Ai Hidden Space | Serge Green

🥸 Mustachio AI Video Ad Made it with a triple combo — ChatGPT 5.6 Sol + Seedream 5.0 Pro on @higgsfield_ai + Seedance with @capcutapp . this method is faster in development, but you trade away a bit of control. ▾ storyboard and prompt below Prompt itself is short. It's working good only with visual storyboard reference. Create a polished 15-second photorealistic 1980s American moustache-cream commercial. Follow the reference storyboard exactly from the first frame to the last: use the same shot order, timing, compositions, character performance, product, moustache transformation and final typography. Treat the reference only as a storyboard guide; never show the grid, panels, captions or timecodes in the video. Add beautiful background music inspired by elegant late-1970s and early-1980s American commercials. Warm, expressive American male voice-over: “He was ready for the day. His moustache wasn’t. Then came Mustachio. Make your moustache happy.” Synchronize the final spoken slogan with the typography appearing word by word.

@WolfRiccardo @AIatMeta @Meta niiiice! good idea good vibe

> Art Vibe 4:21 ratio @AIatMeta / Muse Image

@WolfRiccardo @dreamina_ai i hope 🙏

@digitalwindai @dreamina_ai I think they’ll release an amazing t2i model soon, and everything will be perfect.

Seedream 5.0 Pro has been officially announced! I did a realism test. What do you think? **Realism test / Seedream 5.0 Pro** @dreamina_ai #DreaminaCPP

@noorwithwifi Wow. this is so great idea and execution. Bravo. I think it's can be useful for brand via social media 😎

🇯🇴 Jordan • 🇵🇪 Peru • 🇺🇸 USA Prompt: Create a high-end 3D optical illusion scene featuring a modern laptop on a polished marble desk. The laptop screen displays a premium travel exploration interface for [Destination], with elegant typography, weather information, destination details, navigation menu, curated experiences, luxury stays, and concierge options. Make the digital landscape seamlessly extend from the screen into a realistic miniature diorama covering the keyboard area, blending UI and physical world together. Include iconic landmarks, natural landscapes, local architecture, cultural figures, wildlife, and native plants of [Destination]. Keep the trackpad and laptop edges clean and realistic. Add stylish desk elements such as a coffee mug and hardcover book. Use cinematic warm natural lighting, realistic textures, shallow depth of field, luxury travel branding aesthetic, ultra-detailed 3D render, photorealistic quality.

@CaliraVal You mean cover?)

@digitalwindai Nice Creation

Two weeks of active work with ChatGPT 5.6 Sol and Claude Fable 5. Both are good, but I’m staying with ChatGPT. It all comes down to limits. X has been full of Claude hype lately, and it’s not coming from nowhere. The models are genuinely good. ChatGPT released its answer a little later, and after working with both, I can get the result I need from either one. What surprises me is how people compare which LLM writes better prompts for image and video generation. Wait. I write the prompts, not the LLM. I control the context, language, materials, scene, and camera. Give either model too much freedom and both will eventually write nonsense or lose context. It’s still human in the loop. The model helps, but the control stays with me. What I really discovered after trying Fable, Opus, and even Sonnet was the limits. I work with LLMs a lot every day. Even small requests drain the five-hour limit, and the weekly allowance can disappear in just a couple of days. ChatGPT Sol, meanwhile, gives me agent mode, the same kind of skills for deep specialization, and native image generation. I use all of it heavily and have never hit a limit. I only found the limits menu for the first time after my experience with Claude. So I won’t renew my subscription. Not because the model is bad. I just don’t see the point. Both give me the result I need, but only one lets me work without constantly thinking about when the limit will reset. For me, the choice is obvious. ChatGPT simply offers better economics. Nothing personal. Thanks to healthy competition. How is it on your side? Feel free to leave your experience in replies.

@longstoriesai Wow. so love this. Really good job. especially on the consistency!

Some stories are worth the drama. What’s yours?

@capcutapp @CinaimaFilms It's start from prompt to agent and no choose to generate few images or video iteractions. can't exclude this agent from UI. just wanna button without ai chat... CapCut team. it's a basic, standard in 2026.

It all starts with a prompt. @CinaimaFilms shows us theirs in Video Studio for the CapCut CRE[AI]TE AI Festival. Cinaima Films is an independent studio creating experimental short films with artificial intelligence, redefining the boundaries of visual storytelling. Their work thrives on continuous experimentation and refinement, pushing AI tools to their limits. What are you making for the CapCut CRE[AI]TE AI Festival? Submit your work by August 10, 2026 to capcut.creaite26.com

@im_shahid7 Nice typo and composition. Nit from first iteraction as I see. But... So cool. Love it!

Made with GPT IMAGE 2 Prompt: Create a 4:5 full-bleed editorial action poster for STRIKE SPORT. The brand’s visual identity follows these must-visible traits: a bright outdoor photograph with a clear open sky dominating a large portion of the frame; enormous warm-cream extra-condensed block letters cropped by the canvas and sitting behind the main subject; one oversized action figure cutting diagonally across the layout and breaking through the text layer; a low or close wide-angle camera angle that makes the foreground feel physically imposing; secondary text, large numerals, or stacked words in cream placed along bottom and side edges; compact white editorial microcopy in short tight clusters anchored to strong grid positions; one vivid accent color concentrated on the hero product or outfit while the environment stays sky-blue and neutral; hard midday sunlight with crisp shadows and high-contrast edges; a layered structure alternating between flat graphic type and real photography; minimal ornament — only small marks, rules, or separators; a dense, kinetic layout with the action dominant, type second, and microcopy third. Scene: A professional Runner is throwing a powerful hook with boxing gloves in an outdoor rooftop running in a modern city,, and a distant skyline under a clear sky. Camera & Composition: Low close wide-angle outdoors, oversized foreground scale, decisive frozen motion, one strong diagonal movement from lower left to upper right, subject cropped by at least one canvas edge. Typography: Place massive warm-cream ultra-condensed block sans lettering reading STRIKE SPORT behind the subject, filling over half the canvas, cropped by the frame and partially hidden by the action. Add compact white microcopy reading ROUND 01 / FIGHT HARD / POWER IN MOTION in tight editorial blocks. Include a small generic glove mark symbol and bottom information clusters in cream. Wardrobe: Modern athletic boxing gear, black base with sharp red accent details, tight performance fit, sweat-textured realism. Brand colors: saturated sky-blue or cyan dominant, warm cream type, crisp white microcopy, deep shadows, one vivid red accent on the gloves and highlights. Lighting & Finish: Hard midday sun, crisp shadows, high-contrast commercial photo realism, slight print-grain texture. No illustration, 3D rendering, real logos, or watermarks. Avoid: real brand logos, watermarks, QR codes, comic or halftone effects, dark studio scenes, muted palettes, or a tiny distant subject. Generate as a 4K ultra-high-resolution raster image

@Ciri_ai Super useful in commercial field. Great job! Try to work in same style with another product. Thank you for the work! 😎

Crafted with GPT image 2 + Gemini Omni/ Seedance 2.0 Prompt: Create a clean, premium storyboard infographic for a product ASMR unboxing video. Design specifications: White background with a modern, minimalist layout. Title at the top: STORYBOARD Product name in bold green (replace with: [PRODUCT NAME]) Subtitle: ASMR UNBOXING Include four information boxes below the title: Duration: 30 Seconds Style: POV Hands, ASMR Audience: 18–35 years old Audio Suggestion: Soft ASMR • Crinkles • Tapping • Pouring Create 12 storyboard panels arranged in a 3-column × 4-row grid. Each panel should contain: A numbered green badge (1–12) Timestamp (0–2.5s, 2.5–5s, etc.) A realistic cinematic image showing the scene Handwritten white doodle text like: TA-DA! POP! WOW! PICK! CRINKLE~ TEAR! POUR~ HOT WATER STIR~ SMOOTH! BEST! Three text sections below every image: VISUAL: ACTION: DIALOGUE: Use realistic product photography, warm wooden table, soft natural lighting, shallow depth of field, POV hands only (no face visible), premium commercial advertising style. Storyboard sequence: 1 (0–2.5s) Visual: Product box on wooden table. Action: Hands enter frame and point to the box. Dialogue: "Have you tried this before?" 2 (2.5–5s) Visual: Opening the box. Action: Lift the top flap slowly. Dialogue: "Let's unbox it together." 3 (5–7.5s) Visual: Multiple individual sachets neatly arranged. Action: Fully reveal the inside. Dialogue: "Wow, look how many!" 4 (7.5–10s) Visual: Pick up one sachet. Action: Remove a single stick pack. Dialogue: "Let's start with one." 5 (10–12.5s) Visual: Close-up of sachet. Action: Hold and gently crinkle it. Dialogue: "That crinkle sound is satisfying." 6 (12.5–15s) Visual: Tear open the top. Action: Slow ASMR tearing. Dialogue: "Just a small tear." 7 (15–17.5s) Visual: Powder visible inside. Action: Show the powder close-up. Dialogue: "Looks delicious." 8 (17.5–20s) Visual: Pour powder into mug. Action: Slow pouring. Dialogue: "Pour everything in." 9 (20–22.5s) Visual: Hot water being poured. Action: Steam visible. Dialogue: "Add hot water." 10 (22.5–25s) Visual: Stir drink. Action: Slow circular stirring. Dialogue: "Mix it well." 11 (25–27.5s) Visual: Finished drink. Action: Show creamy texture from above. Dialogue: "Looks smooth and creamy." 12 (27.5–30s) Visual: Product box beside finished drink with thumbs up. Action: Hand gives thumbs up. Dialogue: "Easy, delicious, and ready!" Footer: Total Duration: 30 Seconds Format: Vertical (9:16) Style: POV Hands, ASMR Unboxing Typography should resemble a professional creative agency storyboard, with clean spacing, green accents, rounded panel borders, and high-end presentation suitable for client pitches.

@LudovicCreator Look perfect - pace, consistency. Strong work! 🔥

🎨 SEEDANCE 2 🎨 Prompt : A high-speed cinematic chase across a vast desert at sunset. A rider in a long dark coat gallops on a black horse through dunes glowing orange and gold, pursued by a distant group of armored riders kicking up huge trails of dust. The camera starts wide, showing the scale of the desert and the speed of the pursuit, then drops low beside the horse’s legs, capturing flying sand, muscle movement, and the rider’s intense focus. Wind whips through fabric, dust fills the air, and the light grows redder as the sun sinks behind distant cliffs. At a key moment, the rider launches the horse over a narrow canyon gap, sand exploding behind them as the pursuers close in. The scene feels epic, primal, and visceral, like a historical action film with modern cinematic energy. Made in @LumaLabsAI #LumaCPP

@iamsofiaijaz So cuteee. Love it!

Image with GPT image 2 on Chatgpt Prompt 👇 A whimsical, ultra-detailed 3D illustration of a cute toddler girl with an oversized head and big expressive eyes, standing barefoot inside a white bathroom sink. She is balancing on a giant toothpaste tube while brushing her teeth with a blue toothbrush. Water splashes everywhere, frozen mid-air in sparkling droplets. The child has dark brown hair tied in a messy bun with colorful hair clips, wearing a loose gray t-shirt and patterned shorts. Soft natural morning light streams through a window, creating a clean, cozy bathroom atmosphere. Pixar-style character design, chibi proportions, hyper-realistic textures, shallow depth of field, bright pastel colors, playful and joyful mood, ultra-high resolution, cinematic lighting.

@itsshara_ai It's look so different if try to compare with the storyboard. I think, it's too much panels in gpt2 and for seedance.

Made with Seedance 2.0 + GPT image 2 Prompt below:

@CaliraVal @wavespeed_ai In this ser seedance is lost control... On storyboard one look, at the video another one. I think it's can be fixed better in the prompt. Anyway - looks cool ✌️

Golden roads, ocean breeze, and timeless elegance. Created with Gpt Image 2 + Seedance 2.0 on @wavespeed_ai Prompt: 15-Second Storyboard (Luxury Fashion Cinematic) Duration: 15s | Aspect Ratio: 9:16 | Style: Ultra-realistic Luxury Commercial Shot 1 (0:00–0:02) – Arrival Close-up of elegant white heels stepping onto the coastal road. Black vintage convertible waits in the background. Camera: Low-angle tracking shot. Shot 2 (0:02–0:05) – Walk Model confidently walks toward the convertible with the ocean behind her. Hair gently moves in the sea breeze. Camera: Smooth side tracking shot. Shot 3 (0:05–0:08) – Reflection Close-up of her face in the side mirror as she softly adjusts her hair. Sunlight creates warm highlights. Camera: Mirror close-up with focus pull. Shot 4 (0:08–0:11) – Confidence Sitting in the driver's seat, she puts on elegant sunglasses and smiles. Red leather interior adds a premium feel. Camera: Slow dolly-in close-up. Shot 5 (0:11–0:15) – Drive Away Convertible cruises along the breathtaking Amalfi Coast road. Ocean sparkles under golden sunlight as the title "Rivelazione" fades in. Camera: Drone follow shot transitioning to a cinematic wide aerial. Overall Look Bright golden-hour lighting Premium Italian Riviera aesthetic Smooth cinematic camera movements Luxury fashion TV commercial vibe 24fps, ultra-realistic, high-end color grading

@Shorelyn_ @ImagineArt_X Great set! Bravo. But who yawned that loudly—her boyfriend? 😂 I hope Seedance eventually lets us export the music and sound effects as separate audio tracks so we can edit them.

Seedance 2.0 on @ImagineArt_X Prompt: Create a realistic GRWM (Get Ready With Me) lifestyle video featuring a stylish Korean college student with long silky black hair, radiant skin, and a fresh natural look. Bright modern apartment with floor-to-ceiling windows, warm morning sunlight, cozy Scandinavian décor, premium lifestyle vlog aesthetic, cinematic handheld camera, ultra-realistic photography. The video opens with her walking to the bedroom window and pulling the curtains open as golden morning sunlight floods the room. She smiles, stretches naturally, enjoys the fresh air for a moment, then turns toward the camera before beginning her day. She heads into the bathroom where she completes a refreshing skincare routine using cleanser, toner, serum, moisturizer, and lip balm. Warm natural light reflects across the mirror as cinematic close-ups capture her glowing skin. Next, she blow-dries her hair into soft loose waves and applies fresh everyday makeup with foundation, blush, mascara, soft eyeliner, and a glossy pink lip tint. She smiles naturally while checking the final look in the mirror. She opens her wardrobe and browses several outfits before choosing a fitted pastel blue crop top with high-waisted light blue jeans. She changes into the outfit, accessorizes with delicate gold jewelry, sunglasses, a minimalist watch, and sprays her favorite perfume. Standing in front of a full-length mirror, she admires the outfit, spins once with a smile, adjusts a strand of hair, and captures a quick mirror selfie. She prepares an iced latte in the kitchen, grabs a notebook, tablet, headphones, and a cream-colored backpack before locking the apartment door behind her. Outside, she walks confidently through tree-lined streets toward campus as students ride bicycles and buses pass by. She crosses a lively crosswalk, enjoying the vibrant college morning atmosphere. She arrives on campus, walks between modern university buildings, greets classmates with smiles, enjoys her iced latte outside a campus café, and sits on the library steps reviewing her notes while laughing with friends. The video ends as she walks across the beautiful university courtyard during golden morning light, smiling confidently toward the camera while the camera slowly pulls back to reveal the bustling campus. Style: premium college lifestyle vlog, realistic GRWM content, cinematic handheld and gimbal camera movement, elegant transitions, warm natural lighting, cozy apartment aesthetic, photorealistic, shallow depth of field, luxury social media content, 4K HDR, 16:9 widescreen, no subtitles, no text overlays.

@Kashberg_0 Nice look. Love this aesthetic man ✌️

Seedream 5.0 pro Prompt: { "subject_and_outfit_formula": "A stylish young East Asian woman with a confident and cool expression, her dark, shoulder-length hair gently tousled by a light breeze. She is dressed in an oversized, retro-style red athletic jersey with white side panels and bold graphic lettering on the chest. Below, she wears high-waisted light-wash denim shorts featuring aggressive distressing, large ripped panels across the thighs, and raw, frayed hems. Her footwear includes thick white crew socks with classic red and blue stripes at the top, paired with chunky, multi-layered cream and beige platform sneakers that add to her urban, sporty aesthetic.", "background_and_environment": "The scene is set in a minimalist, sun-drenched outdoor skatepark featuring smooth, sweeping gray concrete ramps and bowls. The backdrop is an expansive, vibrant azure sky dotted with soft, feathered white clouds, suggesting a clear and bright summer afternoon. Intense, direct sunlight originates from a high angle, creating a luminous rim-lighting effect around the subject's silhouette and casting sharp, defined shadows on the concrete surface, evoking a sense of high-energy urban life.", "camera_angle_and_composition": "An extreme low-angle 'worm's eye view' shot captured from a ground-level perspective looking steeply upward, which emphasizes the subject's height and commanding, heroic presence. A colorful, illustrative skateboard with intricate pop-art graphics and bold 'SKATE' typography is held vertically in the immediate foreground, acting as a powerful visual anchor and creating a strong sense of depth. The composition utilizes a wide-angle perspective to frame the subject against the vastness of the sky, making her the central focal point of the frame.", "face_reference": "Use the uploaded photo as the primary reference for facial structure and features.", "camera_and_vintage_style_settings": "Standard high-quality digital photography, crisp and clear." }

@_OAK200 It's look cool in aesthetic but as I see on the wide plan - man have 7 fingers? Waiting Mj fix that. I think normal anatomy is the standard at 2026...

exploring midjourney v8.2 | neo-noir film stills

@impalementd Hah very nice. Good job man..in my practice seedance mini unusable, but you proof that's not true.

터치만 하면 애니메이션으로! 마법의 펜 프롬프트 이런 감각적인 분위기, CF에서 좀 본 것 같지? 이 프롬프트 쓰면 너도 바로 딸깍 할 수 있어..! 준비물 1. Seedance 2.0이나 Mini에 넣고 10초로 제작 2. 변주를 주고 싶다면 GPT나 클로드랑 대화해봐! 프롬프트는 하단 게시글에!

Hey! Prompting an action scene isn’t that difficult. But getting an interesting anime style is another story. Could you show or explain which reference images you used—or perhaps share an image along with the style description? I’d be really interested, because as you said, getting the model to produce anime without defaulting to something like the Ghibli style is a real challenge. Also - cool video man!

This anime prompt on Seedance 2.0 goes incredibly hard. ⚔️🔥 Honestly, I love how much intensity and cinematic energy you can push with this kind of concept. PROMPT below 👇 A fearless kunoichi with flowing black hair, intense violet eyes, elegant combat outfit, athletic and agile presence, rendered in ultra-premium Japanese anime rendering, MAPPA-inspired sakuga, sharp manga linework, vibrant cel shading, dynamic perspective distortion, glowing aura VFX - 0–4s: leaps across rooftops above a city under attack by rogue ninja clans, camera racing alongside her through the skyline; - 4–10s: engages multiple assassins in mid-air combat, chaining acrobatic dodges, kunai throws and spinning kicks while rooftops collapse beneath the battle, speed lines and motion smears flooding the frame; - 10–15s: confronts the clan leader atop a giant torii gate, defeats him in a lightning-fast exchange and sends him crashing into the street below, ending with the city safe as the camera rises above the dawn skyline - Epic-level anime action, kinetic choreography, cinematic rooftop warfare. Want me to share more anime prompts like this? 👇 #DreaminaCPP @dreamina_ai

Thank you — I was starting to think I was the only one coming to this conclusion. After several weeks of testing, I won’t be renewing my Claude subscription. With ChatGPT, I’ve never even had to think about limits, despite using it heavily every day. With Claude, I burn through the entire weekly allowance in just a couple of days and then have to wait for it to reset. Most importantly, even if an LLM writes the prompt, the human is still in control. Fable and Sol are definitely excellent models for this.

Fable and GPT 5.6 Sol work great with Seedance 2.0 Grok 4.5 isn't too shabby either. You can try it for free on Arena. AI Choose DIRECT Chat. Animate this exact image into a seamless 14-second cinematic fantasy sequence in the style of 1980's dark fantasy: practical animatronic puppetry, soft film grain, misty natural lighting, photorealistic yet whimsical. Maintain perfect character likeness, costumes, and rocky misty background with distant ruins at all times. Subtle handheld camera with slow gentle push-in for intimacy. No morphing, no distortion. 0-4s: Woman with long dark wavy hair, golden braided headband and flowing beige dress leans in slightly, brow furrowed with quiet concern, hair and fabric gently swaying in breeze. She speaks softly and clearly with natural lip-sync: “Are there any other choices besides those?” Subtle head tilt and searching eyes. 4-6s: Wise wrinkled brown creature with wild white hair, large expressive eyes and tattered leather armor comes alive with realistic animatronic motion — deep facial wrinkles shift, eyes twinkle mischievously, head bobs gently. He lets out a warm, cackling laugh (raspy elderly puppet voice, joyful and knowing). Leather creaks, armor soft clinks. 6-14s: Creature leans closer with gentle kindness, jaw and lips articulating precisely like a high-end fantasy film animatronic puppet. He replies in the same warm, raspy, storybook voice with clear lip-sync: “Have you heard of GROK Four Point Five?” Eyes crinkle with wisdom, subtle blinks, slight knowing smile. Woman listens intently, expression softening into wonder. Audio design: Soft whimsical orchestral fantasy score (gentle flutes, warm strings, delicate magical chimes that swell subtly). Layered SFX: light wind through rocks, fabric rustle, creature skin and leather creaks, small armor clinks, natural outdoor reverb on dialogue. Perfect emotional timing and clear spoken words. 14 seconds total, cinematic, high fidelity motion, locked to source image composition.

Hey. The styles in MJ are the strongest part of all this. But I have a lot of questions about storyboards with so many panels and how well Seedance actually follows them. In your example, and in many others, I keep seeing the same thing: the storyboard shows one story and visual direction, while Seedance creates something that matches it by maybe 60%. For me personally, that’s a major loss of control. I don’t think this is usable in production—maybe only as a showcase.

I created an entire fight scene between two original characters using only AI. Characters → Midjourney Character sheets + prompting → ChatGPT Animation → Seedance 2.0 The result actually feels good. The movement, timing, and impact all landed better than I expected. Here’s the full fight: PS:) for business inquiries contact here: shaileshshakya818@gmail.com