I believe that StoryDiffusion has the potential to be... Animatediff's complex motion sister-model! While AD is amazing for granular control, micro-motion and all kinds of abstract motion, it fails at complex realistic motion - walking, human movements, cars, etc. StoryDiffusion seems very promising for this + also has characteristics that will likely make the community very receptive to it and likely to extend its capabilities: 2) Appealing base-model results - likely to get the community excited - feels like significantly better realistic motion than AD 2) Modular - their approach is built with a number of components that can be combined and taken apart - it works by generating consistent images, then animating them together - each of these stages can likely be upgraded, used and influenced in different ways. 3) Flexible - they demonstrate a bunch of different conditioning options 4) Likely easy on RAM - it's based on SD 1.5 + authors mention precautions to reduce RAM consumption 5) Built to plug into the existing ecosystem - e.g. the fact that it works with the SD1.5 ecosystem will give it a huge advantage! While it's very early to say - e.g. the video model hasn't even been released yet! - it does seem very promising. With 9 months of SD1.5/Animatediff-esque progress improving every element of it, I can see an an extremely extended version of this beating Sora + running for a fraction of the compute resources on a consumer GPU. Together with Animatediff to drive the micro-motions and abstract stuff, it could produce be extraordinary/otherworldly/insane/beautiful stuff. This is the first open video model I've been excited about since Animatediff - though cautiously optimistic! Link here:show more

I am completely saddened to see what has happened... to Grok Imagine with it's latest update. It's a massive downgrade in motion and it prioritizes slow motion and random zooming in that is not even prompted. Prompt adherence seems to be suffering. If you can't see the night and day difference here, I don't know what else to say. Instead of just talking, look at my comparisons. I am very vocal and honest on here, this update is bad and it needs to be fixed. Grok Imagine used to showcase some of the most realistic and fluid motion, making it outperform a lot of other AI Video generators. To see it get butchered like this is extremely disappointing. Please fix this or roll back the changes. I am not the only one complaining here, just search for "grok imagine update" and read the replies for yourself. The community is not happy. This is not the direction it should be heading in. People in the community need to learn to also be honest and speak up, step outside of your bubble for once. I trust the devs see our complaints and make changes to what was once an incredibly powerful AI video generator.show more

Kling 2.6 Motion Capture is so good. It's a... huge leap forward. We've been able to do motion capture with AI for a while, but the quality bump finally made this approach useful. Here are the steps: - Get a reference video - record it or get a stock video - Grab the start frame of that video - Edit it using Nano Banana Pro. Ask to replace character and background. - Select the Kling 2.6 Motion Capture model in the video generator on Freepik (now Magnific) - Upload reference video + set the edited start frame - Video prompt can be simple e.g. "Gandalf dancing"show more

Is there any real "due diligence" done by the... 🅰️people? All of their points seem empty, vague, and very handwavy, at least that's the feeling I get. It seems to be confirmed when it comes down to the facts, they try to apply that same vague speculatory mindset they use regarding Starlink, arriving at a conclusion that always seems to be wrong. How many guesses have been propagated as truth? How many small differences have been exaggerated so large that they become the very core of their position? Probably a lot, because the trend I see is to take a kernel of truth and cover it with heavy layers of lies and speculation. I like what ASTS is doing, but the community makes it pretty hard to know what's actually significant, and the truth is, it's pretty hard to tell until both constellations are built and delivering data to customers. The issue is that most of them likely have a huge amount of money riding on the company, so they'll take anything and go with it solely for the comfort factor.show more

HTML Artifacts are a big part of how I... work with agents now. Artifacts can be more than just static files. When combined with agents, they can take action or help you take action. This unlocks all kinds of interesting ways to work with agents. This is clearly the future. Check out this writing and scheduler artifact I built in a few minutes. It uses a bit of HTML and JS. All the data is in markdown (Obsidian vaults), so the agent can access and modify it at any time. No DB needed. No sophisticated functionalities. The agent decides all that for me based on the skills, context, and memory it has access to. The best part about this simple stack is that all the important information stays with me. This has allowed me to build a recursive self-improving system and automations that can better tap into coding agents like Codex or Claude Code. I could have paid or built an entire app for scheduling posts, and there are so many of them out there. But I don't need to. I've realized a simple artifact does the job. And the simplicity of it is actually an advantage. Very little maintenance for very high returns on personalization, time, and efficiency. The other benefit of this is that I can add features as I please. That level of personalization feels magical, and we should all be pursuing more of it. All of this just keeps compounding. Of course, this example is just about writing. But I have similar artifacts for research, design, experimentation, evaluation, and so much more. And no, I didn't actually publish the post example I shared in the clip. It was just for demonstration purposes. I actually spend more time than this when writing together with agents. Lastly, having built my own agent orchestrator tool has made me realize that simplifying the tool stack is a superpower. If you are curious about how all this works, I will do a live session next week:show more

✨ Made a new mini feature on Photo AI:... [ Grab from 3d model ] So the problem is we're at that stage in time (typical for AI) where image-to-3d models are not good enough but are fun to play with, but we know they'll be good enough in 1-2 years With [ Make 3d model ] you already can turn any Photo AI pic into a 3d model but it still looks hyper clunky and deformed, but it works! One cool idea I had to make that more useful and made now: Let people make a 3d model then change the view of the it with the 3d viewer, then press [ o ] and it grabs a frame of the 3d That image you can then [ Remix ] (img2img), and it becomes a real photo again and that in turn you can then turn into a video again with [ Make video ] So that essentially gives you a fully freeform camera position control to take photos with One thing I need to fix is the background/skybox, I kinda need to take the original photo and remove the person and just get the background for the 3d model viewer, in this case it should be white, but it's a start!show more

This creative has pulled in a 33% hook rate... and 6x ROAS since we started running it on the client's TikTok ad account. Across the board it's worked extremely well. But why? It's not only relatable, but it's very straightforward We're showing a fit creator How many of us aspire to be in that good of shape? The idea is to show an aspiring fitness level And how someone who is busy can achieve it, even if they don't have a ton of free time We don't want to sell an intimidating amount of work that needs to be done Because no one wants to think about doing 2 hrs of exercise every day + dieting + supplements Workout WHILE you do other tasks Remove the pressure of going somewhere else to workout You can see there aren't a ton of shots. Kept it simple and just had different angles of the creator using the product. So what can you take away from all this? #1 - Give the viewer realistic goals they can achieve with the product (taking 10k steps, rather than "you'll lose 30lbs" - seems much more believable). #2 - Video doesn't have to be complex. If your product is very visual, just showcase the product being used. You don't need to get fancy with your edits. Let the product do the selling.show more

While I have premium I definitely want to do... a long post breaking down the main scene from this show that I obsess with. There's so much that I feel could be learned from it. Not just for expansion animators either. There's honestly a LOT that can be learned from how this show directed its expansion scenes that can be applied to even safe for work animations. Obviously yes, the expansion alone is really good. What makes it so good though is just the fact that there's things you pick up on that you likely don't even realize until you re-watch. I'm using this scene as an example as it's not AS good I would say, but it still has a lot going for it. One thing I've always loved from it that I want to use in my own animations someday is that the expansion sort of comes in waves as opposed to one consistent growth. In a way, it makes it feel more natural while also selling how tight the top is getting. It could have been accompanied by showing the knot getting tighter or smaller with each growth. It's a small part of the animation but just that one thing already adds another layer to appreciate. It's not like most expansion scenes where there's very little outside of just "growing" on its own. There's a bunch of little things that subtly improve it without being obnoxious. The first expansion scene has WAY more that I want to talk about honestly. Far more than this one has. It will probably be a really long post now that I think about it...show more

Gemini Omni's motion control is f*cking cracked i just... figured out how to turn 1 reference video into 50+ AI videos with the exact same movements... you have a video of someone eating, dancing, using a product, doing whatever complex motion you need. you feed it to Gemini Omni and it recreates that exact motion with a completely new AI character in literally one prompt i've tested this against Kling motion control and it's not even close. Kling falls apart the moment you try anything complex. eating scenes look weird, hand movements get mangled, anything multi-step breaks down completely. Gemini Omni handles all of it if you're still using kling motion control or paying creators to split test your videos, this replaces that entire workflow here's the thing though. you can't just prompt this out of the box. if you try to do motion transfer with default prompting you're going to get errors or the motion won't transfer properly. there's a specific prompting method that makes it work every time so i packaged up the whole system.. here's what you're getting: > full step by step video breakdown > how to find the best reference videos to use > the exact prompting system that allows for motion control transfer so you never get errors > the workflow for batching this out at scale (1 video → 50+) RT + reply "MOTION" and i'll send it over (must follow so i can dm)show more

✨ Grok Imagine Video is now live on Photo... AI It's hard to explain how impressive this is because of the speed that xAI got itself from literally nothing to the top of the leaderboards Six months ago Grok's video model was a joke, it wasn't even close to any of the video models out there, it looked cartoony and wasn't there and nobody took it seriously Now it's here and it's instantly the #1 video model out there now, it shot above Kling (which I used before on Photo AI and usually my favorite) and above Runway Gen 4.5 which was just launched 6 days ago! Mmore importantly it's now above xAI's biggest competitors' models: Google's Veo 3 and OpenAI's Sora 2 Being the best video model doesn't mean it's flawless: video is incredibly hard and actually because it looks so realistic now when it does make a mistakes it's even funnier One thing I noticed is that it still has a hard time with is voice, it does it well for a majority of the video but then slips up and produces unintelligible blabbering (which is really funny to hear) in both English (video 1: "it's where I find my naim", what's a "naim"?), and tested it in Portuguese too (video 3 at the end is unintelligible Portuguese I believe) In many ways Grok Imagine Video also reminds me of Sora, it has that weird but funny Sora conversation style But guys it's REALLY really really really close to getting perfect, we're so close to having full video productions being to be able done in AI, actually you already can if you just cut out the bad parts already Very exciting and I'm grateful I can experience thisshow more

GOOGLE 🔥: An upcoming Gemini Omni video model from... Google is expected to be much more advanced in video editing, capable of completing tasks like removing watermarks, replacing objects in the video, and more. It is also likely that Google will release 2 versions of this model, including a Pro variant. And I assume what we see isn't Pro? Anime sample 👀show more

So, my opinion on what the Antarctic (Antarctica) Anomaly... is that it's a type of frequency technology. It must be way more powerful than HAARP, as many have claimed it to be, because we would see these anomalies at other HAARP sites, and we don't, not like this. With that said, and I'm very much trying to avoid letting what I want it to be not play a part here, I think it is a technology that is being used either off the coast of Antarctica itself or Bouvet Island. A third possibility is an area just to the northwest of the island that looks odd. It's possible it is a sonar scan from a ship, but why in that remote location? It looks like an antenna set up or rows of something that is out of place. I also believe that the weather events and fires that have taken place in Africa could possibly have been because of this. Each time we saw the anomaly, it was followed by a destructive weather event in Africa. A weird connection to that is we have been told and warned of a very busy 2024 Atlantic hurricane season. This is in part because of the above-average Atlantic ocean temperatures, which is the fuel to Hurricanes. With all this info, it's possible to see how the Anomaly could be a frequency tech that can manipulate or create weather, And or WARM up the Ocean temps to purposely enhance the Hurricane season and Storm growth. Keep in mind that many of our hurricanes and many of the biggest hurricanes have come from the west coast of Africa and form over the Cape Verde islands before heading towards the Caribbean and the United States. This is all of course speculation, and I'm learning many new things every day, so this idea may morph over time as we learn more. In the end, it is very hard to ignore all these findings. #antarctica #anonaly #AntarcticaAnomaly #BouvetIslandshow more

Sora 2, “ family guy dark humor” My personal... thoughts: This is clearly the best AI video model for replicating animated shows. This truly gives credence to the fact that within the decade AI generated short films/shows is looking like a real possibility. My important caveats. Model trained only on video can get visually indistinguishable for most viewers most of the time. It can match texture, lighting, motion, and camera language so well that only careful inspection gives it away. However For sustained quality at the level of a full scene or an episode, video alone hits a ceiling IMO. Pure video likelihood drives the model toward what is frequent, not toward the rare timing and payoff choices that make the best jokes land. It has weak grasp of long arc causality, character memory, and joke structure. It also does not see intent, off screen context, or prosody unless you give it those signals. So you get something that looks right but drifts on beats that matter. I don’t know what the potential solution would be other than to have an AGI just animate the show for me. Any others ? Credit for the sora clip: figureshow more

Very pleasantly surprised to discover Cursor cloud agents can... playtest the godot game I built. See the (sped up) video below of the agent playtesting the game. As I was watching it play the game, I can see the agent slowly learn how the game works and familiarise with the game's UI. I also realised that the agent is a very 'safe' player, choosing to play very safely and retreating from battle if it foresees it can't defeat. Very interesting to see. I wonder if I could simulate different game playtester behaviours that mimic different types of real-world player archetypes. With agentic playtesting, this means that the agents are able to provide actual gameplay feedback and suggestions to improve the game, having played the game itself. This unlocks a whole lot of possibilities for AI-assisted game dev, since it closes the playtest loop. This feels like the future of recursive game development, where agents can now recursively build > playtest > improve the games they are working on. Thanks edwin for letting me know that these agents can actually playtest games, not just software! Very excited to dig deeper to see what I can do with these agents with computer access!show more

This guy has all the marks of a classic... patsy play. Mentally unstable, young, impressionable loner. Highschool classmates say he has an atrocious shot, got rejected from school gun club. Evidence that the way was laid for him to get onto that roof- ladder, lack of SS coverage, etc. A million questions about SS incompetence that sound an awful lot like sabotage from the inside. We don’t know what happened yet. But think back to JFK- They sold the story of a lone gunman. When in fact the true story was very likely an extremely complex, orchestrated operation with multiple shooters and multiple layers of obfuscation after the fact. There is no reason not to assume this is a similar event. The odds are so wildly against this kid pulling this off all on his own with no assistance or involvement at this point. And if there was any involvement- that implies it was likely a full on op by someone. So think about it- based on the evidence at this point, is it more likely this kid managed to do all this on his own, or that any of the shadowy forces in this world were willing to plan an op and pick out a patsy? Regardless of what you conclude- we don’t know the answers yet, keep your mind open. Don’t fuel hatred and division. Be kind to people.show more

I'd be careful in how you talk about this... subject. It is very easy, even if you are familiar with it, to spread misinformation. The Vril Droning process involves cloning and exposing the clone to a Vril parasite that takes over the central nervous system. It is very possible. It is said to be one of the darkest masonic secrets, and that they inhabit the hollow earth through the entrance in Antarctica. I find it really interesting, but it could just be something created to excuse behaviors. I have a video that explains how they actually use adrenochrome for nutrition. It is a theory but I think it has some ground to stand on. It is said that it is the reason for the floods/storms because they are waging war on them and they inhabit the deep underground bases. It is a subterranean war. It is a fun subject to talk about.show more

THE DEPTH MAP TRICK THAT FIXED DANCE ACCURACY IN... SEEDANCE 2.0 Feed the model a video of someone dancing and it tries to interpret everything- the person, the clothes, the lighting, the room, and somewhere in there, the movement. Feed it a depth map and there's nothing left to interpret but the motion. Most creators trying to transfer a dance to a character reference the source footage directly, then wonder why the choreography drifts. The problem isn't the model - it's that you handed it ten variables when you only wanted one. Here's the workflow 1. Lock the character reference in GPT Image 2 first -face, build, costume, so identity holds independently of whatever motion gets applied to it 2. Convert the source dance footage into a depth map instead of using the raw video -this strips out the original performer's appearance, clothing, and environment entirely 3. Feed the depth map as the motion reference and the character sheet as the identity reference- two separate inputs doing two separate jobs, not one input trying to do both 5. Let the depth map carry only spatial movement -the model receives body position and momentum with no competing information about who's moving or what they look like 6. Keep the character and motion inputs isolated throughout - the moment you mix appearance data into the motion reference, the model starts negotiating between two identities Why this works • Raw footage passes the model everything at once- performer, wardrobe, room, lighting -and the choreography competes with all of it for attention • A depth map is pure spatial information, so the only thing left to transfer is movement • Separating identity from motion means the character can stay locked while the dance stays accurate - normally you're trading one for the other • The accuracy gain isn't the model getting better, it's the model getting fewer decisions to make Use cases: ⁃ Dance and choreography transfer onto original characters ⁃ Motion capture-style workflows without motion capture ⁃ Any sequence where a specific movement needs to survive intact ⁃ Character showcase content built on existing performance footage The character sheet answers who's dancing. The depth map answers how - and keeping those two questions separate is the whole trick.show more

I built a clone of the Yeezy store with... Next.js. This was a fun challenge — the site has some smooth animations and feels very fast. But it was bothering me that I couldn't use the browser back button. Can we do better? So I rebuilt the site with v0 and Motion. Here's how it works: 1. When you click on a product, Motion is able to animate the original position of the product in the grid, to the zoomed in product detail page. 2. During this transition, we also shallow update the URL with the `/p/slug` route for the page. 3. If you press the back button in the navbar, or use the browser back button, or press escape — all options will take you back to the main product listing page. 4. If you reload the page while looking at a product, or someone sends you a link to a specific product, it still works! This is the best parts of a SPA and MPA mixed together. In the future, I can make this even better with View Transitions (I wasn't able to get the product animation just right, but if you can I'd love to see it!). I also took some creative liberties from the original design. The whole 1/2/3 size thing, where you needed to click the "?" to see SM/MD/LG was strange, so I just went directly to those sizes. Similarly, I prefered the more traditional style sheet/modal with the background color change, versus the full screen takeover. If you wanted to actually hook this up to Shopify now, you can swap the cart implementation with Next.js Commerce, which has all the APIs you need + optimistic writes 🔥 Should I make a video walking through the code?show more

After a few more hours, I think I've figured... out Opus 5. Opus 5 is trained to be more agentic than anything I've used. All Claude 5 models are like that. So what changes? The way to interact with Opus 5 or contextualize it won't work the same way as with other models. It loves exploring, so it doesn't need much guidance for it. Unique preferences, artifacts, and references compliment it well and enable cleaner and more effective exploration and execution. Now that it can explore more effectively on its own and understand intent better, the best thing to do is to get out of its way (e.g., it doesn't need examples of your preferences; a clear high-level description of it works best). It's truly agentic in that sense. A good first step to provide better context for Opus 5 is to distinguish between what's situational and what needs persistence. Regardless, persistent system prompts and CLAUDE.MD needs to stay lightweight. Remove memories and tool descriptions from these. CLAUDE.MD is also a great place to tap into progressive disclosure by linking command/skills to it. On the situational side, agent skills and auto-memory can leverage progressive disclosure and the improved ability of the model to use its external context/knowledge. Conflicting and unnecessary instructions, which are common at this layer (mainly to ensure reliability), are going to throw off this model easily. That's the biggest change I had to make. Simple, clean, and clear prompts and skills work best. I had to clean a lot of my skills and system prompts. The way I prompt remains the same (usually clear and well-scoped). MCP tool descriptions are also more descriptive and have been deduped from the system prompt. Anthropic released a guide on the new rules for context engineering, which was helpful here. I started to test the recommendations and created a little artifact with the things that worked along the way. This might feel like a lot of work. Believe me, it has been frustrating. But I think we can expect future frontier models to become more agentic and smarter at figuring out the right context/gaps. The best thing to do is to prepare for that now. Boris Cherny mentioned that Opus 5 is their least prompt-injectable model yet. I am not sure if that was something they intentionally trained for or if it emerged based on how it was trained, which is to be extremely agentic in nature and more direct in execution.show more