Analysis
The long version
Pieces spun out of the daily wire when one line deserves a thousand: what a tool actually guarantees, where a launch will bite you, and what a trend means for people who have to deliver work with it.
- Remove a Person From Video With AI: Why the Frame You Paint by Hand Decides the Whole Shot Akatz Labs' free H3 Person Remover workflow removes a person from a short clip by never letting the video model see them, so the result is decided by two human jobs, painting a clean first frame and…
- AI Storyboard From One Frame: The Free Next-Scene Add-On That Treats Your Prompt as a Cut The Next-Scene add-on for Qwen-Image 2.1 is useful because it was trained on the gap between consecutive film frames, so it reads a direction as a cut to the next shot rather than an edit, which…
- Google's SynthID Detector Is Now Free for Everyone. What That Means If You Make Images With AI Now that anyone can check an image, video or audio file for Google's invisible AI watermark for free, telling people how you made something is cheaper than being found out, but a clean result from…
- AI Video Actor Replacement That Keeps Your Shot and Your Soundtrack, and Makes You Approve Twice Before You Pay The useful part of TEIN's free Genjutsu workflow is less the character swap than its order of operations, which hides the performer from the video model, makes you approve a mask and then a draft…
- Iris-3B Is a Free Image Model Whose Makers Admit Their Big Idea Didn't Pay Off Iris-3B is worth a creator's attention less for its pictures than for its honesty, because a lab that publishes where its own idea failed hands you a map of which claims to trust, and the useful…
- AI Motion Graphics Work Better as Code. Write the Animation, Then Hand It to a Video Model. The reliable way to make motion graphics with AI is to have a language model write the animation as editable code, keep that code as the master file, and only then hand the render to a video model…
- Nano Banana 2.1 Halved the Price of an AI Image. Your References Got More Expensive. Nano Banana 2.1 makes consistent multi-reference images cheap enough to draft every frame at 1K and pay for 4K only on keepers, but the half-price headline applies to the picture, not the reference…
- One Photo, 72 Camera Positions: Building an AI Turnaround Sheet With the Qwen-Image-2.1 Multiple Angles Add-On The Multiple Angles add-on works because it treats camera position as a short fixed vocabulary learned from 3D renders, which makes it a reliable way to rough out front, side and back views of an…
- Kandinsky 6.0 Video: The Open AI Video Model That Makes Its Own Sound, Under a License You Can Actually Sell Kandinsky 6.0 Video matters less for its pictures than for its paperwork, because unlike the other open picture-plus-sound models it carries no revenue cap or territory clause, and the price you pay…
- AI Alpha Mattes Without a Green Screen: Pulling Hair, Smoke and Glass From Ordinary Footage With LTX-2.5 Alpha-Gen LTX-2.5 Alpha-Gen is the useful kind of AI tool because it hands back a matte you still own and grade rather than a finished frame, but it chooses the subject for you, so it belongs on single-subject…
- SCM Is a Free Mac App That Finds the Shot You Remember by Description, and Your Footage Never Leaves the Machine SCM moves AI footage search out of the editing app and onto the whole drive, for free and offline, which makes it the most useful kind of creative AI: one that gives an editor back the hour spent…
- Clean-Plate Cutouts With AI: How PlateExtract Turns Two Photos Into a Transparent PNG With Soft Edges PlateExtract gives the oldest trick in compositing, the clean-plate difference key, the judgment it always lacked on hair, glass and shadow, but the result still depends on shoot discipline, and its…
- PhotoCraft Is a Free Photoshop Rebuild an AI Agent Can Operate, and That Matters More Than Parity PhotoCraft will not replace Photoshop for most people this year, by its own makers' estimate, but it is the first layered, PSD-faithful editor built so an AI assistant can use every menu command a…
- Garments2Look: Dress a Whole Outfit in One AI Edit by Writing the Layering Order AI try-on fails on full outfits because nothing tells the model what sits on top of what, and Garments2Look fixes that with a numbered item list and a written layering order, which makes a whole-look…
- Real Pixel Art From an AI Video Model: Draw Big, Snap to the Grid, Lock the Palette AI video models fake pixel art because nothing forces them onto a grid or a fixed set of colors, and two new MiniMax H3 add-ons plus a three-command cleanup pass (shrink, one palette for the whole…
- LAION's Humaneness Voice Add-ons: 40 Emotions and 500 Voices, Each a One-Megabyte File LAION's 557 voice add-ons make a mood or a voice something you attach like a plug-in, and the 40 emotion files are the useful, low-risk part for creators, while the 500 voice-identity files arrive…
- ldraw-nova: Design a LEGO Model by Describing It to an AI Agent, Then Open It in Blender Ldraw-nova shows that an AI agent which writes an editable parts file, rather than generating a picture of bricks, gives designers something they can revise, render and price, but its own…
- Audio Sliders: Change the Mood of an AI Music Cue Without Rerolling It Audio Sliders turns AI music from a slot machine into an instrument by letting you move one quality of the same clip (mood, energy, ensemble) instead of rewriting the prompt, which matters most to…
- Ideogram 4.5 Precise Edit: The AI Image Editor That Hands Your Pixels Back Ideogram 4.5's real change is that its Precise Edit mode copies the parts of your image it judges unchanged straight back from your original, which makes chained AI edits behave like retouching…
- Comfy Agent: How to Build a ComfyUI Workflow by Describing It (and Why to Leave It on Ask) Comfy Agent removes the node-graph wall by building ComfyUI workflows from a plain description while you watch, but the useful skill is directing it like an assistant (say what to keep, approve each…
- Kling 4.0 Keyframes: Why the Storyboard Matters More Than the 30 Seconds Kling 4.0's headline is 30-second clips, but the change that alters how creators work is up to 10 keyframes per clip, which turns AI video from rerolling a prompt into directing from a storyboard,…
- Draft Your AI Fight Scene Before You Render It: A Two-Pass MiniMax H3 Workflow The most useful idea in the Wuxia Fight Workflow is not the fight choreography but the cheap low-resolution draft you can watch and cancel before the expensive detail pass, a draft-then-commit habit…
- Make a 360 VR Video With Sound From a Text Prompt, Then Watch It in a Headset A new add-on for MiniMax H3 turns a written scene into a look-around 360 video with sound for about two dollars, and the craft lies less in the generation than in writing for a viewer who can face…
- Eleven v4 Audio Tags: Write Your Voice Script Like a Director Eleven v4's real change for creators is that the script itself now carries the performance, so the people who get the best results will be the ones who write clear stage directions, and ElevenLabs'…
- How to Turn an AI Video Glitch Into a Reusable Effect: The CardSpin Recipe A single accidental clip, captioned honestly with timestamps and used for a half-hour top-up on an add-on that already works, is enough to turn a model's mistake into an effect you can apply to any…
- EditVoice Fixes a Wrong Word in Your Voiceover Without a Re-Record EditVoice matters for voiceover and podcast work because it lets the corrected line be a different length from the original, which is the thing that makes patched speech sound rushed, and its real…
- Your AI Image Editor Is Moving the Picture. Here Is How to Measure It Instruction-based image editors redraw the whole frame a few percent off its original position, which is why edit passes never composite cleanly, and the fix starts with a five-minute measurement…
- AnyBokeh Changes a Photo's Focus and Aperture After You Shot It AnyBokeh treats the blur already in your photograph as information about the lens rather than damage to be removed, which is why it can move the focus point and change the f-number without the…
- A 10 MB File Lets You Watch an AI Image Form, So You Can Kill a Bad One at Step Four Preview decoders are not new, but publishing the fifteen-minute recipe to train one yourself changes who has to wait for the next model to be supported.
- Your Local Music Model Is Not Broken. The Wrapper Around It Is. A music model that sang gibberish on a Mac turned out to be receiving a message in the wrong format, and the two-line fix is a pattern worth recognising because it fails silently and sounds like the…
- The Six-Step Image Model Is Real. The Default Way You'll Install It Throws Away a Third of It. A free hosted demo proves the six-step version of Qwen-Image-2.1 holds up against the forty-step original, but the standard way of adding it to ComfyUI discards a measurable chunk of the very thing…
- Google Shipped Six Creative Tools It Didn't Design. One of Them Hands You Separate Audio Stems. The six new Google Flow Tools matter less as products than as proof that describing the tool you need now beats bending your work to fit someone else's software, and the sound tool proves it by…
- How to Get a Speaker-Labelled Transcript From Two Models That Never Talk to Each Other The useful thing about NVIDIA's new speaker model is not its benchmark ranking but its size and its licence, and the pipeline it enables joins two separate models on nothing more than a shared clock.
- Ming-Image-0.1-Design-Layer Pulls a Flat Design Back Into Editable Layers The interesting half of this release is the model that takes a finished design apart rather than the one that makes a new one, and the MIT licence on it is what makes the output yours to ship.
- The Sora API Shuts Down Today. Your Finished Videos Survive. Your Workflow Doesn't. When a hosted video model retires, the footage you already made is the easy part to save and the repeatable process you built around it is the part nobody warns you about, so the useful response is…
- Qwen-Image-2.1 Will Hand You a Transparent PNG, But Only If You Say the Magic Sentence The official ComfyUI templates for Qwen-Image-2.1 can produce genuine transparent cutouts with no selection tool, but the sentence that switches transparency on is hidden inside a note in the…
- Train a Style Control With Six Sentences and Zero Images A published recipe trains a reusable style control from six pairs of sentences and no training pictures at all, which removes the dataset from the middle of custom style work and turns the style into…
- You Can Now Direct an AI Video Model With a Drawing The new control pack for MiniMax H3 adds three input types that let you steer a video model from a drawing instead of from footage you already shot, which moves it from a post tool to a…
- WorldCrafter Turns One Photograph Into a Space You Can Walk Through WorldCrafter replaces prompt adjectives with a written shot list of camera moves and remembers what it already drew, which is the real shift, but the word Fast in its name refers to step count and…
- How to Get a Second Camera Angle Out of Footage You Already Shot The new re-camera workflow is not prompt writing, it is a measuring pass on your own footage plus art direction on the parts the original camera never saw.
- Your Picture Model Is Not What Fills Your Graphics Card. The Prompt Reader Is. Two independent measurements published on the same weekend found that the model reading your prompt is the largest thing resident in a local generation pipeline, and shrinking that file costs nothing…
- Qwen-Image-2.1 Makes Transparent PNGs Without a Cutout Step. Then the Licence Shows Up. Qwen-Image-2.1 generates cutouts with a real transparency channel instead of making you key them out afterwards, which removes a step that has survived every previous generation of image tools, and…
- Someone Finally Tested Six Ways to Train an Image Add-On. Five of Them Load Nothing. Five of the six common formats for saving a trained image add-on are unreadable by the standard loader, which hands you the plain model without an error, so the first thing to check when a trained…
- Chain Three AI Video Shots Into One Take, and the Drift Fix Everyone Gets Backwards Chained AI video shots drift because each shot regenerates from the previous shot's own output, and the per-shot colour and brightness corrections most people reach for cannot fix it, because they…
- Your Music Model Trainer Saves a File Called best. Do Not Use It. The number a music style trainer optimises has almost nothing to do with whether the result sounds like the band, and two independent sources now say the file it labels best is usually the wrong one.
- FLUX.2 Klein Draws in One Pass Now. The Free File That Did It Is 735 MB. The most useful image release of the week is an add-on rather than a model, and the reason it matters to a working creative is not the speed but the licence attached to it.
- VDN-H3 Makes Fourteen Seconds of Video in Nine. Then the Licence Tells You Where You Can't Run It. Video generation has crossed playback speed, which changes the creative loop from submit-and-wait to look-and-revise, but the fast open version carries a licence that excludes most of the people who…
- Your LTX-2.5 Download Is Only a Third of the Bill The compressed LTX-2.5 video file everyone links to is one of four pieces you need, and the piece nobody mentions is the same size again, which is why sizing the download by your card still runs you…
- Linum Threw Away the Compressor Inside Their Image Model. The Detail Got Worse First. Removing the compression stage from an image model made fine detail worse, and the fix was to split the model into one half that plans the composition and another that renders it.
- Ideogram 4 Does Not Want Your Sentence. It Wants a Layout Spec. Ideogram 4 was trained only on structured captions with coordinates and hex colours, so typing a sentence at it is not prompting badly, it is using the wrong interface entirely.
- A 28 MB File Separates the Light From the Paint in Any Photograph ShadeNet-2 pulls a relighting stack out of one photo on a CPU for free, and it works because its lighting layer is trained on nothing but the requirement that colour times light has to equal the…
- Meridian Re-Shoots Your Footage From a Camera That Was Never There Meridian's real contribution is a quarter-second preview that shows you the holes in your shot before you render it, and the thing standing between most editors and that preview is a licence…
- Krea 2 Cannot Edit Images. Here Is How People Are Teaching It To Anyway A reference picture is a more precise instruction than any sentence, and the new Krea 2 edit path lets you teach the model one specific edit from a folder of before-and-after pairs, with three silent…
- The MiniMax H3 Three-Step Adapter Everyone Is Downloading, and the Part That Got Left Behind The three-step TaoMate adapter really does make MiniMax H3 fast on one card, but the streaming runtime it was built for is the part worth wanting, and that part did not come along.
- Paint Six Flat Colours, Get Fire: The Drawing Is the Real Prompt In this kind of tool the painted control frames carry the art direction and the text prompt carries almost nothing, and the team published enough of the recipe that the method transfers to any effect…
- LTX 2.5 Can Now Edit Your Footage. Nine Tools Exist, and Seven Went Missing. LTX 2.5's add-on editing tools turned it into a practical way to change footage you already shot, and the tools that did not get carried over are what should decide whether you upgrade.
- LTX 2.5 Now Renders Ten Real Seconds on a 24 GB Card, and the File That Does It Advertises Its Own Weakness For local video the number that decides everything is whether the whole model fits on the card, which means a less faithful file that stays resident beats a more faithful one that has to be shuffled.
- Ten Hours on One GPU Buys You a ControlNet: The Anima Canny Recipe, Printed in Full The release worth copying is the hyperparameter list, not the safetensors file, because it turns a missing control type from a lab problem into a ten-hour errand.
- Change the Prompt Mid-Shot With Evoke, and Watch the One Number That Says When It Stopped Remembering Evoke can repaint a scene mid-rollout because the geometry lives outside the model in a point-cloud bank, and that same architecture prints a per-chunk coverage number that is the only reliable…
- AuK Makes the Sentence the API, and Its Own Docs Cannot Keep the Sentences Straight AuK has no task selector, so the instruction string is the entire API surface, which makes its inconsistent documentation a functional defect rather than a cosmetic one.
- YuE2 Writes the Sheet Music Before It Writes the Song YuE2's editable ABC score turns revision into an edit instead of a reroll, and that matters more than the benchmark headline it will be covered for.
- ID-V2V Lets Your Keyframe Be Wrong ID-V2V treats identity preservation as a relighting problem, which is why a mismatched stylized keyframe still works and why the workflow is reproducible from one video.
- Turn a Hosted Image Editor Into a Local LoRA You Own Renting a large hosted editing model for one afternoon to label your own images, then training a small local adapter on those pairs, converts a recurring per-image API bill into a fixed cost plus a…
- MiniMax H3 Runs on One AMD Radeon Now. Read the Benchmark File, Not the Headline. The AMD MiniMax H3 package is worth your attention less for its 16.66 percent speedup than for a benchmark file that prints its own missed target, its failed experiments, and a measured clipping…
- MiniMax H3 Runs on Two 16 GB Consumer Cards. Your System RAM Is the Part That Breaks. The two-GPU MiniMax H3 build is a host-memory document and a component-substitution document, and both of those decide whether it works for you long before VRAM does.
- MiniMax H3 on Apple Silicon: Every Shortcut in h3.c Ships With the Number It Cost Publishing the exchange rate for every speed shortcut, rather than only the win, is what turns an optimization document into a tool you can actually tune to your own quality floor.
- This Kokoro Core ML Conversion Hands You a Duration for Every Phoneme. That Is the Whole Subtitle Problem, Solved for Free. Splitting a TTS model at its duration predictor turns narration timing from a second forced-alignment pass into a free byproduct of synthesis, and the conversion that does it also publishes what a…
- Foundry Turns Stable Audio Into a Drum Machine. Its Two-Second Pads Sit Outside the Model's Own Minimum Length. Foundry wraps a diffusion model in an actual instrument, and the fixed operating point that makes it playable sits an order of magnitude outside the range the checkpoint's base config declares.
- There Is No Safe Setting for 4-Bit Quantization. There Is One Per Model. A converted checkpoint can load cleanly, dispatch natively, pass every structural check and still render a smear, so the only setting you can trust is the one you measured on your own model.
- AbsorbQuant Shipped 4-Bit FLUX and SDXL Weights. The Code to Run Them Does Not Exist. A four-bit checkpoint is a promise about a runtime you have to source separately, and AbsorbQuant is what happens when the weights ship and the runtime does not.
- VDN-H3 Renders Video Faster Than It Plays. The Row That Matters Runs on One GPU. VDN-H3's headline is an eight-GPU datacenter number, but the single-GPU row underneath it cuts an eight-step render from four and a half minutes to ninety seconds, and that is the change that reaches…
- Two People Taught a Video Model to Shoot VR for $12.50 Each. The Recipe Is One Sentence. A format LoRA does not teach a video model geometry, it teaches a frame layout bound to a trigger by one caption sentence repeated across every training clip, which is why fifty clips and twelve…
- Provcheck Signs Your ComfyUI Renders From Inside the Graph. Check Two Settings First. A provenance node that runs inside ComfyUI can attest the generation graph itself, which no downstream signer can do, but two of its defaults will hand a first-time user an unmarked file or someone…
- H3-World Turns a Keyboard Into a Prompt Compiler, and the Whole Thing Is 131 MB H3-World shows that action control in video models is now a text scheduling problem rather than an architecture problem, but the 131 MB adapter needs a 135 GB base model and a patched pipeline to…
- OpenShot 4.0 Runs Subject Masking on Your Laptop With No AI Account. The Model Licenses Are the Part Nobody Read. OpenShot 4.0's local subject masking is genuinely free of subscriptions and cloud uploads, but it is assembled from three upstream models under three different licenses, and only the project's own…
- MiniMax H3 Now Generates Video in Eight Steps Inside ComfyUI. The License Excludes the United States. Alibaba's official eight-step acceleration adapters for MiniMax H3 became loadable in ComfyUI five days after release, and the workflow is genuinely good, but the base model's community license names…
- Matrix-Game 3.5 Is Apache 2.0. The Depth Model It Cannot Run Without Is Not. Matrix-Game 3.5 is a genuinely useful open camera-controllable world model whose Apache 2.0 badge does not survive contact with its own quickstart, because the depth checkpoint both entrypoints…
- The Fix for AI Video That Forgets Is an Editable Text File HR Endless Sampler renders arbitrarily long MiniMax H3 video on a 16 GB card by running Gemma 4 as a continuity supervisor between chunks, and because the entire supervision policy ships as an…
- Text-to-MIDI Generation: How to Get a Score You Can Edit Instead of a Song You Cannot The commercial music generators still have no score underneath, so any MIDI they hand you is transcribed back out of audio they already rendered; a small set of open models emit the notes directly,…
- RenderFormer Renders Global Illumination With No Ray Tracing. The Weights You Can Download Are Not the Model in the Paper. RenderFormer is the only scene-generalizing neural renderer with weights you can download, but its released large checkpoint is not the architecture its own paper analyzes, and the fast numbers…
- SANA-Video 2.0 Renders 720p in Four Steps. The Apache 2.0 Badge Covers Less Than It Looks Like. SANA-Video 2.0's four-step preview is a real speed win under a genuinely permissive license, but that license covers only NVIDIA's transformer, and NVIDIA's own mirrors of the two files you need to…
- ControlFoley Adds Sound to Silent Video. The Mode Worth Your Time Is the One Nobody Demos. ControlFoley's reference-audio mode, which copies a sound's character without copying its rhythm, is the one capability that justifies the pipeline, and a free browser demo has existed since April,…
- FastMetal-QAD: Local Video Generation on a Mac, and Why the Biggest Model Is the Wrong Pick FastMetal-QAD makes five-second video generation practical on a 16GB Mac, and the workflow that works inverts two instincts: take the 5B over the 14B, and treat prompt caching as the main speed lever…
- Bonsai Image 4B Runs a FLUX-Class Model on an iPhone. The 95% Number Hides Where It Costs You. Bonsai Image 4B's ternary compression is real and honestly documented, but the headline 95% quality figure is an average across three benchmarks that conceals a 12% drop on the exact axis creators…
- Shrink Your LoRA Adapters by 80 Percent With an SVD Rank Resize Rank resizing turns oversized LoRA adapters into small ones with a documented, reproducible loss, and the fidelity numbers printed on model cards measure weight reconstruction rather than anything…
- ACE-Step 1.5 Runs a Music Model on Your Mac. Nobody Will Quantize the Audio Decoder, and It Turns Out to Be the Cheapest Part. Every quantization of ACE-Step 1.5 independently refuses to compress the audio decoder, and that decision is correct and nearly free, which means the multi-gigabyte local bundles are large for a much…