and cargo pants, walks slowly away from the camera down the center of a wide parking lane, holding a white plastic bag in her right hand. The environment is cool-toned with concrete pillars, fluorescent tube lights on the ceiling casting harsh shadows, and painted arrows on the glossy floor.
She approaches a parked dark green/teal luxury sedan on the right side. She stops beside the car, raises her arm, and hangs the white plastic bag on the side mirror or door handle. She then turns slightly toward the camera, leans against the car for a moment, pulls out her phone with both hands, and looks down at the screen with a focused, slightly uneasy expression.
Suddenly, a eerie supernatural moment: a translucent, ghostly pale female figure with long black hair and a white dress materializes in the background behind her. The woman looks up from her phone in shock as the ghost stands motionless, staring. Quick motion blur and dramatic tension as she reacts. Moody horror-thriller style, realistic lighting, subtle film grain, cool blue-cyan color grading, slow deliberate camera movement following her from behind then panning slightly to the side. 12-second duration, high detail, cinematic."
This prompt captures the full sequence from the provided video frames while being optimized for AI video tools. You can adjust details like aspect ratio (16:9), style (more horror, more realistic), or camera movement as needed.

[How To Prompt @HowToPrompt__]

China has killed the entire vector database industry.

They open-sourced TencentDB Agent Memory. It gives any AI agent long-term memory that runs 100% locally.

No Pinecone. No cloud APIs. No repeating yourself every session.

- 61% fewer tokens
- PersonaMem accuracy: 48% → 76%
- Zero external API dependencies
- Runs on plain SQLite

Most memory systems compress your history into an opaque vector pile. when recall goes wrong, you're guessing. this one doesn't compress, it builds a semantic pyramid.

L0 Conversation → L1 Atom → L2 Scenario → L3 Persona.

Short-term state gets encoded as a Mermaid graph in your agent's context. verbose tool logs get offloaded to disk. when the agent needs proof, it drills back via node_id to the exact raw log.

no lossy compression. every layer is readable markdown you can just open and inspect.

5.1k stars. 100% Open Source.

[Alexandra Aisling @AllaAisling]

Prompt Studio: Motorcycle Ice Racer with Seedance 2.0 in @runwayml

A dangerous motorcycle ice racer with frost-covered black racing gear, mirrored helmet visor, and glowing bike headlights cutting through snowstorms. Frozen arctic industrial wasteland during blue-hour twilight. Ice roads, abandoned oil rigs, frozen bridges, collapsing tunnels, snow-covered shipping containers, and blizzard visibility conditions. Dark cinematic techno with deep sub-bass pulses. Ice friction, engine roar, chain vibrations, snow impacts, and freezing wind dominate the soundscape. Ultra-realistic motorsport cinematography mixed with survival thriller aesthetics and premium winter advertising.
SHOT 1: Ultra-low front tire tracking shot carving through thick ice dust at dangerous speed.
SHOT 2: Whip pan into a near-crash drift around frozen industrial wreckage.
SHOT 3: Wide aerial shot showing the motorcycle racing across gigantic frozen ocean surfaces between abandoned structures.
SHOT 4: Long-lens jump shot over shattered ice sections while snow explodes behind the bike.
SHOT 5: Circular side tracking shot during a prolonged sideways drift inches from a cliff edge.
SHOT 6: Final impossible jump through a collapsing frozen tunnel during whiteout conditions. The rider lands violently, fishtails across black ice, then slowly stops beneath flickering industrial lights while snowstorm winds consume the frame. Music cuts instantly.

[Jokker @0xJokker]

ACABAN DE DARLE MEMORIA INFINITA A CLAUDE, CODEX Y CURSOR

100% GRATIS y open source

Se llama Memanto y ya tiene +1k estrellas en GitHub

Antes en cada sesion nueva tu agente olvidaba todo

Tenias que explicarle de nuevo el proyecto, las decisiones, los errores

Memanto lo resuelve de raiz

→ Guarda el contexto completo de tus sesiones de trabajo
→ Organiza y comprime la informacion utilizando IA
→ Recupera lo relevante en menos de 90ms
→ Funciona con claude code, cursor, codex, LangGraph, CrewAI y mas

Sin bases de datos vectoriales
Sin configuracion compleja
Solo un comando: pip install memanto

Tu agente ya recuerda donde lo dejaste

No mas perder tiempo explicando lo mismo cada dia

[探路AI @TanLuAI]

分享一个我维持东方人员一致性的小tips：
由于香蕉 image2 对于东方人物的人脸一致性的维持能力都比较弱（如图三）。 但又需要维持人物的一致性，我现在一般只生成人脸虚幻的全身三视图，或者左边的面部区域 直接让AI完全截图保留，右边人脸再做虚化处理。 把人脸一致性交给seedance 来处理。
提示词：
标准人设出图，人物全身的正侧背三视图，背景纯白，左侧近景胸像，右侧全身三视图：正视图、侧视图、背视图。完全真人写实风格。严格保持人物一致性，左侧的近景照直接截图即可

基于参考图，生成一张项羽的全身三视图（背景纯白，正视图、侧视图、背视图。完全真人写实风格。服装保持完全一致。参考图完全保持一致。人物面部完全虚化。保持人物一致性。不要出现武器

[Noor @noorlewisx]

Created with seedance 2.0

Prompt:

Cinematic 50-second vertical action trailer, 9:16 aspect ratio, ultra-realistic, dark dystopian cyberpunk city destroyed, heavy smoke, fire, flying debris, dramatic camera angles.

0-2s: A beautiful East Asian woman with long black hair in black crop top jacket and pants runs desperately toward camera on cracked highway, massive orange explosion and fireballs behind her, cars wrecked, dramatic low angle.

2-5s: She leaps powerfully into the air, hair and jacket flowing, background full of explosions and city chaos, dynamic side angle.

5-8s: Close-up of her legs and robotic knee pads glowing red as she runs fast through ruined streets, motion blur.

8-12s: She does acrobatic flips and jumps over wrecked yellow bus and cars, high energy action, epic wide shots.

12-15s: She lands in fighting stance, then full-body transformation into sleek black futuristic mech suit with glowing red neon lines, massive mechanical wings with red energy patterns unfold dramatically.

15-20s: Full armored winged mech suit with red glowing eyes and chest, powerful pose, wings spread wide, facing giant monstrous rock-like creature with red eyes.

20-25s: Intense fight sequence - mech suit flies, punches, kicks the giant monster, sparks and red energy effects, destroyed city background.

25-30s: Mech suit deploys red energy blades from wings, slashes and shoots powerful red energy beams at the monster, monster roars and attacks back.

30-35s: Brutal close combat inside ruined skyscraper floor, punches, throws, glass shattering, monster smashes walls.

35-40s: Epic finale - mech suit charges, kicks the giant monster through a huge glass window, monster flies out breaking glass, slow-motion debris.

40-48s: Mech suit stands victorious in front of broken window, wings fully spread with bright red glowing lines, dramatic back view overlooking destroyed cyberpunk city, smoke and fire everywhere, heroic pose.

48-50s: Screen fades to black, centered white bold text "DINDA PRASETYO" appears and stays for full 2 seconds, clean and powerful ending.

[ImPaul @impaulxyz]

Esto parece una escena de película real

"Frozen Time" brutal en plena explosión, cámara orbitando el caos y reanudación épica. Calidad de cine con Seedance 2.0

Te dejo el prompt completo abajo 👇

https://t.co/tRmVcMlNYI

[WasifAI @doctorwasif]

Seednace 2 mini on @openart_ai

Prompt
Seedance 2.0, 15 seconds, 16:9. Main subject from @ image1 — lock her completely. Face, skin tone, body, outfit, everything stays identical the whole way through. She's wearing a grey faded sleeveless crop top, loose high-waist light blue jeans, black canvas sneakers, black cord necklace, black wavy hair in a messy side-swept ponytail with bangs. Korean woman, early-2000s feel.

The whole thing is shot in a quiet Korean residential neighborhood — narrow concrete alleys, low-rise houses with small terraces, a front yard with a clothesline, potted plants, parked bicycles and motorcycles, big trees, and overhead cables everywhere. No shops, no vendors, nothing commercial. Just a real neighborhood.

Camera treatment is the whole point. This needs to look like someone's friend grabbed a DV camcorder and just started recording — no plan, no setup, no nothing. Heavy handheld shake, constant reframing, subject drifting toward the edges, autofocus hunting, lens breathing, exposure pumping. The image itself should look faded, low contrast, slightly washed out, with that digital noise and compression feel that early-2000s home video had. No stabilization. No modern grading. This aesthetic is non-negotiable.

She starts sitting on a concrete sidewalk fixing her ponytail, arms raised, genuine smile, wind catching her hair — camera barely holding focus. Then the camera follows her into a narrow alley where she crouches down and feeds a stray cat that comes right up to her. After that she's in her front yard hanging laundry on the clothesline, morning breeze moving everything, camera swaying and hunting. Mid-section she's on the front terrace with a coffee cup, just sitting quietly, looking out at the street — loose drifting shot from the side. Then a right-side close shot where she raises her arm, waves warmly toward someone off-frame and says "Annyeong" — camera catches it a beat late. Final shot is a slow tracking walk down the street, coffee cup in hand, she notices the lens, turns slightly and gives a real quiet smile — then the recording just cuts to black mid-motion like the camcorder got switched off.

Audio is strictly natural. Morning birds, light breeze, distant motorcycle sounds, faint neighborhood chatter, cat, coffee cup, footsteps on concrete, leaves. No music, no sound design, nothing added.