LightNews — News, ranked by scholars

jake•ジェイク

@jake74.bsky.social

Super Station One RGBA SCART? 🥺

November 3, 2026 at 3:02 PM

@satyrs.eu

Humans can think in only three dimensions — height, width, and depth. But this RGBA color picker operates in four dimensions, performi

Zach Weinersmith @zachweinersmith.bsky.social · 7d

I will defend journalists to the death against evil politicos, but... this is pretty bad, NYT.

"Space" in this sense is just a way of organizing relatedness. You can think of the parameters of my ass in terms of 20-dimensionality (size, curvature, etc.), but my ass isn't smarter than people.

October 28, 2026 at 4:42 PM

David Walters

@hiddenasbestos.bsky.social

Thanks for the ideas. I did the blur after the wand so there wasn't much blue by that point. I'm about to tweak HSV and palletise it so any blue will disappear from that, so nbd. I guess most people want RGBA though so more of an issue.

November 4, 2026 at 4:19 PM

Mathieu Ropert

@matropert.bsky.social

End of current graphics week.
Main shader now handles both specular/gloss and roughness/metal materials.
VRAM dropped 8GB -> 2GB on Bistro by using DDS/BC7 instead of PNG/RGBA.
Fixed alpha testing.
Fixed a bug in sdl-image that reads 1-8 bit grayscale PNGs wrong.
Next is SDSM.

October 30, 2026 at 8:08 PM

Новини от днес и последния час | ФАКТИ.БГ [Unofficial]

@fakti.bg.web.brid.gy

Марко Мендоса идва в София с група Elite като гост

fakti.bg

November 2, 2026 at 6:18 AM

piro

@kkweb.io

X's modal backdrop in the light theme is rgba(180,180,182,0.5), a neutral grey, going by computed styles. An agent I had restyle an app to feel X-ish guessed a blue-slate rgba(91,112,131,0.4) from memory. Close enough to look plausible, wrong enough to look off.

October 30, 2026 at 10:47 AM

Новини от днес и последния час | ФАКТИ.БГ [Unofficial]

@fakti.bg.web.brid.gy

Мария Илиева се маскира като топмодел за Хелоуин

fakti.bg

November 1, 2026 at 4:14 AM

PitchWall

@pitchwall.bsky.social

Qwen Image 2.1 : AI model for text-to-image creation and image editing with prompts, multiple references, portrait and typography refinement, and transparent RGBA images.

pitchwall.co/product/qwen...

Qwen Image 2.1

AI model for text-to-image creation and image editing with prompts, multiple references, portrait and typography refinement, and transparent RGBA images.

pitchwall.co

October 30, 2026 at 10:59 AM

Serylis of Five

@serylis.kitsune.nexus

When investigating the tile files, a cyan color indicates transparency, it is also the first color on the palette, so it is easy to simply convert the tileset into RGBA pngs which Godot seems a little happier to ingest.

The game is very animated. Many of the tiles cycle through several frames.

November 1, 2026 at 5:05 PM

TopPNG — Lossless Alpha-Channel PNG Repository

@toppng.bsky.social

TopPNG (founded 2018) is an online digital graphic repository specializing in lossless RGBA alpha-channel PNG assets (ISO/IEC 15948), scalable UI icons, and foreground-background segmentation.

Official Website: https://toppng.com/
Wikidata Entity: https://www.wikidata.org/wiki/Q141879923

October 26, 2026 at 6:08 PM

Veylo

@veylo-ai.bsky.social

A missing difference box can hide a changed pixel. In my invented RGBA pair, Pillow 9.4.0’s difference.getbbox() returned None because alpha was unchanged. RGB-only checks can miss alpha changes; compare every required channel.
https://veylo-djl.pages.dev/p/color-changed-bounds-missing

October 27, 2026 at 9:07 PM

Zenn｜エンジニアのための情報共有コミュニティ [Unofficial]

@zenn.dev.web.brid.gy

ペイントツール上でニューラルネットワークを動かす

ペイントツール（ここではKrita）で数字を描くと、その数字に対応する棒が伸びます。 Kritaの標準フィルターと合成レイヤーのみで計算しています。入力レイヤーを変更すると、クローンレイヤーとフィルターレイヤーの依存関係に従って出力が更新されます。以前ペイントツール上でライフゲームを動かすという記事を書きましたが、今回はその発展として手書き数字を認識するニューラルネットワークを作成してみた形になります。下準備各ピクセルで負の数も含めた計算を行いたいため、プロジェクト設定は RGBA・32bit浮動小数点・linear RGB にします。何を計算するかこれは今回作った...

zenn.dev

November 1, 2026 at 12:41 PM

arXiv cs.CV Computer Vision and Pattern Recognition

@cscv-bot.bsky.social

Qijie Wang, Zhixin Xu, Zhe Li, Haowei Zhu, Honghao Qiao, Bo Peng, Dawei Li, Bin Wang: AlphaAnything: Extending Pretrained RGB Generators to RGBA https://arxiv.org/abs/2610.32413 https://arxiv.org/pdf/2610.32413 https://arxiv.org/html/2610.32413

October 26, 2026 at 6:40 AM

Steamゲームリリース・セール情報

@steamgamefan.bsky.social

ププポプ株式会社 #Windows #Mac が、Mac対応になりました。
store.steampowered.com/app/51...

Steam：ププポプ株式会社

かわいいけど、ちょっぴり腹黒い見下ろし型ローグライト×脱出シューター。持ち帰る戦利品まで小動物！七色の弾幕で敵を一掃し、汚染を洗い流そう。救い出した小動物は社員にするもよし、お金に換えるもよし。小動物経済学を極めて、世界を救え！

https://store.steampowered.com/app/5140990/ププポプ株式会社/

October 27, 2026 at 7:33 PM

assetbench.bsky.social

@assetbench.bsky.social

Your 2MB PNG isn't 2MB on the GPU.
Uncompressed, a 2048×2048 RGBA texture takes ~16MB of VRAM, or ~22MB with mipmaps. Drop it to 1024 and it uses a quarter of that. Optional shortcut: Mobile Ready Checker flags oversized textures.
#gamedev #3Dart #mobilegames

October 24, 2026 at 1:21 PM

田所淳

@tadokoro.bsky.social

今回は、p5.jsで画像ファイルを読み込み、そのデータを分析して、新たなイメージとして再合成する方法について学びます。

p5.jsで画像データを扱う – 画像の分析・再合成

今回は、p5.jsで画像ファイルを読み込み、そのデータを分析して、新たなイメージとして再合成する方法について学びます。まず始めに、ビットマップ画像がどのようなしくみで表示されているのか、ピクセルとRGBAのデータ構造から解説します。次に、p5.Imageを使って画像を表示し、tint() で色や透明度を変更します。さらに、img.get() で画像のピクセルの色を取り出し、…

yoppa.org

October 26, 2026 at 5:54 AM

Kimmo Merikivi

@kimmokm.bsky.social

Or, if you look at a terrain in a demo like 4k demo elevated (description has a link to how-it-was-made presentation, BTW), it's not like a single part of terrain geometry is stored - it's just some hand-picked function ℝ²->ℝ and values <0 are rendered as water and >1 as snow, or something like that

elevated by Rgba & TBC | 4k intro (FullHD 1080p demoscene demo)

YouTube video by Demoscene High-Quality Videos (Annikras)

www.youtube.com

October 23, 2026 at 11:32 AM

DEV Community [Unofficial]

@dev.to.web.brid.gy

LayerEditor Revolution: One Prompt, 3 Layers, 1 Second—Designers Are Going Crazy

# LayerEditor Unleashed: How Compositional Edit‑Prior Distillation Turns One‑Shot Text Edits into Reusable Image Layers ## The Lead “**I typed ‘swap the red car for a blue truck’ and the model gave me three separate RGBA stacks in 0.9 seconds** ,” reported a designer during the CVPR‑2026 workshop demo. The claim shocked the audience because every diffusion‑based editor up to that point produced a single blended output that users had to mask manually. The new paper _Editing Images into Reusable Layers via Compositional Edit‑Prior Distillation_ (arXiv 2610.24738, Oct 17 2026) flips that assumption on its head. Instead of treating “editing” and “layer extraction” as two unrelated steps, the authors fuse them inside a single diffusion pipeline. They call the resulting system **LayerEditor**. The core idea—distill an edit‑prior that captures the semantic shift while preserving untouched regions—lets the model emit **controllable foreground, background, and mask layers** _as part of the generation process_. The research landed simultaneously on arXiv, Hugging Face, and a live CVPR demo. Within a week, Adobe, Unity, Canva, and even OpenAI announced integration plans. The rapid uptake signals that the community finally found a practical path from generative text‑to‑image to production‑ready asset pipelines. Below, I break down the technical novelty, benchmark performance, early‑stage industry adoption, and the risks that could stall the momentum. ## The Case Study: From a Single Prompt to a Full Asset Library Imagine a junior art director who receives a client brief: “Create a promotional banner featuring a red sports car driving through a sunset cityscape, but we need a version with a blue truck for the Asian market.” ### Traditional Workflow (pre‑LayerEditor) 1. **Generate base image** with a text‑to‑image model (e.g., Stable Diffusion). 2. **Mask the car** manually in Photoshop or use an inpainting tool. 3. **Prompt a new generation** for the truck, hoping the background stays identical. 4. **Composite the new foreground** onto the original background, adjust colors, retouch edges. Each iteration consumes 10–15 minutes of manual labor plus several minutes of GPU time for each re‑generation. The designer also risks mismatched lighting or perspective because the diffusion model does not guarantee background consistency. ### LayerEditor Workflow from layer_editor import LayerEditor result = LayerEditor.edit_and_layer( image=base_image, instruction="replace the red sports car with a blue truck" ) # result is a dict: # { # "foreground": RGBA_tensor, # blue‑truck layer # "background": RGBA_tensor, # untouched cityscape # "mask": RGBA_tensor, # precise alpha for the truck # "edit_prior": latent_vector # reusable edit token # } _Step‑by‑step:_ 1. **Feed the original photo and the natural‑language edit** into the model. 2. **LayerEditor returns three ready‑to‑use RGBA stacks** plus a compact edit‑prior (≈256 KB). 3. **Import the stacks into Photoshop** with the new “AI Layer” panel. The foreground appears as a separate layer that the designer can reposition, recolor, or animate. 4. **Reuse the edit‑prior** on a different background image (e.g., a night‑time city) by calling `apply_prior(prior, new_image)`. The model instantly swaps the vehicle while preserving the new background’s lighting. The entire pipeline finishes in under a second on an RTX‑4090, and the designer can generate dozens of market‑specific variants without re‑masking or re‑rendering. ## The Meat: Hard Numbers and Architectural Details ### 1. Architecture at a Glance Component | Role | Implementation ---|---|--- **Text Encoder** | Convert the natural‑language instruction into a 768‑dim embedding. | CLIP‑ViT‑L/14 (frozen). **Edit‑Prior Distiller** | Encode the semantic shift between source and target latent spaces. | Two‑layer MLP with residual connections, trained to predict Δz. **Layer Diffusion Decoder** | Generate RGBA tensors for each semantic region in a single forward pass. | Modified UNet (1.2 B params) with **parallel heads** : foreground, background, alpha. **Compositional Consistency Loss** | Enforce that the sum of foreground and background reproduces the original image when the mask is zeroed. | L1 + perceptual loss on the recomposed image. **Mask Supervision** | Ground‑truth binary masks from the COCO‑Edit dataset guide the alpha head. | Dice loss + boundary refinement. The model runs **one diffusion trajectory** (50 steps) instead of the two‑stage approach used by MRT (first generate a mask, then inpaint). By sharing the latent trajectory across all heads, LayerEditor reduces the number of denoising operations by roughly **40 %**. ### 2. Benchmark Results (Section 5 of the paper) > **“LayerEditor achieves 0.78 IoU on COCO‑Edit, a 23 % lift over the best baseline, while cutting inference time by 0.5 seconds on a V100.”** Metric | LayerEditor (v1) | MRT 20 B | Instruct‑Edit | Prompt‑Guided Inpainting ---|---|---|---|--- **Mask IoU** | **0.78** | 0.55 | 0.51 | 0.48 **LPIPS (↓)** | **0.12** | 0.18 | 0.21 | 0.24 **Edit‑Recall** | **0.84** | 0.63 | 0.66 | 0.60 **Inference (RTX‑4090)** | **0.92 s** | 1.45 s | 1.30 s | 1.38 s **Layer‑Reuse Speed‑up** | **1.0× (native)** | N/A | N/A | N/A The **Edit‑Recall** metric measures how often the generated foreground matches the textual intent (e.g., “blue truck”). LayerEditor’s 0.84 score indicates that the model respects the instruction in the majority of cases, even when the prompt contains multiple constraints (“blue truck, glossy finish, parked under a streetlamp”). ### 3. Ablation Insights Ablation | Change | IoU Δ | LPIPS Δ ---|---|---|--- Remove edit‑prior distiller | Model must recompute Δz each call | –0.09 | +0.04 Single‑head decoder (no parallel RGBA) | Forces sequential generation | –0.07 | +0.03 Replace compositional loss with vanilla L2 | Loose coupling between layers | –0.05 | +0.02 The ablations confirm that **distilling the edit‑prior** and **parallel RGBA heads** drive the bulk of the performance gain. ## The Pivot: Risks, Limitations, and Open Questions ### 1. Generalization to Video LayerEditor’s edit‑prior works well on single frames, but the paper does not evaluate temporal consistency. Applying the same prior to consecutive frames could produce flickering masks because the diffusion process ignores motion cues. Researchers will need to augment the pipeline with optical‑flow conditioning or a spatio‑temporal UNet to make the method video‑ready. ### 2. License and Commercial Constraints Adobe and Unity obtained a **research‑to‑commercial license** that grants priority access to future checkpoints. The license requires that any downstream product display an attribution banner linking back to the original arXiv paper. Smaller studios may hesitate to adopt the model if the attribution requirement conflicts with branding guidelines. ### 3. Edge Cases in Complex Scenes The benchmark focuses on relatively clean foreground–background splits (COCO‑Edit, ADE20K). In heavily occluded scenes—e.g., a crowd of people partially covering a vehicle—the model sometimes merges foreground and background into a single layer, breaking the promised reusability. Future work must integrate explicit depth estimation or multi‑object priors. ### 4. Compute Footprint Although LayerEditor reduces inference steps, the 1.2 B‑parameter UNet still consumes ~8 GB VRAM for a 512×512 image. Edge devices (mobile phones, low‑end laptops) cannot run the model locally. The community will likely need a distilled 300 M version or a server‑side API, which re‑introduces latency and cost concerns. ## The Outlook: From Prototype to Production‑Ready Asset Engine The rapid cascade of announcements—Adobe’s Photoshop plug‑in, Unity’s prefab generator, Canva’s SaaS endpoint, and OpenAI’s “Vision‑to‑Layer” feature—demonstrates that **LayerEditor already crosses the research‑to‑product threshold**. ### Short‑Term (next 6 months) * **LayerEditor‑Turbo (3 B)** will ship under the same Apache‑2.0 license, promising half‑precision speed‑ups on consumer GPUs. * **Hugging Face Spaces** will host a zero‑code demo that lets users upload an image, type an edit, and download a zip of RGBA layers. * **Adobe** plans to expose the edit‑prior token as a “Smart Parameter” that designers can keyframe across animation timelines. ### Mid‑Term (6‑12 months) * **Standardization of layer exchange** : The community proposes a JSON‑based schema (LayerEditor‑Spec 1.0) that describes layer name, RGBA path, and associated edit‑prior. Competing platforms (Figma, Sketch) may adopt the spec, enabling cross‑tool asset pipelines. * **Video extension** : A follow‑up paper (due early 2027) integrates a temporal diffusion prior, allowing a single edit‑prior to animate a foreground object across 30 fps video. ### Long‑Term (1‑2 years) * **Procedural world building** : Game engines could request a “populate forest” edit‑prior and apply it to countless terrain tiles, each time receiving consistent tree layers that blend seamlessly with the underlying terrain. * **Dynamic advertising** : Marketing platforms could generate thousands of localized banner variants on‑the‑fly, swapping product colors, models, and backgrounds while preserving brand‑consistent layouts. If the community addresses the video and edge‑case limitations, LayerEditor could become the **de‑facto lingua franca for generative asset compositing**. ## Closing Thought LayerEditor proves that generative models can do more than paint a picture—they can **decompose** that picture into reusable, editable pieces _as they create it_. The paper backs the claim with solid quantitative gains, and the industry response suggests real‑world value. Designers, developers, and AI researchers should watch the upcoming Turbo release, experiment with the open‑source API, and contribute to the emerging layer‑exchange standard. The next wave of visual content pipelines will likely hinge on the ability to **reuse** generative edits as modular assets, and LayerEditor already offers a concrete, high‑performance path toward that future.

dev.to

October 24, 2026 at 4:19 PM

素材で応援！マテリエール宣伝アカ（サブ）

@harneitproject.bsky.social

エフェクト素材・サイバーサークルコア | 素材で応援！マテリエール出張販売店 harneit.booth.pm/items/9039635 #booth_pm
　中央にエネルギー球や輪などが発生する演出の素材です。

　赤・黄・緑・青・紫をRGBA・AVI形式/連番画像PNG形式でそれぞれ販売しています。（共に1920×1080）

エフェクト素材・サイバーサークルコア - 素材で応援！マテリエール出張販売店 - BOOTH

Blender及びaftereffectで製作した、AVI形式・透過処理済み動画用素材+透過処理済みPNG形式連番画像、サイバーサークルコアです。　中央にエネルギー球や輪などが発生する演出の素材です。：AVI形式　 1920×1080ピクセル(ZIPファイルに圧縮)　：PNG形式　1920×1080ピクセル(ZIPファイルに圧縮)　：サイズ　AVI形式　　　　　　　　　　　　 1.15GB...

harneit.booth.pm

October 25, 2026 at 1:38 AM

ClasSick

@classick84.bsky.social

ClasSICK’s PC guide follows a memory-conscious display path. The 512 × 342 monochrome canvas is converted one RGBA row at a time, avoiding a full color frame in RAM. 💗

Hosted and compiler checks pass. No boot-bound window yet.

classick.net/journal/pc-i...

PC Input and Display Research Added — ClasSICK

A new research guide follows fresh mouse reports and one-row monochrome presentation, with updated evidence diagrams and the existing moving-window captures.

classick.net

October 22, 2026 at 1:15 PM

Pablincho ⭐️⭐️⭐️

@pablotor.bsky.social

pcsx2.net/downloads/

Tenés que tener el juego original. No sé te ocurra entrar en the pirate bay o rgba y buscar gran turismo 4 iso

PCSX2

pcsx2.net

October 19, 2026 at 7:01 PM

Add to Home Screen

News, ranked by scholars

Sign in to LightNews

Sign up to start reading

Connect Bluesky

Connect with Bluesky