SEEDANCE 2.0/2.5 PROMPT to convert your videos aspect ratio from 16:9 to 9:16 (or vice versa):
"Convert the original 16:9 horizontal video @(TAG THE VIDEO) into a native 9:16 vertical video.
Do NOT simply crop the original video. Intelligently reframe and extend/reconstruct the scene so the vertical composition feels like it was originally created in 9:16.
Preserve all important visual information, characters, actions, objects, background details, and story beats from the original horizontal video. Reposition elements naturally within the vertical frame when necessary so nothing important is cut off.
Keep the exact same characters, animation, actions, timing, camera movement, environment, lighting, colors, saturation, and visual style as the original video.
Maintain correct anatomy, object geometry, perspective, spatial relationships, and continuity. Newly generated areas outside the original frame must seamlessly match the existing environment.
Final result: 9:16 vertical, full-frame, naturally composed, no black bars, no stretched image, no important details cropped, and visually consistent with the original 16:9 video."
We just open-sourced our entire marketing playbook.
After huge viral success with our Marketing OS running on Grok Bot, we decided to bring it to Claude.
Introducing Marketing AGI by Maxfusion.
You no longer need your first 5 marketing hires.
📁 Marketing Department
┃
┣ 📁 Head of Marketing
┃ ┣ 📁 Positioning & Offer Design
┃ ┣ 📁 Pricing Strategy
┃ ┗ 📁 Competitor Teardowns, Public Data Only
┃
┣ 📁 Copywriter
┃ ┣ 📁 20 Variants, Panel-Scored
┃ ┣ 📁 Email Sequences, Written in Full
┃ ┗ 📁 Posts Built to Survive the Feed
┃
┣ 📁 Creative Strategist
┃ ┣ 📁 The 18-Tactic Hook Engine
┃ ┣ 📁 Fatigue Caught at the Concept Level
┃ ┗ 📁 Next Tests, Ranked & Briefed
┃
┣ 📁 Launch Lead
┃ ┣ 📁 The Runway Before Launch Day
┃ ┗ 📁 Product Hunt, Hour by Hour
┃
┣ 📁 GEO Lead
┃ ┣ 📁 Ranked by ChatGPT & Perplexity
┃ ┗ 📁 App Store, Metadata to Screenshots
┃
┗ 📁 Analyst
┣ 📁 Audits, Weighted 0-100
┣ 📁 Numbers That Mean Something
┗ 📁 AI Slop, Caught on Sight
And they coordinate all the work:
A single Claude skill runs the whole loop:
The Analyst finds the problems, the Copywriter rewrites it, the Creative Strategist tests the new version, and the Analyst grades the outcome.
Comment "AGI" and I'll send you the setup.
Gpt image 2 + Seedance 2.5 on Higgsfield
Prompt:
Scene 1 — Busy Morning | 0:00–0:05
“Photorealistic handheld street footage of a young Asian woman in her mid-20s walking through a busy city sidewalk in the morning. She wears a beige jacket, white shirt, loose blue jeans and carries a small shoulder bag. Natural pedestrians, bicycles, buses and storefronts move around her. She checks her phone while walking, completely unaware of what is about to happen. Authentic documentary-style video.”
Scene 2 — The Discovery | 0:05–0:10
“Low handheld camera angle following behind the woman as she walks away. A black leather wallet accidentally slips from the side pocket of her shoulder bag and lands on the sidewalk. She continues walking without noticing. A young man walking several steps behind suddenly notices the wallet on the ground.”
Scene 3 — The Decision | 0:10–0:15
“Medium handheld shot of the young man picking up the wallet and looking around for its owner. He opens it briefly only enough to identify who it belongs to, then immediately closes it. He spots the woman disappearing into the crowd and starts walking quickly after her. Realistic expressions and natural body movement.”
Scene 4 — Catching Her | 0:15–0:20
“Dynamic handheld tracking shot of the young man moving through the busy sidewalk, carefully avoiding pedestrians as he tries to catch up with the woman. He finally reaches her and gently taps her shoulder. She turns around with a confused expression, then looks surprised when he holds out her wallet.”
Scene 5 — The Reaction | 0:20–0:25
“Close realistic shot of the woman taking the wallet back and checking her bag in disbelief. She realizes she never noticed losing it. She looks at the man with genuine gratitude and smiles. He simply smiles back and gestures that everything is fine. Natural emotional acting, no exaggerated expressions.”
Scene 6 — Small Good Deed | 0:25–0:30
“Wide handheld shot as the two people walk in opposite directions through the busy city street. The woman briefly looks back and smiles. The man continues walking normally as the city moves around him. Warm late-morning sunlight, realistic pedestrians and traffic, subtle camera movement, authentic everyday-life atmosphere.”
Overall style:
“Ultra-realistic live-action footage, documentary cinematography, natural human behavior, realistic skin and clothing, authentic city environment, imperfect handheld movement, believable background activity, natural lighting, subtle motion blur, no cinematic fantasy effects, no logos, no text, no watermark.”
Another Vox style✨️
🎨generate pake : gemini
🖌 prompt :
10-second smooth time-lapse animated video in the exact Vox-style historical documentary animation.Background: aged parchment paper with subtle vintage texture, faint grid lines, and paper-like creases, exactly like old map animations.All elements are clean hand-drawn cutout / paper sticker style illustrations with soft drop shadows. Use stylized cutout human figures only — no detailed visible hands or close-up human actions.Story in fast, lively time-lapse (no voiceover, only background sound):A cool and interesting 10-second time-lapse showing the journey of nasi goreng from being made to becoming a busy popular street food:Start with a simple cooking station appearing on the parchment. A stylized cutout cook figure prepares nasi goreng — wok, ingredients (rice, eggs, vegetables, spices) smoothly appear and mix in cutout style.
The finished nasi goreng is served on plates. A small food stall quickly appears.
Lively movement begins: multiple stylized cutout people figures start appearing from different directions on the parchment (like routes on a map). They move toward the stall, form a growing queue, and buy nasi goreng.
The scene becomes rame (crowded & lively): more and more people come, some sit and eat around the stall, money exchange and happy eating movements in smooth animation. The stall area gets busier with many customers.
End with a vibrant, crowded scene — lots of people enjoying nasi goreng around the popular stall, creating a busy and energetic atmosphere.
Animation style: very smooth fluid time-lapse, clean motion graphics, elements appearing and moving organically like the historical map animations in the source video. People move along stylized paths. Make it menarik & keren, lively (“rame”), with good energy but still elegant and premium documentary feel. Calm yet busy visual storytelling.Color palette: earthy tones — warm browns, creamy beige parchment background, vibrant yet natural colors for food and people. Subtle cinematic lighting with soft shadows. No text overlays. No voiceover. Only subtle lively background sound implied.Duration: exactly 10 seconds. Cinematic quality, smooth 24fps animation.
Seedance 2.0 (@BytePlusGlobal) is LIVE inside Agent Opus & we're giving away free credits for you to try it out!
Using this new model, you'll notice the following upgrades to your Agent Opus videos:
🏃♀️ More believable and lifelike physics, for both objects and humans
⏱️ Better pacing and transitions, making your videos smooth and immersive
🤩 Jaw-dropping visuals, across almost every visual style. Plus more accurate text.
Your AI creative team. Now with the best video generation model in the world.
Available Now! RT + Comment "SD2" to grab some free credits to test it out, we'll DM 500 of you!
1 min of Seedance 2.0 Video costs around $10.
That’s why coming up with a solid prompt can save you a ton of cash on your video projects!
7 wild examples of how to use Timeline Prompting 🧵
1. Just one prompt to make a 4:20 music video
https://t.co/du5rzMxU7o
Rewatch this and count the tools it would've taken anywhere else.
Character lock. Product lock. Logo lock. Style lock. One prompt.
From Creative → Creator, for real.
First 100 to RT + comment "ADS" get DM'd credits to try it 👇