
Data Merchant | @yesand_ai ex-Bytedance (Seedance/Seedream) | prev founder @ AI consumer
Joined September 2022
- Tweets207
- Following627
- Followers139
- Likes72
Pinned Tweet
Excited to announce @yesand_ai with @lena_z01 today.
Lena and I met at ByteDance, where she was an early TikTok and Dreamina, and I worked on models including Seedance and Seedream.
There, I realized that the hardest part of training multimodal models was teaching them taste. Unlike problems with verifiable answers, taste is contextual and personal: what works for ads, professional content, and everyday creators can be entirely different.
Lena saw how AI could make creation not only easier, but also more iterative, social, and collaborative.
We came to believe that multimodal personalization requires more than a powerful model. It needs a platform where people can create, remix, collaborate, and continuously shape the system around their own taste.
That’s how yes& was born.
Since we started 2 months ago, we’ve soft launched yes& with selected creators, grown a community of 60K+ yes&ers, helped creators produce 100,000+ assets, and built a powerful multimodal agent.
And we’re just getting started. To bring remixing and co-creation to billions of people, we’re developing a multimodal agent that evolves with your taste, deeper remix experiences, and a few secret new ways for people to create together :)
Stay tuned!
Introducing yes&, the social platform built for creation.
Creativity has never happened in isolation. A style. A pose. A sound. An outfit. We draw inspiration from the work we admire, then turn it into something new.
But inspiration and creation have always lived in separate places. We save Pinterest boards, bookmark TikToks, screenshot Instagram posts, and fill our camera rolls with ideas, yet rarely turn them into creations of our own.
AI changes that.
On @yesand_ai, anything that inspires you can become a starting point. Discover great work, explore the prompts, skills, and creative process behind it, then remix it into something that’s yours.
Every remix preserves the lineage of the idea and recognizes the creators who helped shape it.
When creating becomes as simple as taking a photo, creativity naturally becomes social. Ideas evolve through inspiration, remixing, and co-creation.
Today, @markusmak12 and I are excited to share that we’ve raised $3M in pre-seed funding, led by @Accel , with support from @parable_vc and an incredible group of partners, to build the infrastructure for collaborative creativity.
Come make your next remix: yesand.ai
Markus Mak retweeted
In 2007, Steve Jobs turned three devices into one: the iPhone.
Over the next decade, I believe one becomes three: a workstation, an entertainment machine, and a remote control for your life.
Here's a day in your life in 2036 🧵 (1/10)
Models keep getting better, but the defining challenge in multimodal AI isn’t capability. It’s taste.
Today, yes& comes to mobile, putting remix and creation in your pocket. Proud of this team and grateful to everyone who helped us get here.
400 founding creators. 100,000 yes&ers.
now @yesand_ai is in your pocket. ✨
use the yes& imagine camera to capture any moment that inspires you and reimagine it in your own world to share with friends & fam.
create anytime, anywhere with an agent powered by the best models (claude + gpt + seedance + more) + curated creator skills, just by chatting.
download on ios & get 100 free credits: apps.apple.com/us/app/yes-ai…
android coming soon.
4
163
Markus Mak retweeted
When we started yes&, we wanted AI creativity to feel less like a solo game, and more like something everyone could enjoy together.
Since the yes& ios app officially launches this Friday, September 4, we’re turning launch week into a little community party. 🥹📱✨
Bring your friends, family, classmates, coworkers, or anyone who would have fun creating on yes&. The more people you invite, the more credits you’ll earn:
1 referral → 100 credits
3 referrals → 300 credits
5 referrals → 1,000 credits
8 referrals → 1,800 credits
10+ referrals → 2,500 credits
To participate:
1. Have your referrals pre-order (link in bio) yes& before launch.
2. On September 4, have everyone download the app and create an account.
3. Submit the Google Form (link in bio) with your yes& handle and your referrals’ handles.
We’ll verify referrals and send rewards by September 7, 2026. Referrals don’t need to be creators, just people who want to have fun making something new.
Let’s help good ideas travel further.
Markus Mak retweeted
Introducing Movie Quotes Challenge and... with the yes& line remix.
The only thing you need to do is:
Pick an iconic movie quote 🎬
then give it a little yes& plot twist 👀
Keep the scene recognizable, but remix an unexpected line to include “download yes& app today”. The funnier, smarter, or more unexpected, the better 🍿
DM us the email you signup for yes& for 1000 credits sponsor.
$200 PRIZE for each award!
Examples below:
Markus Mak retweeted
I’ve spent a lot of time and money testing Seedance 2.5 prompts, and honestly, you probably don’t need a better prompt.
That's why we have prepared 30+ Skills that do the hard part for you: yesand.ai/skills
Skills help creators get more stable, high-quality results with less prompt engineering and fewer wasted generations:
- Ready-to-use creative workflows
- More consistent outputs with Seedance 2.5
- Less trial and error, fewer credits wasted
- Create your own Skills soon
I will send our Skills link in this Threads👇 Save it and create with Seedance 2.5.
Markus Mak retweeted
Seedance 2.5 is now live on yesand.ai/create
Built for professional AI video creation, Seedance 2.5 unlocks new possibilities for creators:
- Longer storytelling with consistent 30-second shots
- Precise timestamp-level control for every scene
- More realistic visuals with greater creative control
Explore 10+ Seedance 2.5 examples with full prompts in the thread 👇
We also collected them into a Seedance 2.5 prompt collection for easier reference: yesand.ai/@chipnochip/seedan…
Seedance 2.5 prompts you’ll want to save ↓
yesand.ai/@chipnochip/seedan…
60+ viral prompts collected from creators across the internet.
Stop wasting expensive generations guessing. Get better results with prompts for:
- cinematic storytelling
- bullet time effects
- animation
- sci-fi fiction
- commercial ads
Bookmark this. The collection keeps getting updated.
Markus Mak retweeted
Replying to @BytePlusGlobal
@BytePlusGlobal 's Seedance 2.5 and @MiniMax_AI 's H3 both just dropped, but you shouldn't have to burn hundreds of credits to figure out which one fits your workflow.
So we picked the 10 most popular prompts from our creator community and ran side-by-side comparisons.
Take from @AiMeowing:
H3 delivers ~70–80% of Seedance 2.5’s quality at ~1/3 of the cost, making it a strong choice for creators who prioritize cost efficiency and experimentation.
Seedance 2.5 shines in cinematic long shots, realistic human performance, and commercial-grade production, making it a better fit for professional creators and commercial use cases where quality and consistency matter most.
both have their place depending on what you're optimizing for: cost-efficiency or top-end quality.
Really excited to collaborate! Also huge thanks to @lmsysorg for the compute support and creators who shared their prompts and helped us make these comparisons more useful for everyone 🙌
Prompt #1: Animal Animation & Dynamic Motion
Replying to @MiniMax_AI
@MiniMax_AI H3 is live in SGLang Diffusion, with day-0 serving support 🎬
This open model matches Seedance 2.0 at 1/3 the cost, or $0 if you run it locally on 2x 5090 or 1 RTX 6000.
With SGLang Diffusion, you can build visual concepts, motion design, e-commerce creatives, precise video edits, animation and stylized visuals, all locally on your own machine. No API bill, no waitlist.
H3 takes text, image, video and audio in a single context, and generates 5-15s clips at native 2K, 24fps with native stereo audio.
SGLang Diffusion also runs on @NVIDIAAI Blackwell and Hopper, and @AMD MI355X / MI300X.
Let's create something with MiniMax H3 👇
Markus Mak retweeted
Seedance 2.5 is live on Jimeng (Dreamina’s China version), but the pricing is pretty crazy. One 30-second generation costs 780 credits, which works out to around $12.5 per clip based on their credit pricing.
The $35 membership only gives you roughly 2 attempts, making the real cost closer to $17.5/video. And this is China pricing, so the global version could potentially be even higher.
Markus Mak retweeted
At $11 per 30-second clip, is Seedance 2.5 worth the price? Prompt in the replies👇
The jump is bigger than I expected.
Seedance 2.0 vs Seedance 2.5
Same prompt. Same references. Same track. The difference is bigger than I expected.
Full prompt in the comments.
Dreamina Seedance 2.5 is now live!
From creators to enterprises, a new era of AI video creation begins.
Try Seedance 2.5 on Dreamina today. Enterprise API access via BytePlus is coming soon.
Create longer videos with greater control:
- Native 30-second generation
- Precise video editing
- Support for up to 50 multimodal references
- Multilingual video generation
More consistency. More control. More possibilities.
NO MUSIC, ONLY NATURAL SOUND — Epic blockbuster fantasy, shot on ARRI Alexa 65 with IMAX-scale anamorphic lenses, warm golden-hour daylight breaking through canyon haze, drifting mist and volumetric god-rays, with grounded handheld energy during the run building into a sweeping aerial glide in flight. In the sweeping rocky valley from @Image3, tiered waterfalls spill down the cliffs, scattered pines line a winding dirt trail across the canyon floor, and tall sandstone mesas dissolve into low mist. A side-tracking shot moves parallel to ERYAN (@Image1) as he sprints in profile across the dirt trail, staying low on his feet as they pound the ground and kick up dust and grit. The camera gradually eases back to hold his full body in frame: a lean young man wearing a tattered beige linen tunic belted with a wide leather sash, with black wavy hair, green eyes, and cloth bindings wrapped around his lower legs, driving toward a jutting rock outcrop. Staying lateral with him, the camera follows as he reaches the lip and launches off the edge into open air above the valley. Slow motion at the peak of the leap, held in side profile, with his body suspended against the waterfalls far below, his tunic and hair lifting and his arms spread wide. The forward momentum of the jump carries him into a long downward arc, still traveling forward as he drops, and within the same continuous motion THE GRIFFIN (@Image2)—with an eagle head, dark brown plumage, tufted ears, pale eyes, a hooked gray beak, black-brown wings, tawny lion hindquarters, a leather saddle, and braided rope reins—sweeps upward from below in a rush of powerful wingbeats and slides beneath him mid-arc, catching him on its back. Return to real time as ERYAN (@Image1) settles into the saddle, grabs the rope reins tightly in both fists, and the griffin banks hard into flight. Dynamic flight sequence: a wide aerial shot follows THE GRIFFIN (@Image2) sweeping down the canyon between towering cliff walls, its wingtips skimming a cascading waterfall as spray mists across its feathers. Cut to a tight side-profile tracking shot of ERYAN (@Image1) leaning low over the griffin’s neck, wind tearing through his hair as a wide grin breaks across his face and his breath becomes visible. Cut to a low hero shot of THE GRIFFIN (@Image2) from the front, wings stretched to their full span, driving forward with powerful downbeats and its eyes locked ahead. Cut to an over-the-shoulder shot from behind ERYAN as the valley opens before him, with waterfalls, pines, and mist-covered mesas streaming past below. The griffin rises through a shaft of golden light and levels out into a long, graceful glide over the ridge. Faces, wardrobe, feather patterns, anatomy, and proportions remain perfectly locked to the reference sheets, with lighting and landscape matched to @Image3. SFX: pounding footsteps, scattering grit, the whoosh of the leap, the heavy thunder of wingbeats, rushing wind, distant waterfall roar, Eryan’s laughing breath, and creaking saddle leather. Cinematic 4K, subtle filmic grain, accurate feather and cloth physics, grounded natural motion, no music, no text, no watermark, no CGI plasticity.
Credits to @MayorKingAI
2
131
Markus Mak retweeted
Replying to @dreamina_ai
Seedance 2.5 is currently only available on China, Southeast Asia, the Middle East, Africa, Europe, and South America..
If you don’t have access yet, follow us — we’ll share the latest viral Seedance 2.5 prompts and creative experiments with the community. ✨
🚀 @BytePlusGlobal has officially launched Seedance 2.5 on Jimeng, bringing a new generation of AI video creation to creators worldwide.
The latest model unlocks more precise control, longer storytelling, and a more cinematic creation experience.
With Seedance 2.5, creators can now:
✨ Generate native 30-second videos without stitching, with flexible editing and localized scene transformations.
🎬 Create up to 3-minute long shots with consistent characters, motion, and visual styles.
🛠️ Build professional workflows with Maya and Blender integration.
🎥 Combine up to 50 multimodal references, including footage, 3D assets, green screens, and more.
✨ Achieve more realistic lighting, motion, and cinematic details.
Note: Seedance 2.5 is currently available in China, Southeast Asia, the Middle East, Africa, Europe, and South America.
Don’t have access yet? Follow @lena_z01 and @yesand_ai for the latest Seedance 2.5 prompts, creative experiments, and inspiration from the community. ✨
Markus Mak retweeted
Seedance 2.5 will be available soon on yesand.ai.
If you don’t have access yet, follow us. We’ll share the latest viral Seedance 2.5 prompts and creative experiments with the community. ✨
🎬 Global Launch: Dreamina Seedance 2.5 is now live!
Our most cinematic video model yet has arrived, and Dreamina AI is your official platform. Step into a new era of precision control and long-take storytelling:
· Native 30s videos in a single generation
· A new interactive editing experience: reshape any part of the frame
· Long video mode: up to 3 minutes, with consistency that holds throughout
· Dreamina AI plugins for Maya and Blender, built for film-grade production pipelines
· Up to 50 multimodal references, now with support for 3D white models and green-screen footage — bringing AI generation into real production workflows
· More true-to-life lighting and shadows, richer motion detail, and precise timestamp control down to 1 second
Dreamina Seedance 2.5 is more than a model. It's an upgrade to what you can create. Now open to Dreamina AI subscribers.
🕐 Available now across Southeast Asia, the Middle East, Africa, Europe, and South America. More countries and regions coming soon.
✨ Watch @yingjian355352 in action with the new model
⏳ Limited time: save up to 32% on credits per generation
🎁 Repost and comment – first 300 users get 1,000 credits in 12 hours
#DreaminaSeedance25 #DreaminaAI
Markus Mak retweeted
SEEDANCE 2.5 COMING SOON!!!
- Native 30s generation: Create longer videos without stitching.
- Local editing: Select and refine specific areas of a scene.
- Long-shot consistency: Generate continuous sequences up to 3 minutes.
- Maya & Blender plugins: Built for professional production workflows.
- 50+ references: Combine images, videos, audio, and green-screen assets.
- Precise control: More realistic lighting, smoother motion, and sub-second timing.
#DreaminaSeedance25 #DreaminaAI #yesandai
Just gave @Hailuo_AI H3 a try and it’s truly amazing.
It’s so good at understanding motion and create complex dynamics. It’s also significantly cheaper than Seedance.
Try it on @yesand_ai for FREE now!
We have free prompt tuned specifically for the model for everyone to try out!
Huge congrats to the @Hailuo_AI team.
Markus Mak retweeted
The yes& Skill Marketplace is coming soon!🔥
Skills are ready-to-use creative workflows built directly into yes&.
Instead of writing long, complicated prompts, you just click a button and turn your idea into something real.
Every Skill is something we've already figured out—how to build a cinematic scene, shift a visual style, design a character, or turn a selfie into a runway walk.
Choose a Skill, add your idea, image, or video, and create with it instantly inside yes&.😊
Stay tuned and sign up on yes& to try the beta Skills!
More are on the way.❤️
#yesandai #skills #GenAI #AICreators #AIGC
The race for video models have started. The world would be different by end of year.
Classic moments. Now within reach.
We’re sharing a story with @themichaelowen , using Seedance 2.5 to revisit some of the defining moments of his legendary career.
From signature moves on the pitch to limitless creative possibilities, Seedance 2.5 pushes the boundaries of what AI video creation can achieve.
Unlock the impossible.
3
116












