A blog of links related to computer animation and production technology
https://kiosk-library.com/get/ Key Features of Kiosk Library: 100% Local Secure: Your assets never leave your machine or local network. Fast and completely private. Deep DCC Integrations: Deep, native plugins for Blender, Houdini, Maya, and Cinema 4D. OpenPBR Detection (New in 2.0): Kiosk automatically detects texture variants (Base Color, Roughness, Normal, Metalness) and wires up the material…
https://www.youtube.com/@T-Photoworks How to Watch: Best Experience : Use a high-quality VR headset (e.g., Meta Quest 3, Vive Pro, Index) at maximum resolution to enjoy the full stereoscopic 3D effect and extreme 6K detail. Desktop : View with Chrome or Firefox for full 360 navigation using your mouse. Mobile : Use the YouTube app for an interactive panoramic view.
https://onyxofx.com/ What s new in v3.0 ⚡ ~2x FasterSame footage, half the processing time. 🧩 Unified Pipeline — all prompts in ONE sceneNo more switching between separate pipeline modes. Bbox, Point, Text, and Mask prompts now coexist in a single scene — mix and match freely. 🔢 Up to 16 Objects per NodeTrack up to 16 objects simultaneously in one node [ ]
https://kitbash3d.com/pages/kitbash-acquires-sketchfab-and-artstation-kitbash3d Whether you’re building games, VFX, film, television, commercials, visualization, or emerging media, our goal is to help you create better work, faster.We know that building worlds is only one part of your process, though. You also need places to find inspiration, share your work, and connect with the community. That’s…
https://www.foundry.com/products/nuke-family/hiero https://www.cgw.com/Press-Center/News/2026/DNEG-migrates-editorial-workflows-to-Foundry-s-H.aspx
https://www.bforartists.de/ Why use Bforartists, and not Blender? Because the work on Bforartists GUI is streamlined, cleaner, organized, customizable, has consistent colored iconography, left aligned text, and many more details that make day to day work easier. Bforartists also is 100% compatible with Blender. The files are transferable.Give it a whirl and see! You’ve got nothing to loose. For a…
https://www.shamelstudio.com/ https://stagerunner.net/after-nearly-40-years-movie-magic-has-a-challenger/
https://www.minimax.io/blog/minimax-h3 https://huggingface.co/MiniMaxAI/MiniMax-H3 A brief overview of H3 s pretraining paradigm Data and Tasks Text-to-image Text-to-video With jointly generated audio, all audio output is native stereo Native multi-shot modeling Text-to-audio No separation between voice, sound effects, and music — all jointly modeled Generalized reference and editing…
https://seed.bytedance.com/en/seedance2_5 https://higgsfield.ai/?fpr=dankieft fp_sid=sd25
https://ben3d.ca/blog/gaussian-splatting-for-threejs https://rawcdn.githack.com/mrdoob/three.js/5b8fcba16c8e0ab1e3745cd2c8185fe527998a36/examples/webgpu_gaussian_splatting.html
https://cavalry.studio/en/
https://www.maxon.net/en/autograph
https://www.caddis.app/ Timeline + Node Graph Animate on a layer timeline and build looks in a node graph — two views of the same composition, switch fluidly between them. GPU-Accelerated Engine A Rust + wgpu engine runs effects, blends, transforms, and fields on the GPU across Metal, Vulkan, and D3D12. 130+ Composable Nodes Shapes, fields, points, text, color, time, tracking, and [ ]
https://pixel-artistry.com/3DGenStudio https://github.com/visualbruno/3DGenStudio
https://www.flashforge.com/products/flashforge-creator-5-pro https://www.flashforge.com/products/flashforge-creator-5
https://www.prusa3d.com/en/product/indx-conversion-kit-8-toolhead/ https://www.prusa3d.com/p/bondtech-indx/
https://superhivemarket.com/products/truedepth?ref=835
Third-Party AI Services Risk Register IDRiskDescriptionPotential ImpactSuggested MitigationR-01Model availabilityThe provider may remove, replace, restrict, or deprecate models and model versions without sufficient notice.Production workflows may fail, and historical outputs may no longer be reproducible.Maintain an approved model inventory, monitor deprecation notices, archive model metadata, and…
For years, product lighting workflows have often depended on commercial tools like HDR Light Studio. Those tools are excellent, but not every artist, freelancer, student, or small studio can justify adding another paid package to their pipeline.That is why I’m excited about where LeoMoon LightStudio is heading. The latest versions bring a more complete product-lighting workflow directly inside…
https://huggingface.co/NemoStation/Marlin-2B Marlin is a 2B video VLM tuned for the two questions developers actually like ask their videos: what is happening, and when? It produces structured Scene + Event captions with second-precise timestamps, and resolves natural-language queries to span-grounded (start, end) ranges in the video. At 2B params, it is the strongest open model in its weight…
https://cglounge.studio/assets/glass Make CG look photographed in Nuke 14.1 to 17.0, on Windows, Linux and Mac. Nine lens modules from one node: distortion, defocus, flare, sensor, grain. Free tier and Nuke Indie build. Why it s different Real lens artifacts are not independent. Stop the aperture down and the bokeh, vignette, aberrations, and flare all shift together. Swap a spherical prime for […
Podman vs Docker https://podman.io/ https://medium.com/@omaisafzal225/understanding-podman-a-comprehensive-guide-to-dockers-alternative-678139e7aaeb RedHat Podman and Docker are both open-source tools designed to build, run, and manage Open Container Initiative (OCI) containers, but they use radically different architectural designs under the hood. While Docker relies on a central background…
https://github.com/LoHhhha/LATO.2 LATO.2 factorizes mesh generation into a vertex flow (V-Flow) that generates vertex positions under a controllable vertex count, and a topology flow (T-Flow) that predicts connectivity from the realized vertices. This decomposition unlocks: High-quality generation (image bottom left). Part-wise generation (image bottom middle). Topology-adaptive editing (image…
https://www.anthropic.com/news/claude-opus-5 Claude Opus 5 is available today. It’s a thoughtful and proactive model that comes close to the frontier intelligence of Claude Fable 5 at half the price. On coding and knowledge work evaluations like Frontier-Bench and GDPval-AA, Opus 5 is the new state-of-the-art, though it remains behind Mythos 5 on cybersecurity tasks. Opus 5 is designed to be used…
https://caveacademy.com/product/cave-community-membership/ CAVE Academy is looking to make some major changes.For CAVE v002, they are planning to wrap everything we do around the theme of Community and make all their offerings available for one small fee of £2/month.You can think of it as a Patreon-style approach where you ll get: All of their current and upcoming courses. Join their tech talk…
https://unid-video.github.io/ https://github.com/YihongSun/UniD Official PyTorch implementation for the ECCV 2026 paper: Unified Video Dense Prediction from Disjoint Data .
Introducing FLUX 3.One multi-modal model for Image, Video, Audio and Action-Prediction. Creations are truer to life in every kind of style.FLUX 3 Video is now available in early access (link below).Jointly trained in one unified architecture, our model can be extended to… pic.twitter.com/voQ5iUJJZY Black Forest Labs (@bfl_ai) July 23, 2026 Over the next few weeks and months, we’ll make the [ ]