.Qwen has cooked really deep 🔥 Multi-Layer Decomposition is... here! This is so photoshop completely AI powered! QwenImage-Layered is an end-to-end diffusion model that decomposes a single RGB image into multiple semantically disentangled RGBA layers That means, you can have targeted editing with much more precision without troubling other layers / components!show more

We’re finally getting layers in AI images. The new... Qwen Image Layered LoRA allows you to decompose any image into layers - which means you can move, resize, or replace an object / background. This is Photoshop-grade editing, offered as an open source model 🤯show more

Canva is reinventing Photoshop from first principles (you can... now one-click separate an image into layers)show more

3.5 Soon: Up to 8+ Layers, 16 LLMs in... Parallel🪄 A fully parallel, multi-layered system with 8+ orchestration layers handling everything from prompt parsing and tool execution to code generation and live editing—all powered by 16+ LLMs running in sync for real-time, adaptive creation. ➡️v1: Single agent, single output ↕️v2: Multiple agents, single output 🔃v3: Single agent, multiple outputs 🔀v3.5: Multiple agents, multiple outputs — scalable, context-aware, and built for real-time builds🔨show more

Upcoming Live2D 5.4 will fix the longstanding annoyance with... Procreate PSD files. With new import PSD workflow you can automatically trim the layers! No more back and forth editing with Photoshop/CSP. It has options to selectively merge layers on import too 👀 #cubism54_alphashow more

Adobe Photoshop launched an "AI Assistant.” This is a... conversational editing feature that lets you edit photos using plain language.show more

Latest clip of the actuator. This is a single... layer. It works sort of like a stepper motor, but runs linearly. Next step is to add more layers. But first I have to fix an issue with friction. It’s an easy fix, but will require a new flex PCB order, which will take a week or so.show more

Landscapes with overhang. What is this magic? 👀 Mesh... Terrain in UE 5.8 is shaping up nicely! Really like that I can have sculpt layers that I can then move, rotate and resize. #UE5 #gamedevshow more

President Carter’s time on this earth is coming to... an end according to his grandson Jason Carter. What a great man. At 99 he has accomplished so much. With an election coming up let’s remember all he has done for voting rights. Jason Carter: "My grandfather is doing okay. He has been in hospice, as you know, for almost a year and a half now, and he really is, I think, coming to the end. I’ve said before, there’s a part of this faith journey that is so important to him, and there’s a part of that faith journey that you only can live at the very end and I think he has been there in that space."show more

The new model Extract Object by Bria is now... live on fal! - Isolates any object from an image with a single API call - Turns a natural-language prompt into a clean RGBA-PNG cutout - Outputs composite-ready results with no masks or manual editing requiredshow more

Selected as a best paper finalist at #CVPR2026: PixelDiT... from NVIDIA Research In most image generation models, a pretrained autoencoder compresses the image before any diffusion happens, causing quality loss that accumulates across the entire pipeline. PixelDiT, or Pixel Diffusion Transformers, removes this step entirely. It's a single-stage model that learns the diffusion process directly in pixel space, end-to-end.show more

Wait… why did nobody tell me AI-generated posters could... go back into an actual Photoshop workflow? Turns out GPT-6 Astra + Dreamina Seedance 2.5 is an actual pipeline. I generated a poster in Dreamina first, then sent it to GPT-6 Astra. Astra used Photoshop to break the image apart into separate layers, so I could finally adjust the background, typography, and individual elements instead of being stuck with one flat image. For designers, this feels like a missing step between AI generation and professional editing. And because Dreamina keeps the creation cost competitive, I can test multiple poster ideas before deciding which one deserves a full edit. This workflow is kind of a game changer for rapid design exploration. #Dreamina #DreaminaPartnershow more

The next generation of #PhotoshopAI is here. Learn more... about the latest features and capabilities in Photoshop (beta) and Photoshop, powered by #AdobeFirefly Image 3 Model. Questions? Let's dive in. 💙show more

The Hidden Language of Diffusion Models paper page: tackle... the challenge of understanding concept representations in text-to-image models by decomposing an input text prompt into a small set of interpretable elements. This is achieved by learning a pseudo-token that is a sparse weighted combination of tokens from the model's vocabulary, with the objective of reconstructing the images generated for the given concept. Applied over the state-of-the-art Stable Diffusion model, this decomposition reveals non-trivial and surprising structures in the representations of concepts. For example, we find that some concepts such as "a president" or "a composer" are dominated by specific instances (e.g., "Obama", "Biden") and their interpolations. Other concepts, such as "happiness" combine associated terms that can be concrete ("family", "laughter") or abstract ("friendship", "emotion"). In addition to peering into the inner workings of Stable Diffusion, our method also enables applications such as single-image decomposition to tokens, bias detection and mitigation, and semantic image manipulationshow more

Muse Image is now available on Meta Model API... and priced for production volumes at $0.01/image. It’s an agentic image model that reasons before it renders. Each call searches the web to refine the output through iterative passes and evaluates the prompt for precise elements like charts and QR codes. Text-to-image, single-image and multi-image editing, and multi-reference composition all live in one model, so there's no multi-step pipeline to stitch together. Start building →show more

Excited to introduce Diffusion Augmented Agents (DAAGs)✨. We give... an agent control of a diffusion model, so it can create its own *synthetic experience*.🪄 The result is a lifelong agent that can learn new reward detectors and policies, much more efficiently. Here's how. 👇show more

I honestly didn’t expect this part of the AI... design workflow to work this smoothly. Turns out GPT-6 Astra + Dreamina Seedance 2.5 is an actual pipeline. I started by creating a poster concept in Dreamina. The image looked finished, but I wanted to edit the individual elements instead of recreating everything. So I gave the poster to GPT-6 Astra and had it call Photoshop to separate the design into editable layers — background, text, objects, and visual elements all became independent pieces. This is the part that surprised me: AI doesn’t just help make the design anymore, it can help turn the final image back into a real design file. Dreamina makes exploring different poster concepts much easier with its competitive pricing, then Astra helps take them into the editing stage. #Dreamina #DreaminaPartnershow more