Can Adobe Firefly's "Edit" feature compete with Photoshop? Select... a region, describe the fix, keep the rest of the frame intact. That's the pitch. Here’s what we observed across 4 sessions and 8 targeted edits with real working creatives: >1 edit landed cleanly 🥇 >5 landed partial 🥈 >2 missed entirely ❌ Firefly understood the request almost every time, it just couldn't hold the rest of the image still while executing it. Avoiding drift is hard. In the partials, the target moved but something else broke. >A product lost prominence / focus >A shadow stayed broken >A new artifact appeared on the wall while the format crept closer to the brief Social was the hardest category. 0 clean wins across 4 attempts. With social content, crop, pose, and product placement ARE the deliverable, so any drift fails the job. TLDR: Firefly can edit like Photoshop, but avoiding drifts is the real challenge. I personally use this feature a lot, how have you solved for this ?show more

✨ Every week a new AI model comes out... and it suddenly makes my half broken features work a lot better Yesterday Seedream-4-Edit came out and it made my [ Hold product ] feature on Photo AI a lot better You can now go from: 🎁 Product photo -> 👱‍♀️ Talking video with your AI model while holding your product. In just a few minutes! Here's a photo I took from the weekly farm box we get in our kitchen, I set it as the product and then with Photo AI made it into a talking video where my trained AI model presents it It's not perfect, as the objects inside the farm box still move around a bit, but pretty close. If the product is more uniform (like lip gloss, a product box or a book) it does a pretty good job at keeping it exactly the same This "consistency" as they call it is quite important for actual real world use. Product sellers don't want to have an image or video of an AI model if the product doesn't look exactly the same as what they sell With that, I'm getting pretty close now and every week with every new model that comes out, a bit closer And it's interesting cause now I'm finally moving from B2C a bit more to B2B where businesses can use Photo AI more, designers and stores already use it for trying on clothes etc. but now they can generate content for real products! 😊 LIVE now on Photo AIshow 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

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

✨ 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

Everyone loves saying: "Why don't Indian brands make products... like this?" But they don't see the real problem. A well-wisher sent me a reel of a product that would be a huge hit in India. I checked the numbers. China factory price: $20 Landed cost in India: ~₹3,000 Retail price needed: ~₹6,000 Too expensive for most Indians. The funny part? If we Indianised it, we could probably sell it for ₹3,000 and still make it work. But there is one big wall. Moulds. Just the tooling would cost around $80,000. Before selling even one unit. That's the real challenge with making products in India. Not ideas or demand. But the cost and risk of building from scratch. So for now, we focus on smaller bets. Products where we can afford to take the risk. Still, it hurts seeing great ideas and not being able to build them all. How can we solve this?show more

Hi guys! Me and the programmers are working on... a little hotfix with some shit we didn't add in and to fix all the bugs once and for all! But this is where I need all of your help! If you have encountered a bug, post it here in the comments. (finished product of freeplay in video)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

I just dropped myself into a Taylor Swift-style music... video without writing a single prompt, timeline, or storyboard. I uploaded one photo and the song. That's it. Atlabs AI took over from there: • Built the character sheet • Planned the scenes • Generated the prompts • Synced every cut to the beat • Delivered a finished edit Most AI video tools promise automation, but the tradeoff is usually creative control. This was the opposite. The agents handled the production work while I focused on direction. Every scene, transition, framing choice, and creative decision stayed in my hands. When the edit was ready, I could jump in, swap shots, rework sequences, change the mood, and fine-tune the story. It felt less like using a tool and more like working with an AI production crew. We're moving beyond prompting. The next wave is directing autonomous creative workflows that understand the music, build the narrative, and still leave the final call to you. Character: ChatGPT Image Video: Seedance This is the most fun I've had making a music video in a long time.show more

✨ Grok's new Imagine video model also comes with... an Edit model We know edit models for images, you submit an image, write a prompt what to change, but this is the first time I've seen a proper edit model for video And it kinda works, not great yet though but it does something Here I had to remove the old name "Nomad List" in the video for my site First it said "Go nomad -> Nomad List", so I prompted it "remove the text Nomad List. do not change anything else", it didn't remove it but it replaced it with just "Go nomad" again, okay good enough Useful because otherwise I'd have to scour my backups for the original video in Final Cut Pro, and this is faster One thing you see is it changes the pattern on the door also, but that's okay for now if I fade it inshow more

As I sit here in DC this week, we... are closer to something I was not sure I would ever see. I have been working in this industry since 2015. For most of those years, the defining feature of crypto in Washington was not policy. It was the absence of it. A gray zone where serious people built serious things under a constant cloud, never quite sure which rules applied or whether the ground would move beneath them. This week the CLARITY Act sits on the Senate calendar. A federal framework for digital asset market structure, the thing this industry has wanted for the better part of a decade, is closer than it has ever been. It is not law yet, and there are real hurdles left. But the distance between where we stood a few years ago and where we are sitting today is hard to put into words. I keep thinking about the work that got us here. Over the past year I watched Chainlink move from outside these conversations to inside them. Sergey at the White House for the signing of the GENIUS Act. The Department of Commerce putting government economic data onchain. Meetings with the SEC that became real interpretive guidance. Conversations with the lawmakers now writing the rules. None of that happens by accident. It happens because people keep showing up, year after year, and make the case in rooms where it is not yet obvious. And there is something fitting in it. The entire premise of what we build is verification. Making truth provable. Removing the question of what is real. The work here in DC is the same thing in a different form. Trading a decade of ambiguity for something the industry has never actually had. We are not at the finish line. But sitting here, it is hard not to feel the weight of it. The gray zone is ending. What comes next is something this industry has never had. Clarity.show more

i quit my “dream” web3 job last month. remote.... good pay. chill life. from the outside, it looked perfect. on the inside, i was stuck in the same 9–5 loop, waiting for a paycheck instead of doing what i actually love. i’m 22. people say “you can take risks at any age” ~ but for me, it feels like now or never. this is only the second video i’ve ever made. the audio might be mid, the edit might be rough, but it’s real. here’s the video: watch it and roast / review / share what i can improve.show more

Magic Quill: A Free AI Image Editor That Feels... Like Magic This tool is incredibly useful and free to use now! It lets you select parts of an image and edit them with just a text prompt. Mostly I’ve gotten exactly what I needed on the first try! Here’s how to use it:show more

NanoBanana 2 just made your static ad agency obsolete.... And I just open sourced the entire tool. Drop your product page URL. It pulls your logos, product images, fonts, colors, and brand voice automatically. Builds a full brand guide for you. Then generates ad creatives at scale using nearly 4,000 high-performing ad templates across 8 niches. It dynamically matches the best templates to your brand and brief. Here's what makes it different: → Instant resizing Get any ad in 1x1, 4x5, 9x16 with one click. No regeneration. No broken text. → Highlight-to-edit See an issue? Highlight the area and tell it what to fix. → Multiple brand profiles Run different brands or segments from one tool. → Auto persona building from real customer reviews → Multiple QC loops on briefs and final assets Catches AI-isms before you do. → Upload your own templates or use ours Runs locally. Just needs your Claude and Google API keys. This is the lite version of what we use internally. You get the full finished tool AND the open source code to make it your own. Creatives still design the system, this handles iteration and scale. Want a copy to download? 1. Like this post 2. Comment "AI" Will DM you the tool along with a tutorial shortly after.show more

there is so much real data just sitting in... the open right now it's almost funny. four years of starlight on every star, a NASA archive that's been free for over a decade, detectors still recording the sky tonight, and barely anyone has a net pointed at any of it. so i pointed one. this is me pulling the planet data, the data loading is the boring part. the net i built to read it, the wall it hit, and what that taught me about where AI goes next, that's the full story, and it drops tonight. the data's public, the tools are free, the box fits on a desk. what's stopping you. you can just do things anon.show more

Aberdeen Press / Off-the-ball shape 🔴 Hard to tell... if the positioning of Aberdeen here was just due to an attack just ending, but: • If Cameron is high, then the rest of the team has to have a strategy to block the centre of the pitch. • Armstrong can see Gilmour is free, get across and leave your man to Keskinen - shut off one side of the pitch. • Milanovic can also this progressing. Interpret what is more dangerous, Gilmour driving through the centre or Gilmour passing back towards your man at fullback? • Shinnie is so deep, almost in the back line, spacing between the units makes it so easy for Gilmour to progress up the pitch.show more

Yep! We spent a 21 months building Werm, and... we’re genuinely proud of how we’ve done things. We’ll keep doing everything possible to build great products. What you see now is the result of countless iterations from the version shown in the below video. With just three people, building and scaling a multiplayer game has been incredibly challenging, even large studios struggle with this. The 21 months of development were necessary. We went through multiple rebuilds, learned a ton about launches, and built real relationships across the ecosystem. We stayed away from presales and token launches because the product wasn’t ready. Now we finally feel confident to give it a real shot. There’ll be bumps along the way, but unlike most crypto projects built on hype, we’re launching with an actual product and genuine intent to make it work. We believe we’re doing it the right way and that’s how we plan to keep going. The goal is for the community to trust that when we build, it’s 100% real, never a scam. More news to come about Werm!show more

Step 1 : input your char reference, poster and... your product into GPT Image 2 and then put the prompt : Use the woman on image 1 as the main subject. create a vertical poster ad inspired by the reference poster style. show the image 1 woman holding the kimchi jar with her left hand, while the right hand eating kimchi to her mouth. with framing wide lens, low angle from the reference poster. This step is where you lock the visual direction. Step 2 : take the generated image into Seedance 2.0 and convert it into motion. Set it to 1080p if your design includes a lot of typography, this helps preserve text clarity. You can also strengthen your prompt by adding keywords like: “dynamic motion design commercial advertisement” to push the result closer to a polished ad style. Important note : If your design contains heavy typography, expect some inconsistencies in text rendering. The best approach is to generate multiple variations and select the cleanest result. For this sample, I generated it 4 times before landing on the final version.show more

We were taught the derivative as a formula to... memorise. A definition to recite. A rule to apply. Something that "gives you the slope." But nobody told us what the formula was actually saying. Every symbol is a sentence. Every fraction is a question. Every limit is a story about getting closer and closer to something you can never quite touch. The top of the fraction? That's a change. A difference. A before and after. The bottom? That's how long you waited to see it. The limit? That's you, zooming in, refusing to settle for an approximation - chasing the truth all the way down to an interval so small it almost disappears. Put it all together, and you get the most honest question in calculus: How fast is something changing - right now, in this exact instant? Not on average. Not over a minute. Not eventually. Right now. That's it. That's the derivative. It's not a trick. It's not a rule. It's a beautifully precise way of asking a very human question: what's happening, in this moment? We spent years solving these. Maybe it's time we actually understood them.show more