СПЕШУ АИ: Проводники в ИИ | ChatGPT, Claude, Gemini и ещё 300+ нейронок
3.1K subscribers
331 photos
196 videos
3 files
251 links
SpeShu.AI — платформа с мультидоступом к 300+ нейросетям

Открыть сайт 👉 https://speshu.ai
Download Telegram
Зарабатывайте на нейросетях вместе со SpeShu.AI

Приглашайте новых пользователей и получайте 30% от первого пополнения и 20% от всех последующих 🎁

Тема ИИ сверхпопулярна, поэтому привлечь аудиторию легко. Объёмы трафика огромные, средний чек у бизнес-клиентов достигает 100 000 рублей, а проценту конверсий вы сперва не поверите.

Если у вас есть аудитория, вы вебмастер, блогер, маркетолог, продюсер или хотите рассказать о CПЕШУ АИ всем знакомым и близким, становитесь партнёром SpeShu.AI.

Получите реферальную ссылку в личном кабинете после регистрации. Там же вы найдёте прозрачную статистику. На скриншоте — кабинет одного из наших партнёров.

За вами навсегда закрепляется реферал, который платит. Чтобы система не потеряла его, куки хранятся вечно.

Узнайте больше о партнёрской программе в отдельной статье. Если останутся вопросы, обязательно напишите менеджеру.

Становитесь партнёром SpeShu.AI, пока у тренда на нейросети такой потенциал 🔥
👍1
This media is not supported in your browser
VIEW IN TELEGRAM
Сэкономьте 1 МЛН рублей на кругосветке

Снимите видео на фоне 20 главных мировых достопримечательностей.

Загрузите своё фото в Seedance 2.0 на SpeShu.AI и прикрепите промпт:
Create a 10s hyper-lapse selfie-travel video of uploaded character. Strict identity consistency across all locations. 20 distinct tourist spots worldwide with hard cuts on every single beat. Handheld selfie-stick camera angle, wide-angle lens capturing the character's face, specific outfits, and iconic landmarks. High clarity, vibrant cinematic color grading.

LOCATIONS, OUTFITS & POSES (1-20):
1. Paris, Eiffel Tower | chic red beret, beige trench coat | smiling, classic hand wave
2. Tokyo, Shibuya Crossing | modern neon cyberpunk streetwear jacket | peace sign, playful wink
3. New York, Times Square | bright yellow oversized puffer jacket | wide-eyed excited grin
4. Rome, Colosseum | elegant white linen summer dress | thoughtful look, looking back at camera
5. Cairo, Pyramids | beige safari utility shirt, wide-brimmed sun hat | amazed expression, blocking the sun
6. Rio, Christ the Redeemer | vibrant tropical patterned Hawaiian shirt | joyful laugh, head tilted back
7. London, Big Ben | classic plaid wool blazer, emerald green scarf | subtle smirk, checking wrist watch
8. Sydney, Opera House | casual summer tank top, stylish sunglasses | sunny smile, looking at camera
9. Agra, Taj Mahal | elegant embroidered pastel tunic shawl | serene positive expression, hands in namaste
10. Beijing, Great Wall | traditional red hanfu-inspired modern jacket | triumphant fist-pump, determined look
11. Moscow, Red Square | heavy fur-trimmed winter coat, matching ushanka hat | cozy smile, breath visible in air
12. Istanbul, Hagia Sophia | elegant silk headscarf loosely draped over shoulders, modest blouse | warm welcoming smile
13. Venice, Canals | classic blue and white striped sailor top | charming smile, slight tilt of the head
14. Dubai, Burj Khalifa | luxurious metallic gold evening blazer | impressed grin, looking up in awe
15. Peru, Machu Picchu | colorful traditional Andean wool poncho | breathless happy smile, scenic background
16. Athens, Acropolis | white draped sleeveless Greek-style top | proud confident look, wind-blown hair
17. Berlin, Brandenburg Gate | edgy black leather motorcycle jacket | friendly nod, direct eye contact
18. Amsterdam, Windmills | casual denim jacket over a floral dress | relaxed content smile, gentle breeze
19. Barcelona, Sagrada Familia | artistic colorful patterned blouse | open-mouthed amazed look
20. Seoul, Gyeongbokgung Palace | elegant pastel pink and white hanbok dress | finger heart sign, final cute smile
This media is not supported in your browser
VIEW IN TELEGRAM
Блог из Лос-Анджелеса на 2 МЛН просмотров можно сделать одним промптом

1. Регистрируемся на SpeShu.AI
2. Активируем промокод TG15
3. Получаем 15% к пополнению и переходим к Seedance 2.0
4. Загружаем своё фото, дополнительно описываем свою внешность и прикрепляем промпт:
15-second high-energy California travel vlog starring an extremely beautiful playful sensual Japanese girl. Fast-paced multi-shot edit, trendy Gen-Z travel influencer aesthetic, cinematic handheld vlog energy, vibrant California sunlight, youthful chaotic fun, premium TikTok/Reels editing style.

IMPORTANT:
Keep her appearance and outfits consistent with the reference images:
• long black hair
• slim curvy body
• soft natural makeup
• playful bright smile
• youthful sensual energy

MAIN OUTFITS (consistent across scenes):
LOOK 1:
black triangle bikini top, oversized loose white button-up shirt worn open, light blue denim shorts, delicate necklace, casual California beach aesthetic

LOOK 2:
white cropped tank top, light gray high-waisted leggings, sporty influencer vibe

LOOK 3:
white strapless tube top with loose white sweatpants and black sunglasses

VIDEO STYLE:
• fast cuts every 1–2 seconds
• no slow motion
• energetic handheld camera
• realistic vlog movement
• natural hair physics and clothing movement
• authentic sunlight and shadows
• playful travel influencer behavior
• dynamic camera whip transitions
• high-vibes summer energy
• realistic environment physics
• subtle lens flares
• social-media luxury aesthetic

AUDIO:
Upbeat female-fronted indie rock song with driving drums and electric guitar. Ambient California city sounds underneath. Opening includes soft ASMR whisper close to microphone.

OPENING HOOK (0:00–0:02):
Extreme close-up selfie angle while walking on Hollywood Walk of Fame. She leans close to camera and whispers softly in ASMR:
“California with me today?”
She smiles mischievously and immediately pulls camera away into fast transition.

SHOT SEQUENCE:

0:02–0:04
Hollywood sign overlook. Wearing white crop top and gray leggings. Wind blowing through her hair naturally while she turns toward the camera smiling.

0:04–0:05
Fast rollercoaster POV shot. Wearing black bikini top and open white shirt. Laughing wildly as wind hits her face.

0:05–0:07
Disneyland castle background. She spins playfully while holding the edges of her oversized white shirt. Bright sunlight, energetic tourists around her.

0:07–0:09
Walking through Beverly Hills in denim shorts and fitted white crop top. Sunglasses on. Confident influencer walk. Quick hair flip toward camera.

0:09–0:11
Venice Beach palms and sand. She pauses, smiles at the ocean breeze, shirt flowing naturally in the wind.

0:11–0:13
Golden Gate Bridge overlook. Wearing sporty white crop top and gray leggings. Camera circles around her as she leans on railing looking at the water.

0:13–0:15
Santa Monica Pier at sunset. She walks toward camera laughing, grabs the camera playfully with one hand, then final fast whip-pan ending on palm-tree-lined California street.

COLOR & LOOK:
Golden California sunlight, vibrant blue skies, dreamy summer glow, cinematic travel vlog grading, social-media luxury aesthetic, realistic skin texture, natural body motion, energetic editing rhythm.

NEGATIVE:
No slow motion, no stiff movement, no duplicate people, no unrealistic physics, no floating hair, no uncanny facial animation, no anime style.
This media is not supported in your browser
VIEW IN TELEGRAM
Еле живые мыльцы стоят по 20 000 рублей из-за тренда на нулевые

Эстетика Y2K собирает по 1 МЛН просмотров в соцсетях.

Снимите сверхреалистичное видео со своим лицом на такую мыльцу бесплатно.

Инструкция в 3 шага👇
1️⃣ Сгенерируйте первый референс

Загрузите своё фото и в промпте, где квадратные скобки, опишите свою внешность или задайте короткую фразу: «the character you see in the photo».

A realistic close-up shot of a small digital camera screen glowing brightly in a dark indoor environment. Displayed on the LCD is a candid early-2010s style photograph of [...].

She wears a black spaghetti-strap top with a loose white cardigan hanging casually from both shoulders and faded blue jeans. Captured mid-laugh while turning her face slightly sideways, her expression feels spontaneous and natural, with hair falling softly across part of her cheek.

The harsh direct flash from the compact camera creates strong highlights on her face and cardigan while flattening shadows in the background, producing an authentic nostalgic digicam aesthetic. Slight motion blur and digital grain enhance the candid realism.

Camera UI overlays are visible across the LCD screen, including the timestamp “8. 1. 2012 3:15 AM,” exposure data “1/30 F3.4 ISO 100,” focus indicators, and a small green battery symbol in the corner.

The image preserves visible screen pixel structure, slight glare reflections, chromatic softness, and compressed digital texture. Outside the LCD, the surrounding darkness fades smoothly into blur, emphasizing the glowing nostalgic screen.

Shot to resemble an authentic Sony Cyber-shot point-and-shoot camera from the early 2010s using a CCD sensor with vintage digital rendering and imperfect flash exposure.
2️⃣ Сгенерируйте сториборд на основе референса

Прикрепите фото, которое получилось после первой генерации, и попросите ChatGPT сделать сториборд. Запрос стал частым в последний месяц, так что нейросеть поймёт даже на русском.
3️⃣ Загрузите сториборд в Seedance 2.0 и отправьте промпт для анимации

В промпте дополнительно пропишите MAIN CHARACTER под свою внешность. Если возникнут вопросы, вам поможет Claude. Благо, нейросеть располагается в соседнем окне и не требует подписки, если вы используете её через SpeShu.AI.

Use uploaded image @[character_ref] as the permanent character identity reference and uploaded image @[storyboard_ref] as the exact visual timeline and sequencing guide. Follow storyboard timing, shot transitions, framing rhythm, emotional flow, and scene continuity precisely. Expand every storyboard panel into smooth connected motion while preserving natural pacing and visual readability.

MAIN CHARACTER:

Same exact [person from the photo] throughout all scenes. Female college student around age 20. Long dark soft wavy layered hair with natural movement and strands occasionally falling across face. Warm light skin tone, dark brown eyes, slim proportions, youthful face, small mole under left eye, natural lips, minimal makeup, friendly expression. Maintain exact identity consistency throughout entire video. No face morphing, hairstyle changes, age changes, outfit changes, or body proportion shifts.

OUTFIT:

Black spaghetti strap top. Loose white cardigan hanging casually from shoulders. Faded blue jeans. Casual aesthetic campus fashion. Preserve exact clothing proportions and textures through all scenes.

PERSONALITY:

Playful, cheerful, naturally expressive, spontaneous, comfortable talking to camera, campus-girl energy, charismatic but effortless. Frequently smiles, small laughs, subtle eye expressions, natural head tilts, realistic blinking and soft reactions.

VIDEO STYLE:

Authentic early-2010s Sony Cyber-shot digicam aesthetic using CCD sensor rendering. Entire footage must feel like old memory-card footage discovered years later. Harsh direct flash, slight overexposure on skin, soft grain, digital compression artifacts, LCD pixel texture, slight chromatic softness, imperfect white balance, tiny autofocus hunting, nostalgic camera defects and realistic point-and-shoot rendering.

POV RULE:

Entire video remains from digital camera LCD POV exactly like storyboard. Viewer constantly sees glowing LCD screen in dark surroundings. Outside LCD screen fades softly into darkness and blur.

Camera UI overlays visible entire video:

REC icon
focus brackets
battery icon
timestamp "8.1.2012 3:15 AM"
1/30 F3.4 ISO100

Visible LCD glare reflections and realistic screen texture.

Duration exactly 15 seconds.

SCENE 1 (0:00–0:02)

Library interior. Walking slowly between bookshelves while holding camera facing herself. Handheld movement slightly shaky. Small laugh.

Character says softly in Indonesian:

"Lagi di perpustakaan jam segini, sepi banget tapi nyaman."

Camera autofocus briefly searches face. Bookshelves tightly packed with colorful books.

SCENE 2 (0:02–0:04)

Stops near manga shelf. Looks sideways and laughs naturally. Hair falls over cheek. Slight Cyber-shot zoom movement.

SCENE 3 (0:04–0:06)

Campus staircase. Walking downstairs while filming herself. Camera shakes naturally with footsteps. Students moving behind.

SCENE 4 (0:06–0:08)

Glass campus corridor. Walking backward facing camera. Afternoon sunlight entering windows. Soft lens flare.

Character smiles and says:

"Jadi bagus banget vibes nya hari ini."

SCENE 5 (0:08–0:10)

Outdoor campus area. Rotates camera briefly toward scenery before returning to face. Trees and students visible.

SCENE 6 (0:10–0:12)

Mall bookstore. Walking while holding drink. Direct flash creates bright skin highlights and darker background.

SCENE 7 (0:12–0:13.5)

Standing in front of store glass. Camera reflection visible. Adjusts hair and laughs softly.

SCENE 8 (0:13.5–0:15)

Close-up shot. Waves toward camera. Freeze frame briefly.

REC icon flashes.

Cut to black.

Keywords: nostalgic digicam, cyber-shot LCD vlog, college life memory footage, authentic CCD rendering, handheld documentary aesthetic, candid moments, realistic camera flaws, early-2010s aesthetic nostalgia.
This media is not supported in your browser
VIEW IN TELEGRAM
Мона Лиза избила Венеру: тренд на файтинги в Seedance 2.0 получил переиздание

Теперь в эпичных бойнях участвуют персонажи шедевров.

Чтобы повторить поединок Джоконды и древнеримской богини любви, копируйте промпт и применяйте в SpeShu.AI:
Round 1:
Use image1 as opening frame — MONA LISA left, VENUS right. Full HUD: yellow health bar left, green right, portraits, names, ROUND 1 center, SUPER bars bottom. Arena: A dark Renaissance cathedral merging with a stormy ocean shore. Photorealistic cinematic. Mortal Kombat style. HUD reacts every action. CHARACTERS: - MONA LISA (left): Dark silk robes, enigmatic smile, uses smoke-like "Sfumato" magic. - VENUS (right): Wrapped in elegant flowing beige silk drapery, golden hair, uses water and pearl magic.
SHOT 1 (00:00–00:01) — ROUND 1 Start. "ROUND 1" gothic gold text. Voice: "ROUND ONE. FIGHT!" Camera rockets in.
SHOT 2 (00:01–00:04) — DIRECT COMBAT. MONA LISA vanishes in dark smoke, reappears behind VENUS, striking with a hidden wooden dagger (Da Vinci design). VENUS blocks with a giant pearl shell — sparks and water spray. VENUS counter: a massive water whip slash — MONA LISA ducks, ground cracks. Camera 360° orbit. SLOW MOTION 20% on impacts — black oil paint and sea foam spraying outward.
SHOT 3 (00:04–00:07) — SPECIAL ABILITIES. MONA LISA summons a wooden Da Vinci tank that fires a heavy bolt — VENUS backflips over it, landing on a wave. VENUS calls the Zephyr winds — a tornado of pink rose petals and wind blasts MONA LISA backward. Camera ECU: petals clashing with dark oil smoke. Bars dropping.
SHOT 4 (00:07–00:10) — TITAN CLASH. MONA LISA summons a GIGANTIC SKELETAL HAND made of dry cracked oil paint. VENUS summons a MASSIVE TIDAL WAVE shaped like a goddess. SLOW MOTION 15%: both titans charge. MASSIVE COLLISION center screen. Camera RUSHES into explosion of black paint and blue water.
SHOT 5 (00:13–00:15) — EPIC DRAW. Both slammed into opposite pillars. Smoke and mist everywhere. Camera slow orbit. Both bars empty. FREEZE FRAME. "EPIC DRAW" burns center. Hard cut black.
Round 2: Final Canvas (Reality Collapse)
Hint:
Use video 1 @Video1 and continue with MONA LISA on the left, VENUS on the right. Full HUD: yellow health bar on the left, green on the right, portraits, names, ROUND 2 in the center, SUPER bars on the bottom. Arena: Reality cracks, revealing canvas textures and gold leaf. Photorealistic cinematic shot. Mortal Kombat style.
FRAME 1 (00:00–00:02) — Beginning of ROUND 2. Text “ROUND 2” is neon gold. Voice: “ROUND TWO. FIGHT!” MONA LISA’s eyes glow gold. She waves her hand, sharp shards of cracked paint flying like knives. SLOW MOTION 20%. VENUS spins, her beige drapery creating a protective silk cocoon. The debris bounces off, scattering sparks.
FRAME 2 (00:02–00:05) - EXTREME CLOSE COMBAT. VENUS charges in with a golden trident. MONA LISA parries the blow with a mechanical Da Vinci claw. The ECU is cut: metal collides with gold, faces contort. Speed ​​increases from 60% to 400%. Screen shakes. Black oil SPLITS from MONA LISA's hand on impact.
FRAME 3 (00:05–00:07) - ULTIMATES. MONA LISA opens a portal into a dark landscape - hundreds of shadows surround VENUS. VENUS raises her hands - the sky opens, showering pearls that explode like grenades. The camera rotates 360°. A complete chaos of artistic styles.
SHOT 4 (00:07–00:10) - TRUE FORM. MONA LISA's body cracks, she turns into a GIANT DARK WHIRLPOOL of oil and shadows. VENUS expands, transforming into a Light Being of pure light and ocean foam. The camera flies back.
SHOT 5 (00:10–00:12) - FINISH. VENUS releases a single, perfect rose petal, glowing like a star. It falls into the center of MONA's vortex. SLOW MOTION 10%: The dark oil begins to transform into beautiful golden flowers upon contact.


Вторая часть выйдет в обед ⏰
Мона Лиза избила Венеру: 2-я часть промпта

SHOT 6 (00:12–00:15) — MERGE. The hideous forms collapse. Silence. The two women stand side by side, their garments now a mixture of dark oil and golden silk. A single black tear, made of ink, falls from Venus’s eye. The camera zooms out widely: the arena is now a perfect masterpiece. Both bands disappear. Disappear into silence. The end.


Если вы хотите видео с другими персонажами, отправьте промпт в ChatGPT. Напишите, чтобы он выполнял роль промпт-инженера с образованием режиссёра. Он поправит внешность персонажей и придумает новые экшн-сцены.

В SpeShu.AI нейросети ChatGPT и Seedance 2.0 буквально располагаются в соседних вкладках и работают за токены. Так что вам не нужны подписки за 20$ и 35$ соответственно.

А получить дополнительную выгоду вам поможет промокод TG15 🎁
✍1👍1🤯1
Нужно быстро оформить документ в нейросети? Вот простые промпты

Акт выполненных работ
Ты юрист, специализируешься на российском договорном праве. Напиши акт выполненных работ по договору оказания услуг. Исполнитель: [название компании или ИП]. Заказчик: [название]. Предмет: [описание услуги, например «разработка сайта-каталога»]. Стоимость работ: [сумма] рублей, НДС не облагается / НДС 20%. Период выполнения: [даты]. Структура: реквизиты сторон, перечень выполненных работ, подтверждение отсутствия претензий, подписи. Юрисдикция: Россия. Реквизиты сторон замени на [placeholder].


Техническое задание
Ты технический писатель с опытом в разработке веб-продуктов. Напиши ТЗ на разработку [название продукта или функции]. Заказчик: [описание компании]. Исполнитель: [тип — студия, фрилансер, in-house команда]. Включи разделы: цель проекта, функциональные требования, нефункциональные требования, стек технологий — поставь [placeholder], этапы и сроки, критерии приёмки. Объём: 1–2 страницы. Стиль: технический, без воды. Специфические технологии и сроки замени на [placeholder].


Коммерческое предложение
Ты менеджер по продажам B2B с опытом в [отрасль]. Напиши коммерческое предложение для клиента из сферы [отрасль клиента]. Наша компания: [что делаем, 1–2 предложения]. Услуга: [название и суть]. Структура: боль клиента → наше решение → три конкретные выгоды → стоимость [placeholder] → следующий шаг. Тон: деловой, без давления и восклицательных знаков. Объём: одна страница.


NDA — соглашение о неразглашении
Ты юрист, российское право. Напиши двустороннее NDA между двумя юридическими лицами. Стороны: Сторона А — [название], Сторона Б — [название]. Предмет соглашения: передача конфиденциальной информации о [тип данных — технологии, клиентская база, финансовые показатели]. Срок действия: [X] лет с даты подписания. Санкции за нарушение: неустойка [placeholder] рублей. Включи: определение конфиденциальной информации, исключения из режима конфиденциальности, порядок возврата или уничтожения материалов. Реквизиты сторон замени на [placeholder]. Юрисдикция: Арбитражный суд города [placeholder].


Служебная записка
Ты делопроизводитель. Напиши служебную записку. Адресат: [должность и имя руководителя]. От кого: [должность и имя составителя]. Тема: [суть вопроса]. Содержание: [опишите ситуацию в 2–3 предложениях]. Что требуется от руководителя: [согласование / выделение бюджета / разрешение]. Стиль: официальный деловой. Объём: не больше половины страницы. Дату и номер документа замени на [placeholder].


Регламент или внутренняя инструкция
Ты технический писатель, пишешь внутреннюю документацию для компании. Напиши регламент [название процесса, например «обработки входящих заявок»]. Контекст: [тип компании, размер команды, суть процесса]. Включи разделы: цель регламента, область применения, ответственные лица [placeholder], порядок действий по шагам, сроки на каждый шаг, что делать в нештатных ситуациях. Стиль: нейтральный официальный, нумерованные пункты. Имена и должности замени на [placeholder].


Попробуйте любой промпт с бонусом 15% по промокоду TG15 на SpeShu.AI.
✍2👍1💯1
Новый азиатский тренд: успейте сгенерить, пока все соцсети не заполнились им

Будьте первопроходцем и удивляйте всех, кто увидит такие фото с вашим лицом.

1. Прикрепите своё фото в ChatGPT Image 2.0 на SpeShu.AI;
2. Опишите свою внешность в третьем абзаце;
3. Активируйте промокод TG15 на 15% бонуса и вставьте промпт:
Hyperrealistic optical illusion photo of a stylish 20-year-old woman realistically emerging halfway out of a smartphone screen only slightly outside the phone, maintaining believable proportions. POV high-angle DSLR shot with macro lens detail, vertical 9:16 composition.

A hand holding a smartphone with a burgundy case is visible in the foreground. The phone screen is active and clearly shows the realistic iOS Camera interface with white shutter button, “PHOTO” mode text, focus UI, and sharp readable elements. The woman’s legs and brown leather boots remain fully INSIDE the phone screen, while only her upper torso, shoulders, head, and part of her arms subtly emerge from the screen into reality. Keep the illusion physically believable and proportional do not make the body oversized outside the phone.

She has long dark black wavy hair with soft shine and light wind movement. Korean-inspired facial features: high nose bridge, double eyelids, defined jawline, natural matte glam makeup, ultra-realistic skin texture with visible pores and imperfections. She looks directly at the viewer with a playful confident gaze while blowing an elegant Korean-style kiss.

Outfit includes a fitted leather jacket with high collar, dark gray mini skirt, and premium brown leather boots. Realistic proportions, slim defined waist, natural fashion pose full of energy and life.

Foreground hand wears realistic gold rings. On the phone screen, handwritten-style white notes with arrows point to outfit details like “suede” and “leather boots.” All text must be perfectly readable and NOT mirrored.

Background: cinematic Parisian autumn park with shallow depth of field, green bench labeled “Le Silencio,” gray pavement, scattered autumn leaves, soft cloudy daylight, creamy bokeh effect.

Ultra-detailed realism: fingerprints on the phone glass, sharp screen pixels, leather textures, fabric stitching, natural reflections, realistic shadows, DSLR editorial photography quality.

Important:
Keep body size realistic relative to the phone.
Only slightly emerging from screen.
Boots stay inside the phone display.
Sharp readable iOS camera UI.
No mirrored text.
Cinematic but believable optical illusion best qbd cute pic.
👍7💯3👨‍💻2⚡1
This media is not supported in your browser
VIEW IN TELEGRAM
Запрещённая фишка в Seedance 2.0

Управлять камерой можно с помощью рисунков.

1. Сгенерируйте сцену, которую вы хотите анимировать;
2. Нарисуйте линию движения камерой в Paint;
3. Сгенерируйте в модели SpeShu промпт, который будет учитывать эту линию.

Например, вот какой промпт нужен, чтобы получить видео-пролёт из Стамбула ⬇️
Create a cinematic realistic high-speed drone video over Istanbul at golden hour, using the reference image as the exact location and flight-path guide. The drone starts very low above the sea surface, almost skimming the water, facing the Galata shoreline. It accelerates quickly forward over the rippling sea, following the drawn path from the foreground water toward the city. After the orbit, the camera tilts and opens toward the Golden Horn, the Historic Peninsula skyline, sunset reflections, ferries, rooftops, and glowing Istanbul atmosphere.
The red drawn line must not appear in the video; it is only a hidden flight-path reference. Add powerful emotional Turkish cinematic music: deep ney melody, dramatic darbuka rhythm, orchestral strings, subtle bağlama texture, epic rising percussion, and a grand heroic crescendo as the drone reaches Galata Tower. No text, no subtitles, no logos, no graphic overlays.


Если вам нужно другое видео, вставьте этот промпт в SpeShu и попросите написать похожий промпт с пролётом, но с учётом вашей сцены.

Нейросеть SpeShu подключается за два клика на странице «Подписки». А сгенерировать видео можно в соседнем окне с бонусом 15% по промокоду TG15. Попробуйте на сайте SpeShu.AI.
👍2🤯2💯2⚡1
This media is not supported in your browser
VIEW IN TELEGRAM
Новый мировой рекорд: 15 очков за 15 секунд

Теперь подобрать аксессуар можно в Kling и Seedance, не выходя из дома.

Промпт максимально короткий, копируйте и вставляйте вместо со своим видео в SpeShu.AI:
Start with video and glasses unchanged. then change the glasses every 0.5 seconds to a different style. show wide range of styles: early 1900s, 1970s sunglasses, 1980s shutter shades, and other colorful vintage interesting styles of glasses or sunglasses. only photorealistic tasteful real glasses styles throughout decades, showing wide variety of shapes, sizes, colors, translucency, materials. no music, no dialogue. play subtle minimal natural sound effects in sync with glasses changing. keep the person's movements, room environment, and clothes exactly the same. one continuous shot.
⚡1🤩1💯1👨‍💻1
Тренд с переодеванием на 5,6 МЛН просмотров

Выглядит сложно, но мы составили максимально простую инструкцию.

1️⃣ Загрузите своё фото в ChatGPT Image 2.0 и сгенерируйте первый наряд. Не забудьте указать севшую батарейку над головой 😁

2️⃣ Сгенерируйте любой другой образ, который должен появиться следующим. Лучше взять сразу 3-5 аутфитов. Чтобы они генерировались как надо и слева была инфографика с элементами одежды, используйте готовый промпт:
Use the uploaded character image as the only character and outfit reference. Create a 3:4 vertical composition with a pure white background, generous negative space, and a clear visual hierarchy. Place an information area on the left side. Add a prominent large English title at the top as the main visual focus. Below it, break down the character’s current outfit into three groups, with two items per group, for a total of six items. The first group shows accessories, the second group shows upper-body clothing items, and the third group shows bottoms and footwear. Each item should be presented as an individual product image. All items must be extracted directly from the character’s actual outfit. Only show items that genuinely exist on the character. Do not add, replace, or modify any items. Arrange the three groups vertically, separating them with thin divider lines while maintaining consistent sizing, spacing, and strict alignment. Place the full-body character on the right side as the main subject, showing the complete outfit. The character should occupy the main visual area and showcase the full outfit in a natural, confident pose. The character and the information area must not overlap, allowing a clear relationship between the character and the three outfit breakdown groups. The overall layout should feel balanced, clean, and organized.


3️⃣ Оживите образы в Kling 3.0. Загрузите сперва один наряд, а потом второй. Затем второй и третий. Третий и четвёртый. Тогда у вас получится правильное перевоплощение за счёт поочерёдного преобразования «фреймов». Промпт:
Locked camera. The character first performs a short natural action that matches their personality. Then rotates clockwise 360° continuously in place, maintaining the same direction throughout. No turning back, no reversing direction, and no pauses. The outfit changes only while the character is in a side profile. The front view remains unchanged, and when the character faces forward again, the final outfit is fully revealed. All items and their corresponding text switch simultaneously. Items and text always remain fixed in their final positions and only perform a single clockwise spin in place. No movement and no group rotation. Everything becomes static once the rotation is complete. The character ends in the final pose. All rotations happen only once and then stop. No flickering, no frame glitches, no flying elements, and no exaggerated visual effects.


И ChatGPT, и Kling работают в одном окне SpeShu.AI. Покупать подписку не нужно. А дополнительную выгоду можно получить с промокодом TG15.
⚡2💯2🤯1
Как сэкономить 20 000 рублей на съёмке с друзьями и подругами

Секретную фишку с пролётом дрона можно использовать для группой фотосессии и видеопродакшена.

Изобразите ваших друзей группой в любой стильной локации — квартира в небоскрёбе, пентхаус, яхта. Сделать это можно в ChatGPT Image 2.0.

Затем нарисуйте красную линию в любой редакторе, хоть в Paint. По этой линии будет летать квадрокоптер.

Отправьте получившееся фото в Seedance 2.0 вместе с этим промптом:
FPV first-person view shot, with the camera following the movement logic of the red guide line, and ensure the final footage does not show the red line.


Открыть ChatGPT Image 2.0 и Seedance 2.0, не оплачивая 55$ за подписки, можно в SpeShu.AI. А по промокоду TG15 вы получите +15% к своему балансу.
⚡1
This media is not supported in your browser
VIEW IN TELEGRAM
Pixar ненавидит ИИ. Эти два промпта создают мультики на миллионы просмотров и долларов

Нашли в сети классное видео. Разбираем, как его повторить👇

1) Создаём сториборд. В предыдущих постах мы писали, что крутой результат получается при двухступенчатой работе.

Сначала нужно создать персонажей и их характеры в ChatGPT Image 2.0:
Main Character Casting Descriptions:

- Pizza Chef - Jack (main actor in kitchen): Early 50s energetic male, messy silver hair, large prominent nose, thick expressive eyebrows, sharp intense eyes, fair skin with slight blush from heat. Wears white double-breasted chef jacket, wear white chef hat with text “el.cine” in front, gree neckerchief. Highly animated face — furrowed brows, focused squint, dramatic determination turning to exhaustion.
- Pizza Delivery Guy - Tom (main actor on street/scooter): Late teens/early 20s lanky male, long blue hair, huge expressive brown eyes, long nose, very animated facial expressions (surprise, determination, panic, relief). Wears white helmet with spinning yellow propeller on to, light blue leather with text el.cine at back, white pants, sneakers. Fast, exaggerated movements.
- Customer (final shot): Large, middle-aged stern woman, brown hair, heavy eyebrows, downturned mouth, wearing beige suit jacket, white shirt, dark trousers. Standing in doorway with impatient/annoyed expression.


2) Затем этот сториборд отправляем в Seedance 2.0 с промптом-раскадровкой. Обратите внимание, промпт большой. Часть выкладываем в этом посте, а часть пойдёт во второй пост:
High-energy 3D CGI animated comedy short, Pixar quality, ultra-detailed character animation, exaggerated physics, vibrant colors, warm orange kitchen lighting with glowing flames, bright daylight city streets, dynamic camera work with fast pans, tilts and dramatic angles, subtle motion blur on fast movements, comedic timing and expressions, upbeat energetic music with whooshes and impacts.

SHOT 1 (0:00–0:02) – Cinematic fast motion, dramatic low angle with subtle Dutch tilt and intense push-in: fast push from kitchen wide shot to close up on the Pizza Chef’s face in the bustling kitchen. He grips the large pepperoni pizza on a metal tray with raw, over-the-top determination — brows dramatically furrowed into deep angry V-shapes, eyes sharply narrowed with a fierce glint and slight crazy wideness at the edges, teeth gritted in heroic effort, dramatic sweat beads flying off his forehead. Bright orange flames explode upward from the pizza in the foreground with massive sparks and heat waves licking toward his face.
Dynamic camera orbits left while pushing in for maximum tension, subtle motion blur on the flames. Background shows chaotic kitchen with stacked pizza boxes, glowing ovens, and flying embers.

SHOT 2 (0:02–0:04) – Medium close-up, eye-level: Chef lifts the flaming pizza higher with both hands, leans forward, eyes wide with concentration as flames lick upward toward his face.

SHOT 3 (0:04–0:06) – Medium shot, eye-level, dynamic pan: Chef dramatically spins the flaming pizza on the peel in a huge fiery arc above his head, left hand on forehead in dramatic pose, right arm extended. Flames trail in a perfect circle.

SHOT 4 (0:06–0:08) – Low-angle dramatic shot looking up: Chef tosses the flaming pizza high into the air with both hands. The camera follows the spinning fiery pizza as it arcs toward the ceiling tiles.

SHOT 5 (0:08–0:10) – Extreme low-angle on ceiling: The flaming pizza spins in a perfect circle of fire against the tiled ceiling, sparks flying.

SHOT 6 (0:10–0:12) – Wide dynamic shot, low angle: Chef does a full acrobatic flip in mid-air, upside-down, catching the flaming pizza behind his back while still in the air.

SHOT 7 (0:12–0:14) – Wide action shot, eye-level: Chef lands in a wide stance, spins the flaming pizza on one hand like a basketball, then dramatically throws it forward toward the open doorway with full body power, flames trailing, quick push in and follow the close up of the flying pizza in slow motion