Seedance 2 vs Seedance 2 Mini - a full... comparison thread 🧵 I ran both models through 9 very different scenes. Sword & sandal epics, vampire seduction, kung fu, futuristic bars, J-horror and more. Left is Seedance 2. Right is Mini. How does the smaller model hold up? Judge for yourself ⬇️ 1. Giant vs Armyshow more

GPT Image 2 + Seedance 2.0 Prompt Share Mei... Lin's Elemental Kung Fu Performance Created on mitte.ai I'm experimenting with Laban right now. I think it helps make movements feel smoother and more expressive, but I still need to do more tests. For this one, I only added a small Laban section to the Seedance prompt. Laban is a movement analysis system that describes motion through weight, time, space and flow to shape expressive body language and performance. You can find the prompts below.show more

I've been testing the new Seedance 2.5 model, and... it's now available on CapCut. What I like most is that I can generate and edit AI videos in one place instead of switching between different tools. The workflow feels much more seamless, especially when refining longer projects. It also gives creators: → More controllable video generation & editing → Timestamp-based storyline control → Support for up to 50 references → Up to 90-second video generation (30s native + 2 extensions) → Improved multilingual performance Experience Seedance 2.5 on CapCut today: → Try it on the web: → Get the app: #CapCut #Seedance25 #CapCutai #CapCutDidThatshow more

seedance 2 is crazy... this model works completely different... than anything else out there i gave it a very vague prompt with a starting image and it handled all the b-rolls, voiceover, transitions - without me specifying any of that the way this works, it looks like AI ugc automation might actually be possible now if you build the right system around it still a lot to play around with but this is looking very promisingshow more

Dreamina Seedance 2.5 is almost here!🔥— today — while... US rollout begins August 7. Transitioning from "prompt-based guessing" to **"reference-driven creation"** — this provides the exact stellar upgrade creators have been waiting for. ✅ All of the Seedance family (2.5, 2.0, and future releases) operates at its lowest-ever tier ✅ Dreamina proves to be not just the perfect platform for Seedance 2.5 — it remains the most affordable way to run it, full-capacity, skipping any add-ons What makes it so remarkable? First video model to accept 50 multimodal references — drag in characters, scenes, reference shots, and tunes all in one go. Eliminate the nightmare of endless prompt writing. 🎬 30-second native clips — unfold complete stories, instead of mere fragments. You get 2 extensions ready in post-editing, plus a robust ultra-long mode extending up to 3 minutes. ✂️ Professional editing— powerful 3D white model preview, integrated green screen workflow, alongside Blender/Maya plugin support. 🌏 10+ languages — making sure lip-sync and subtitles align perfectly. It means zero translation tools needed. Dreamina Seedance 2.5 goes live globally first on Dreamina — undoubtedly the 2026 premier AI video model for creators. Coming soon. Create alongside Seedance 2.0 today and master the ultimate workflow! #dreamina #dreaminapartner #seedance #dreaminaseedance25show more

This looks like a mid-five-figure luxury campaign shoot, but... I actually just put it together for about $0.02 per second using Pippit and the new Seedance 2.0 Mini model. Most marketing teams treat every asset like a massive production task, which is why they run out of budget so fast. I’ve been testing the Marketing Shortcuts on Pippit to see if I could skip the studio entirely and go straight to a Narrative Ad format. The reason Seedance 2.0 Mini is actually useful here is the speed. It lets you take one product shot and turn it into a story-driven ad in a few seconds. This kind of Narrative Ad usually takes weeks to produce, but this workflow makes it easier to test different plots and iterate without the usual production headaches. It’s basically moving from a text prompt to publishable content without needing the massive budget. There is a limited-time deal running right now if you want to try the workflow yourself. #PippitAI #Seedancemini #PippitPartner #AIads Pippitofficialshow more

not sure why nobody is talking about this but... Google Omni is insane at video editing Original Video (left) vs Omni Edited Video (right) everyone is comparing it to Seedance and missing the point completely. Seedance is for generating videos from scratch. Google Omni is for editing videos that already exist. which are two completely different use cases this is like when Nano Banana 1 first came out and nobody realized how big it was going to be. this is the first AI that can actually properly edit videos.. i've generated a few hundred videos with this model and it can do literally any type of edit you can think of. changing voices, swapping characters, removing watermarks, adding captions, transitions, pop ups, whatever. if you can describe the edit you want it can do it this completely crushes every other model on the market when it comes to video editing. nothing else even comes close right now and this is just the flash model. imagine what the pro version is going to be able to do when it drops in a couple months this should have way more hype than it's getting..show more

sora 2 is unmatched for AI UGC right now,... but VEO 3.1 just unlocked something massive for other AI ads... VEO 3.1 (left) vs SORA 2 (right) i've spent the entire day testing every angle of the new VEO 3.1 model and found some crazy use cases nobody's talking about yet the biggest win is that character consistency is finally SOLVED i put together a complete step-by-step guide including: - when to use VEO 3.1 vs SORA 2 (most people get this wrong) - the specific ad types where VEO 3.1 absolutely destroys sora - how to leverage character consistency to scale your creative output 10x RT + reply 'VEO' and i'll send you the full guide (must follow so i can dm)show more

Wait? Is this Seedance 2 Mini? The mystery Seedance... 2 model IS HERE! No wait this time. About 55% of the cost of the 2.0 Fast is about 75% Quality wise they say to expect Fast level output and that seems fair? Thoughts? Left is Seedance 2 Mini Right is Seedance 2.0 Full Prompt Image To Video Use the uploaded images as identity, costume, and lighting reference. Same naturally confident charismatic age 25 woman throughout performing a sold-out arena concert. Real concert documentary feel, handheld camera energy, practical stage lighting only. gritty, real, fun, clean editing, english language high energy modern concert performance 0: 00–0:01 — Open tight on her face mid-performance, eyes bright, genuine laugh breaking through a lyric, hair catching stage light. Crowd noise swells under faint mic hum. 0: 01–0:06 — She steps forward to the edge of the stage, singing into the mic with playful energy, she frowns, sad "Wait! Is this Seedance 2 Mini?" and then smiles and laughs free hand reaching out toward the crowd, fingers brushing toward raised phones and hands. The crowd repeats the lyric back to her as she laughs. Warm stage lights and lens flares in the background, slight handheld camera sway following her movement. 0: 06–0:09 — Wide shot from a low angle near the crowd barrier — she's framed against haze and colored stage lights, band visible in soft focus behind her (guitarist stage left, keyboard player stage right). She throws her free arm out wide, laughing between lines, hair whipping slightly as she turns. 0: 10–0:12 — Cut to a closer three-quarter shot — she playfully points the mic toward the crowd for a sing-along moment, grinning, eyes scanning the audience with real warmth and connection. Visible sweat sheen, natural skin texture, slight camera shake as if shot from the pit. — Final beat: close-up, she looks directly into the lens with a bright, genuine smile Camera: handheld documentary-style movement throughout, natural focus pulls, no perfectly smooth gimbal shots, slight shake and imperfection consistent with a real concert film crew. Practical stage lighting only — no CGI glow, no artificial bloom, no glossy skin, visible natural texture and sweat under hot lights. Audio: live arena ambience — crowd roar, cheering, phone-camera flash pops, her voice carrying clearly over a full live band mix (electric guitar, keys, drums, bass). No studio polish — natural live-mix dynamics, slight room reverb. No on-screen text, no logos, no subtitles, no watermarks, no identity drift, no extra performers beyond the band already in frame, no slideshow stillness, no overly smooth or glossy rendering, no jarring cuts, no akward moments, no jerky moves, no duplicates, no clonesshow more

Beauty ads just changed forever. Free Claude Opus 4.8... + GPT Image 2 + Seedance 2.0 workflow to spin up 100s of video ads. No studio, no model, no macro lens, no shoot day. Here's what nobody in beauty marketing wants to say out loud. That glossy lip shot. The droplet hitting the surface in slow motion. The whip-pan into the next scene. The crystalline product splash. All the stuff that used to need a real set, a real camera op, and a full shoot day. You can generate every frame of it from a text prompt now, and stitch it into a finished ad before your coffee goes cold. The workflow is almost stupidly simple: → Tell Claude Opus 4.8 the beauty shot you want (dewy skin macro, gloss-on-lips contact, ripple transition, the works) → Claude turns it into a shot-by-shot storyboard plus a prompt for every frame → GPT Image 2 generates the photoreal stills, frame by frame → Seedance 2.0 animates each one into a clip with that buttery slow-mo glide → You drop the clips into HeyOz and assemble the full ad in one place The real unlock is volume. This isn't one hero video. Once the workflow is dialed, you spin up hundreds of variations. Different shades, different models, different hooks, different transitions. The exact creative volume Meta rewards, minus the production cost that used to make it impossible. Old way: one shoot, one look, $10k+, weeks of waiting. New way: a hundred angles, any look, a few dollars each, same afternoon. I wrote up the entire workflow. The Claude storyboard prompt, the GPT Image 2 frame prompts, the Seedance motion settings, the full assembly flow. Completely free, no email gate. Want it? Comment "GLOSS" and I'll send it straight over. (make sure you're following so it can actually reach you)show more

HOLY MOLY running a 35B model locally on a... MacBook shouldn’t be THIS FAST 🤯 Spent my weekend in atomic.chat testing Qwen 35B vs. Qwen 27B on my local machine. I had them generate a fully animated HTML/Canvas car mini-game (demo below), ... and both models breezed through the physics and parallax scrolling without a hitch! The secret sauce here is the Atomic Chat app. Because it's perfectly optimized for Mac and uses Google's new TurboQuant under the hood, you can run heavy open-source models flawlessly while keeping top-tier output quality 👊 Other perks: → ZERO setup required → Access 1,000+ models completely free → 100% offline and private → Zero API limits ... and MUCH more! I dropped the prompt I used in the 🧵↓ Spin it up locally and let me know what you get!show more

MiniMax is the James Bond of AI agents. It... uses the world's first open-weight model (MiniMax-M1), and it squeezes every bit of power from it. The agent takes a prompt and does more than any other agent in the market right now: 1. It can do Deep Research 2. It can write code 3. It can design web pages 4. It can build 3D models I built 5 different experiences using MiniMax and recorded them for you:show more

Claude + GPT Image 2 + seedance + Meta... ads MCP Replaced my 10k/month performance marketing agency Here's the exact stack (and how it works): Step 1: Research Feed Claude your product URL, your competitors' URLs, and your top-performing ad angles. It builds your full brand brief + competitor intelligence in minutes. No agency strategist needed. Step 2: Static ads in seconds Claude writes image generation prompts based on your brief. Those prompts go straight into GPT Image 2. Out comes scroll-stopping creative. Batched. On-brand. No designer. Step 3: Video ads that convert Claude writes video prompts. Those go into Seedance 2.0. UGC-style videos. AI actor formats. Product showcases. All generated, not filmed. (Both GPT Image 2 + Seedance are live on HeyOz right now.) Step 4: Publish + optimize on autopilot Connect Claude to Meta Ads MCP. It publishes your creatives, monitors performance, and keeps iterating. Your agency was charging you for this. This entire workflow is documented in a guide I put together, covering prompts, setup, and the exact MCP config. Why this matters: Most brands are still paying for slow, expensive creative production. The ones who figure this out in the next 90 days will have an unfair advantage. Don't be the last one to know. Comment "REPLACE" and I'll send it to you directly.show more

Claude + GPT Image 2 + Seedance + Meta... Ads MCP Just fired my $10k/month performance marketing agency. Here's the exact stack (and how it runs): Step 1: Research Hand Claude your product page, your competitors' pages, and your best ad angles. It spits out a full brand brief + competitor breakdown in minutes. No strategist. No $200/hour consultant. Step 2: Static ads in seconds Claude crafts image prompts from your brief. Drop those into GPT Image 2. You get scroll-stopping creative. Batched. On-brand. No Figma needed. Step 3: Video ads that convert Claude writes video prompts. Feed them into Seedance 2.0. UGC-style clips. AI actor formats. Product showcases. All generated. Zero filming. (Both GPT Image 2 + Seedance are live on HeyOz right now.) Step 4: Publish + optimize on autopilot Hook Claude into Meta Ads MCP. It pushes your creatives live, tracks performance, and keeps iterating. Your agency was billing you hourly for this exact thing. I documented the full workflow in a guide: prompts, setup, and the exact MCP config. Why this matters: Most brands are still bleeding money on slow, overpriced creative production. The ones who crack this in the next 90 days will own an unfair advantage. Don't be the brand that figures it out too late. Comment "REPLACE" and I'll DM it to you.show more

Seedance 2.0 + Claude Code is f*cking insane 🤯... I built a Claude skill that creates UGC ads on demand. One product + one prompt = the AI creator, the script, the scene-by-scene shot list, and the finished video. All inside Claude Code. Perfect for DTC brands and agencies who can't afford to keep paying $500-$1,500 per UGC video and waiting 2 weeks for revisions. This skill eliminates the entire loop: → Tell Claude the product, ad angle, and length → Skill writes the GPT Image 2.0 prompt to generate the AI creator from scratch → Skill writes every scene prompt, dialogue line, and delivery direction → Pipes it into Seedance 2.0 with character + product + voice locked → Speed up + caption in CapCut → Ship the ad in 20 minutes No more paying $11 per video on Arcads. No more 2-week revision cycles. No more PR boxes to creators who ghost you. What you get: → Perfect character consistency across every scene → Voice consistency that holds clip-to-clip → Real product fidelity using your actual product photo as a reference → Multi-scene day-in-life, testimonial, and action-shot formats out of the box Built 100% with a Claude skill + Seedance 2.0. I recorded a full step-by-step tutorial showing the exact workflow so you can build these AI UGC ads yourself. Want the full breakdown? > Like this post > Comment "UGC" And I'll send it over (must be following so I can DM)show more

i live on ranch, and it cost me less... than buying an apartment in california. the downside is isolation from city life. if that doesn't bother you, quality of life shoots up. you'll become obsessed with animals 😂 i have 2 mini cows, mini horses, poodles. must stop, but... learning to train them is too fun. i've included a video of my mini cow giving "hello friend" head nods to my new mini horse i'm also building a soundshed on the property with two hifi audio systems to incept my friends to fall in love with the hobby. over time, you also become interested in being off grid. think solar, starlink, rain catchment, cattle + chickens, herb + fruit + veggie garden. life slows down and you start to value building these skills—to self-sustain. going outside between Zoom calls and just looking at the trees and hearing wind rustle through them is so calming. this is how i grow up. shouldn't have done a full 15 years in the city in between. i've built a bunch of guest cabins, and friends can come stay for a couple weeks at a time. i put guitars + pianos + hifi in their cabins so they can feel creative next up is a giant golf cart racing course that traverses through the propertyshow more

Batch Normalization by hand ✍️ ~ 7 steps walkthrough... below Batch normalization is common practice for improving training and achieving faster convergence. It sounds simple. But it is often misunderstood. 🤔 Does batch normalization involve trainable parameters, tunable hyper-parameters, or both? 🤔 Is batch normalization applied to inputs, features, weights, biases, or outputs? 🤔 How is batch normalization different from layer normalization? So I drew and calculated one entirely by hand. Goal: normalize a mini-batch of 4 examples to mean 0 and variance 1, then let the network scale it back. = 1. Given = A mini-batch of 4 training examples, each with 3 features. = 2. Linear layer = Let us multiply by the weights and add the biases. Batch norm sits after this, which answers the second question: what gets normalized is features, not inputs, weights or biases. = 3. ReLU = We apply the activation, and -2 becomes 0. Negative values are suppressed before any statistic is taken. = 4. Batch statistics = Let us compute the sum, mean, variance and standard deviation, one row at a time. A row is a feature and the four columns are the four examples, so every number here measures one feature against the rest of the batch. That is the "batch" in batch normalization, and it is exactly what layer normalization does not do. The statistics are rounded to whole numbers, which is what keeps the rest of the page doable in pen. = 5. Shift to mean 0 = We subtract the mean, in green. The four values in each feature now average to zero. = 6. Scale to variance 1 = Let us divide by the standard deviation, in orange. Each feature now has variance one, whatever scale it arrived at. = 7. Scale and shift = We multiply by a linear transformation and pass the result on. The diagonal and the last column are trainable, so having just forced every feature to mean 0 and variance 1, we hand the network the means to undo it. The outputs: Mean of each feature = [2, 1, 2] Std dev of each feature = [1, 1, 2] To the next layer = [2, -2, 2, 0], [-3, 3, 6, -3], [2, 0, 1, 2] The answers: 🤔 Both. The scale and shift are trainable, the statistics are not. Epsilon and the momentum on the running statistics are the hyper-parameters, and one mini-batch by hand needs neither. 🤔 Features, after the linear layer, not inputs, weights or biases. 🤔 Batch norm measures across the batch, one feature at a time. Layer norm measures across the features, one example at a time. 💾 Save this post!show more

This happened in the Little League World Series in... Softball, Nevada vs. Northern California. The last inning, Nevada is losing 2-1 and the bases are loaded and there is 2 outs. 2 strikes on the batter, 0-2 and she hits a ground ball to the shortstop. The shortstop fields the ball but falls on her rear and her throw to first base is wide. Two runs score and Nevada goes up 3-2. But wait….the umpire called runner’s interference. After discussing it with the other umpires, the call stands and that is the final out. Game over. Runner’s interference is not reviewable. That’s one rule right there that needs to change. The ball reaches the shortstop BEFORE the runner does. I do not see runner’s interference. I feel bad for those girls. Don’t think they should have lost that way. You make the call with your own eyes.show more

Here's how to get 100% consistent product ads from... one seedance 2.0 generation. I did it all in a single chat using the Comfy MCP. The real control here comes from calling my existing workflows (shared below) instead of the agent improvising a pipeline. I directed the agent to call my ComfyUI workflow for cinematic product ads. I specified the close-up shot of the sprite animating, the bezel turn flipping the screen, the display changing to the time 10:04. Now for the consistent variations. The driving video does the heavy lifting but you need to get it right → depthanything v3 pass blended with canny edge lines to show the fine detail... it's why the tiny debossed logo is there → the initial sprite outline lived in those edge lines too, and every gen kept inheriting it. claude suggested a sam3 mask over the screen to hide it (s/o the agent) → with the screen masked, the new star sprite is just prompting: one gpt-image-2 still to generate a reference, one extra line in the seedance 2.0 prompt, and it animates oh and the whole process is a claude skill now.show more

Seedance 2.5 is LIVE on Higgsfield UNLIMITED for 33... days at zero credit cost. You'd be INSANE to waste this window: 1. Seedance 2.5 dropped on Higgsfield today 2. Unlimited generations for 33 days 3. Zero credit cost. Read that again. 4. No rationing. No credit anxiety. No choosing between experiments. 5. That constraint is the #1 reason people never master AI video 6. It just disappeared for a month 7. Generate 10 versions of every shot. Keep the winner. Delete the rest. 8. Up to 30 seconds of continuity in ONE pass 9. Up to 50 references per generation 10. Physics that actually behaves like physics 11. Advanced CGI + production-ready editing built in 12. The clip attached? That's what a single pass looks like now 13. 33 days is enough runway to build a full film 14. The $1M Higgsfield Global Film Festival is running right now 15. Unlimited practice + a $1M prize pool = the math does itself 16. In 33 days there will be two groups: people who mastered this and people who "meant to" Open Higgsfield tonight and generate until your ideas run out because for the next 33 days, your credits won’t. (clip attached: one single pass, untouched)show more

Imagine making 2D concept art for a game world... –pressing a button – and suddenly you can walk around an interactive 3D world. That's what Google DeepMind's new paper Genie 2 can do – simulate virtual worlds, including the consequences of any action (e.g. unlock door, jump, swim etc). Right now Genie 2 can generate consistent worlds for up to a minute. And this world model seems to generate larger 3D worlds than what World Labs showcased yesterday. Plus they're dynamic vs. static worlds – the foliage moves in the wind, the water ripples etc. Not quite ready for prime time, but promising on two fronts: 1. For game developers: enabling rapid prototyping of interactive experiences straight from concept art 2. For AI research: providing unlimited, diverse 3D environments for training and testing AI agents The race for building the biggest, baddest world model is very much on. Meanwhile, all I can think is "if only Stadia was still around!"show more