Silhouette 2026 lands with fewer steps between “I need a clean matte” and “shot approved”, without taking the steering wheel away from artists. The release updates multiple ML-driven matting tools that can detect, segment, propagate, and refine, while still keeping the workflow artist-controlled.

The additions cluster around three pain points that never die in production: edge stability over time, tracking that survives real-world footage, and pipeline plumbing that does not explode when you scale beyond a single workstation. Silhouette 2026 touches all three, and it does it in a very node-graph way: new models, new nodes, and more data moving through the graph instead of getting stranded in side files.

AI matting that thinks in objects, not in one mask at a time

The AI toolset gets updates across five ML nodes, with a focus on scalable multi-object workflows. Face ML gets a new model plus new Nose and Neck matte options, a full-face matte option, and deeper integration with ML masking and compositing workflows. Depth Map ML gets a new model aimed at more detail and improved temporal consistency.

Mask ML adds multi-object workflow features, including object list management, foreground and background refinement tools, and per-object Cryptomatte data. Matte Assist ML adds intermediate frame caching, improved propagation performance across long shots, and multi-object Cryptomatte output. Matte Refine ML adds a new Video Matting model for improved temporal consistency along edges, and it preserves Cryptomatte data after refinement.

Be wary: running many ML masking nodes can load multiple custom models onto the GPU and fill VRAM quickly, so the multi-object approach inside a single Mask ML node matters for both speed and sanity.

If you live in the land of shallow depth of field, it is simple: keep your IDs, then soften your edges with the model that holds up over time. The Video Matting model option in Matte Refine ML is a temporal-consistency favourite in the training material.

Head Track ML and the 3D Scene node get real

Silhouette’s 3D Scene node now pushes further into 3D-aware shot work. It is powered by SynthEyes technology, and Silhouette 2026 adds a new workflow centrepiece: Head Track ML.

Head Track ML uses ML to automatically build and track a full 3D head mesh, preserving facial motion and expressions for face-aware effects. The ML model loads onto the user’s graphics card, detects the head, and then Silhouette creates and tracks an aligned and scaled 3D head mesh.

From there, the new Unwrap and Rewrap nodes connect 3D to 2D UV space for roto, paint, and beauty work, and a Render Depth node can generate depth maps from Head Track ML meshes for beauty work or downstream VFX pipelines.

The training walk-through frames the workflow as a practical alternative to the classic “stabilize a patch, paint, reapply motion, repeat until retirement” approach. The point is to unwrap the tracked head into a stable 2D space, do the detail work, then rewrap it back onto the moving performance. It even comes with a candy-wrapper analogy, because every 3D workflow deserves at least one metaphor before it hits the studio floor.

There’s limits: For example, Head Track ML does not detect relative distance between multiple heads, and suggests using an “All render” option in the Render Depth node if a depth map for all heads is still needed.

On the camera side, Refine Solve is designed to let artists improve a camera solve without reprocessing the entire solve. It supports fixing bad frames and smoothing problem areas by deleting erratic or unnecessary 3D features, aiming for more stable solves and faster cleanups.

Tracking upgrades that target the annoying bits of reality

Silhouette 2026 gives love to two tracking tasks that tend to chew time: point tracks that fall apart when anything gets in the way, and repetitive object tracks for faces and license plates.

Point Track ML updates the long-running point tracker workflow with ML assistance aimed at motion blur, occlusions, objects going off-screen, and changing reference patterns. It includes three accuracy settings and Viewer Stabilisation to validate and lock the track. This is not a guaranteed fix, but it increases the chance of success in those failure cases that always show up right before delivery.

Object Tracker detects and creates layers for object classes, including faces and license plates, to reduce setup time, and tracker types support occlusion matte input. In the tutorial flow, it can automatically generate new layers and shapes when new faces enter a shot during a forward track.

This feature that works best when you treat it like a fast first pass – the result may not be 100 per cent perfect, but perfect for fast turnaround work. You don’t get “final shapes”, but points where you can attach additional Tracking data, and modify what needs to be cleaned.

Paint tools that aim for fewer clicks and fewer regrets

Silhouette’s paint system gets new tools and workflow changes aimed at cleanup and beauty work. A new Healing Brush supports cleanup and retouching with expanded colour sampling from any input. Brush controls add blend modes and pressure-sensitive sizes. Blur, Clone, and Drag brushes get more natural and flexible behaviour. Clone workflow updates add continuous mode and auto-grade locking. Resize Paint introduces a resolution-independent workflow that allows working in a lower-resolution session, then rebuilding strokes accurately on higher-resolution media.

Resize Paint is a way to work quickly at low resolution and later rebuild exact stroke replicas at high resolution, which is basically a polite way of saying your workstation fans can stop auditioning for a jet engine while you block in cleanup.

Cryptomatte, data ports, and fewer matte files to babysit

Silhouette 2026 deepens Cryptomatte-centric workflows, and the important bit is that it treats mattes as data that should travel with the graph, not as files that should multiply in folders.

Pipeline changes include passing filtered Cryptomatte data as alpha through nodes via an Matte input, enabling objects and layers to act as matte sources. A new Cryptomatte Mixer node can combine multiple Cryptomatte streams into a single output. ML and AI tools support multi-object outputs with improved viewer-based selection tools to speed up scene isolation and matte management.

Beware the workflow trap: do not build one Mask ML and one Matte Assist ML node per object, because each node loads its own model to the GPU and VRAM fills fast. Instead, multiple objects can live inside a single Mask ML node, and Cryptomatte over the data port can move reference data to Matte Assist ML even when reference keyframes are scattered along the timeline.

For OFX plugin users, there is a limitation: Cryptomatte data cannot simply be routed to an output node and expected to appear directly in the host application, due to how OFX plugins work. The workflow is to export to the file system instead, using an Output Multi node for Cryptomatte-generating nodes.

Export details matter, too. Cryptomatte needs EXR for multi-channel properties and uses only lossless compression, and it warns against lossy formats such as DWAA, DWAB, or PXR24. That is a lot of words to say: keep your IDs clean, keep them in one sequence, and do not turn your matte export into a science project with ten folders named “final_final_3_forreal_v02”. Unless you enjoy that sort of thing. Some people collect stamps, after all.

Performance, stability, and the stuff you notice at 2 a.m.

Silhouette 2026 includes performance and playback improvements through ML node caching for several ML nodes, plus predictive playback via pre-fetching and batched render jobs. Playback controls add optimisation options, including adjustable job queue size, preload frames, and threading settings.

Daily workflow improvements include advanced node search with category, intent, and data-type filtering, a Favourites node, an improved naming system, a context-sensitive HUD, and a Safe Mode troubleshooting workflow to enhance stability in demanding environments.

This is the kind of feature that helps the person who inherits your comp at the worst possible time. If your node tree looks like it was assembled during an earthquake, you still have to deliver, so better search and safer startup modes are not flashy, but deeply production-friendly. Yes, you should still test new tools and innovations before use in production, especially when ML models and GPU caching sit in the critical path.

Pipeline automation and AI assistants, now with actual plumbing

The most pipeline-forward change is a built-in JSON-RPC server and an MCP server. The JSON-RPC server allows studios to drive Silhouette remotely, execute Python code, run script files, and control the application via JSON-RPC.

A Python Package Manager manages third-party Python packages inside a directory in Silhouette and stays isolated from the system Python. This is powerful, and it is also the kind of feature that deserves a boring rollout plan. Build guardrails, keep permissions sane, and do not let the intern’s chatbot become the new show supervisor. The intern already has enough power.

The MCP server allows direct calls from AI assistants, which can inspect projects, build node trees, edit shapes and keyframes, and render frames. “ChatGPT, explain what I did there!” is now a valid question that can be answered. Not truthfully or understandably, because … LLMs, but still.

What to watch to get productive fast

If you want a training rabbit hole, the Silhouette training and tutorial ecosystem lives in the video library and training hub on the BorisFX-site, spanning both quick tips and longer courses on all packages and levels of experience.

Pricing and availability

Silhouette is available as a standalone application and as a plugin, with subscription, upgrade, support, and permanent license options. Subscriptions start at $ 545 per year or $ 103 per month. Silhouette supports macOS, Windows, and Linux. Supported host applications include Adobe After Effects, Adobe Premiere, Foundry Nuke, Blackmagic Resolve and Fusion, and Autodesk Flame.

Customers with an active Silhouette subscription, Boris FX Suite subscription, or an active Silhouette upgrade and support plan receive the 2026.5 release directly as a update.


https://borisfx.com/products/silhouette/

The post Silhouette 2026 gets smarter roto and 3D heads first appeared on DIGITAL PRODUCTION and was written by Bela Beier.

For those who don’t know the tool: Beeble Background Remover is a Cloud roto and matte extractor for comps, now offering CorridorKey or MatAnyone before upload, so your key tests can happen before your pipeline meeting turns into a sequel.

What changed in Background Remover

Beeble‘s Background Remover now lets you choose between MatAnyone and CorridorKey before you upload footage. MatAnyone stays positioned as the general-purpose option. CorridorKey is positioned as the green screen option, aimed at cleaner edges and more accurate keying on chroma key shots. Background Remover runs only in the Cloud app and does not run in the desktop product.

The fastest way to try it without committing

CorridorKey has the kind of momentum that makes people want to try it immediately, and also the kind of setup that can make them postpone it indefinitely. If you do not want to download code, install dependencies, and explain to your producer why your machine is now compiling something called a model, running CorridorKey inside the Background Remover toolkit gives you a low-friction way to test it on your own footage first. That includes testing it against your current keys, and checking whether your exports land cleanly in your comp toolchain, without rebuilding that toolchain just to run an experiment.

How CorridorKey was invented

CorridorKey started as a response to a workload problem. A greenscreen-heavy show needed a lot of shots, and the team wanted an automated way to cut subjects out so they could spend time on the creative side of VFX instead of hand-cleaning keys frame after frame.

The design focus landed on a specific compositing headache: a greenscreen edge pixel often contains a mix of foreground and background light. A matte can be good and the color can still be wrong, because the plate already baked the screen contribution into semi-transparent detail. The CorridorKey approach targets a straight color foreground output paired with an alpha output, so semi-transparent materials, motion blur, and hair can keep behaving like actual transparency instead of looking like tinted cutouts.

Training data was coming from CG so the model could learn from mathematically clean answers. The workflow renders greenscreen plates, then renders the same foreground without the background and with a perfect alpha, giving the model ground truth for both color and transparency. Scale was coming from procedural variation, including procedural scene generation work in tools like Houdini and Blender to produce many variations in lighting, materials, objects, and motion without rebuilding each shot by hand.

Early results were treated as tests and iterated on through retraining. One tactic for pushing quality was to composite results over random backgrounds and neutral gray during testing, so leftover contamination becomes obvious and gets punished during training. The tool is being used as a first step in a broader pipeline, with outputs intended to drop into comp and realtime contexts in apps like Adobe After Effects and Unreal Engine.

What you get out of Beeble after a run

If you are testing CorridorKey for greenscreen work, this matters because the outputs determine how painful your handoff is. A quick trial that ends in a format conversion detour still counts as pain. It just wears a different hat.

Background Remover is built around alpha extraction for compositing and VFX workflows. You can upload a video, an image sequence, or a single image, then download results intended to slot into a comp.

On the Cloud pricing page, export options are listed as RGBA exports in MOV or PNG sequence and alpha exports in MP4 or PNG sequence. MOV here refers to the QuickTime container, PNG refers to the PNG format, and MP4 refers to the MPEG family container.

Pricing, credits, and practical limits

Background Remover usage is credit-based. The Cloud pricing is around image uploads as consuming one credit per image and video uploads as consuming one credit per second of video.

The plans listed include a free Starter tier that includes ninety credits per month and is labeled non-commercial. Two paid tiers have Background Remover included. “Creator” is listed at nineteen US dollars per month or sixteen US dollars per month when billed annually, with five hundred forty credits per month. “Professional” is listed at seventy-five US dollars per month or sixty US dollars per month when billed annually, with two thousand four hundred credits per month.

Per-upload maximums for video length are thirty seconds on the five hundred forty credit tier and one minute on the two thousand four hundred credit tier. There is also a batch upload up to twenty files at once on the paid tiers.

A production reality check

CorridorKey is a model option, not a replacement for judgement. Every keying tool behaves differently across compression, sensor noise, spill, lens artifacts, and the very special chaos of talent wardrobe choices. Test CorridorKey on your own porudction plates before you trust it with a deadline, and keep your existing approach ready for the shots that refuse to behave.

If the results look good, treat the first integration step as a controlled experiment: run a small batch, validate edge stability, validate color behavior in the semi-transparent areas, validate the exports in your comp, then scale up. That is less romantic than a revolution, but it is how tools earn their place in compositnig pipelines.

https://docs.beeble.ai/beeble/background-remover

https://github.com/nikopueringer/CorridorKey

https://beeble.ai

The post Beeble adds CorridorKey green screen model first appeared on DIGITAL PRODUCTION and was written by Bela Beier.

For those who don’t know the tool: Beeble runs AI relighting and pass generation in the browser via the Cloud app and locally via Beeble Studio, using SwitchLight for video-to-PBR work and SwitchX for background swaps, with exports that slot into comps in Nuke and motion work in After Effects.

Background Remover does not add a brand new trick. It pulls the same AI masking model used in VFX Pass Generator into a standalone, faster workflow meant for the quick matte job, with the provided materials calling it more credit-efficient than a full pass as a marketing claim. Exports lean hard into practical comp handoffs, including RGBA video with alpha, RGBA PNG sequences, and alpha-only sequences, which fits motion graphics work where you want clean holdouts so titles and design layers can live behind moving subjects.

For more background, see Digital Production coverage of SwitchX background swaps, Studio local 4K relighting, and SwitchLight 3.0.

The real news is the shortcut

Background Remover lives inside the Cloud app as a standalone alpha extraction workflow. The core promise is not mystery science. It is a packaging change that targets one task, foreground mattes, with fewer steps and fewer credit demands than running a broader multi-pass job.

That matters because a lot of shots do not need a full buffet of passes. Plenty of days you just want a clean subject cutout so you can comp a replacement plate, push a quick relight downstream, or build motion graphics behind a moving performer. Background Remover aims at that moment when you would normally sigh, open your roto tool of choice, and start paying for coffee by the hour.

It also draws a bright line between where it runs and where it does not. Background Remover is available exclusively in the Cloud app and it is not available in the desktop product yet.

Inputs that match real-world chaos

The tool accepts three kinds of input: a single image, a video, or an image sequence. Single images support common formats, including PNG and JPEG. Image sequences support up to 2,000 frames. For video, the supported container and codec combinations include MP4 using H.264 and MOV using ProRes 422, ProRes 4444, or H.265. The maximum file size is 2 GB. The tool supports up to 2K resolution at 2048 pixels, and it will downscale larger video. It supports clips up to 60 seconds and up to 30 fps, with higher frame rates reduced.

Color handling has a practical bias. Rec. 709 for video and sRGB for images are called out as the best quality settings, while other color spaces such as Log can degrade quality. That is less of a moral stance and more of a reminder that alpha extraction likes predictable input, not surprise curves.

Preview first, then commit, unless you like living dangerously

Background Remover runs a two-phase workflow for video. First comes a preview stage that extracts a preview frame and generates rough alpha previews. This stage exists for sanity checking. The preview alpha is explicitly rough, not pixel-perfect, and fine details like hair edges and semi-transparent areas are refined during full extraction.

If you want to steer the result, there is an interactive refinement step. The workflow uses an Edit Alpha action inside the preview dialog. That opens a rotoscoping UI designed around quick subject selection. The demo workflow shows clearing the existing mask and selecting only the subjects you want to keep by clicking them, then applying the alpha.

There is also a Skip Review mode. It bypasses preview and refinement and runs full extraction immediately. In that mode, the first frame becomes the reference and the pipeline runs without manual review. It is intended for simpler shots with clear subjects and consistent backgrounds. None of this replaces judgment. It simply gives you the option to front-load a small amount of control before you burn the full render.

Exports that behave in comps

Background Remover produces two output types: RGBA results with transparency applied, and grayscale alpha mattes. For RGBA, it can output a MOV file with an embedded alpha channel, plus RGBA PNG output as a sequence or a single image. The MOV output is 10-bit RGBA in sRGB. The PNG RGBA output is 8-bit in sRGB.

For alpha-only delivery, it can output an MP4 grayscale matte as well as grayscale PNG output as a sequence or a single image. Grayscale alpha outputs are 8-bit and represent the matte range from 0.0 to 1.0.

The point here is pipeline friction. An embedded-alpha MOV can drop straight into After Effects, DaVinci Resolve, or Final Cut Pro without juggling a separate matte file. When you do want a separate matte, the alpha-only options cover both video-centric and frame-centric workflows.

If you build motion graphics, this is the part that keeps paying rent. A clean matte lets typography, UI, and graphic elements sit behind a moving subject while staying readable. That trick stays stubbornly useful, even when the rest of the shot changes.

Credits, pricing, and the part everyone asks first

Pricing is expressed in credits and it is published on the official pricing page for the Cloud plans. Background Remover is listed at 1 credit per second of video, and 1 credit per image. VFX Pass Generator is listed at 3 credits per second of video, and 3 credits per image. That is the math behind the one-third claim.

Plan details and credit bundles live on the Cloud pricing page, including per-plan limits. Note that Background remover is not included in the free tier.

Limits that matter when you are on a deadline

Image and image-sequence uploads have a maximum of 100 MB per file. Resolution supports up to 2K at 2048 pixels, and larger files are rejected. Video uploads support up to 2K, with larger video downscaled. Video duration supports up to 60 seconds and frame rates up to 30 fps, with higher rates reduced.

Bulk handling exists too. The tool supports bulk downloading multiple completed results at once. For anybody juggling variants, alt takes, or multiple elements, that avoids the classic cloud workflow of clicking download until your wrist files a complaint.

Where it fits in the larger toolset

Background Remover sits as a focused subset next to the broader pass workflows. If you only need a matte, it keeps you out of the heavier multi-pass path. If you need more, the pass generator remains the place for depth, normals, and other map outputs that support relighting and downstream work in 2.5D and 3D contexts.

https://app.beeble.ai/

The post Beeble Background Remover hits Cloud app first appeared on DIGITAL PRODUCTION and was written by Bela Beier.

ONYX builds ONYX Ai Matte as a GPU-accelerated matte extraction tool for segmentation, tracking, and mask refinement inside OFX-compatible hosts. It targets hair and fur edge work and shots with more than one subject, and it frames the speed and quality claims as marketing claims. Under the hood, it uses Meta SAM3 and VitMatte models, packaged via ONNX in FP16 and accelerated with NVIDIA CUDA 12.6 and TensorRT 10.x.

Prompts, trimaps, and tracking

The UI exposes five pipeline modes: box or point prompts with auto track, box or point prompts with manual track, text prompts with auto track, mask prompts with auto track, and a trimap workflow using VitMatte with manual track. Point and box workflows let you set foreground and background points and a bounding box. The interface supports up to 32 points.

Text prompt mode detects objects that match your text. If it finds multiple matches, one foreground point picks the instance. Mask prompt mode takes a rough input mask and uses it as the prompt for a refined segmentation. The trimap path expects white foreground, black background, and a grey uncertainty band for edge refinement. Tracking integrates directly into the prompt workflows. In Nuke, the box center can be driven by expressions so a tracker can push it through the shot while size stays consistent. You still need to test any new tool before it goes into production, especially when the alhpa becomes the single point of failure.

Hosts and compatibility

The published host list includes DaVinci Resolve 18 and later, Fusion Studio 18 and later, and Nuke 13 and later. It also positions the plug-in as working in any OFX compatible app, like Autodesk Flame specifically.

System requirements and what is not supported

Minimum requirements list Windows 10 64 bit, an NVIDIA RTX GPU, 6GB of VRAM, 16GB of RAM, and 8GB free space. Windows 11 64 bit is also supported. Text prompts require 8GB of VRAM or more. The baseline GPU callout is an NVIDIA RTX 2060 or better with SM 7.0 or higher. Not supported: GTX 1000 series, AMD Radeon, and Intel Arc.

Trial, licensing, and pricing

A full featured 7-day trial is offered with no credit card required. Licenses are sold as lifetime, one time payments with no subscription, plus free minor updates. Pricing is published in euros as lifetime tiers on the official pricing page. Indie costs €80 for one machine node locked. Studio 3 costs €180 for three machines node locked. Studio 10 costs €450 for ten machines node locked. Studio 10 also includes priority support.

https://onyxofx.com/

The post ONYX Ai Matte for OFX hosts first appeared on DIGITAL PRODUCTION and was written by Bela Beier.

For those who don’t know the event: FMX is where post, VFX, and realtime folks compare notes, spot new workflows, and meet toolmakers from Foundry to AYON .

The 30th edition runs on site May 5 to May 7, with Online and On Campus on May 8, and On Demand from May 9 to June 9. Early Bird ticket options run until March 20. Tickets are sold through the ticket shop, and the full schedule is published as an online program schedule.

This year’s reveal is a broad spread across VFX, animation, and digital media creation, with more updates promised as additional speakers and topics get added. The headline message is simple: the program is live now, and it is designed to be browsed like a buffet. Get your preferred morsels here :)

RENO turns a studio inward

A newly confirmed session in the Shorts track focuses on RENO, an original sci fi short used as a live testbed for virtual production and machine learning workflows. The session names Tav Flett, Rob Hifle, James Pollock, and Paul Silcox, and describes how a traditionally post-driven VFX studio re-engineered its pipeline for a newly opened virtual production stage. It also calls out Gaussian splat scanning, automated rotoscoping, and marker removal as tools for streamlining production.

Generative video, now with shot notes

The hype cycle is almost over. The bubble tends to pop the moment somebody asks where this stuff fits into an actual production pipeline. That is the useful angle of Moonvalleys‘ session in the “The Road ahead” track. . Instead of treating generative video as a party trick, Ben Lock looks at what happens when studios try to use it for real: control, continuity, versioning, integration, governance, and all the other small details that usually kill shiny ideas on contact.

For VFX and animation teams, that is the point. Not more halfbaked sizzle reels, but a sober look at where generative video already helps, where it still breaks, which parts of the panic were never grounded in production reality, and when studios may begin hiring artists again once practical applications, and their many many limits, are easier to assess.

Predator: Badlands, built as a handoff

A joint presentation in the VFX for Features track names Laurens Ehrmann from The Yard VFX and Dominik Zimmerle from TRIXTER discussing work on Predator: Badlands. Shared assets, shared look development, and constant creative exchange across studios to ensure continuity while elevating environments, characters, creatures, and effects, plus a deep dive into selected sequences and the creative and technical challenges behind them.

And there is more to come! Much more!

https://fmx.de/en/program/program-2026/overview

The post FMX 2026 program goes live first appeared on DIGITAL PRODUCTION and was written by Bela Beier.

Mocha Pro 2026 is out, and Boris FX’s Emmy and Academy Award-winning planar tracker returns with an update that focuses on refinement rather than reinvention. The 2026 release adds new AI-driven roto and matte tools, smarter 3D-solve cleanup, and a rebuilt Curve Editor, all tuned to make shot-fixing and cleanup faster and more predictable for working compositors.

The update also aligns with VFX Reference Platform 2025, adding support for Qt 6.5.4 with PySide 6, Python 3.11, OpenEXR 3.4.5, Alembic 1.8.8, and FBX 2020.3.7. This ensures fewer pipeline compatibility issues in studio environments.

Matte Refine ML: AI for tricky edges

The new Matte Refine ML system expands Mocha Pro’s machine-learning masking family, which already includes Object Brush ML, Matte Assist ML, and Face ML. It analyses existing masks and automatically refines soft or semi-transparent edges which is useful for hair, fur, motion blur, and defocus.

Two refinement modes are available: one optimised for soft motion or blur, the other for sharper edges. Additional post-processing sliders (Black Clip, White Clip, Edge Grow, Shrink/Grow, and Blur) let artists fine-tune how transparency and detail are blended along the edge.

For multi-layer composites, the new Group Layer Mattes option merges multiple layers into a single matte clip, improving render and playback performance. Combined with Matte Assist ML, this creates an efficient path from object masking to refined alpha without intermediate renders.

Refine Solve: faster, cleaner 3D tracking

The Refine Solve tool targets 3D camera solves that have drifted or accumulated bad data. Using the Clean Up Features dialog, users can delete unstable or short-lived tracking points, then recalibrate the existing solve without starting over.

Because Refine Solve builds on the original solve data, it preserves previous adjustments such as ground-plane alignment or scene scaling. For extended tracking and finishing, the refined data can be exported directly into SynthEyes for further cleanup. The result: faster iterations and fewer re-solves for 3D match-move tasks in complex shots.

Blips and 3D

Technically, Mocha’s camera solver identifies trackable “blips” in the image and converts them into 2D trackers, which are then triangulated into static 3D feature points. The software measures the average deviation between the 2D trackers and 3D points as HPix (horizontal pixel error). A low HPix value signals a stable camera solve, while spikes in the error curve expose moments where the 3D reconstruction drifts. These spikes often correspond to unstable track data caused by motion blur, occlusion, or minor parallax inconsistencies.

The Clean Up Features system provides targeted filters to address these issues. It can automatically disable feature points during high-error frames, discard very short or inconsistent trackers, and remove features that contribute excessive deviation. Once unwanted data is removed, Refine recalibrates the existing camera without re-solving from scratch, updating only the relevant calculations while maintaining previously established orientation and coordinate systems. This allows technical directors to preserve scene alignment and object placement while improving solve precision.

Refinement should be applied only when the base camera movement is physically plausible. If the initial camera path is incorrect or erratic, a full re-solve remains necessary. However, for typical production shots where the solve is broadly correct but slightly unstable, this incremental workflow offers a reliable way to tighten accuracy, lower HPix variance, and maintain alignment integrity across multiple refinement passes.

Curve Editor rebuilt for modern pipelines

After a long hiatus, Mocha Pro’s Curve Editor makes a full return. The interface has been rewritten from the ground up, with tighter integration between the Dope Sheet and Graphs panel. Artists can now visualise tracking, roto, and camera-solve data as curves, then smooth, zoom, or isolate problem areas directly. A new offset-curve overlay in the Adjust Track module displays how refinements affect the original track in real time. Filtering options allow users to display only keyframed parameters or selected spline points, helping to pinpoint problematic data without clutter.

Smaller but useful refinements

Beyond the headline features, Boris FX lists numerous “quality-of-life” updates under the hood. Playback of refined mattes no longer requires separate rendering, and composite mattes can now be applied directly in other Mocha render modules, such as Insert or Remove.

Mocha Pro 2026: Pricing and availability

Mocha Pro 2026 is available as a standalone application and as plugins for Adobe After Effects, Premiere Pro, Avid Media Composer, Foundry Nuke, Blackmagic Fusion, Autodesk Flame, and VEGAS Pro. Subscription pricing starts at €42 per month or €290 per year. Perpetual licences (from €675), upgrades, and support plans are also offered. Customers with active Mocha Pro or Boris FX Suite subscriptions receive the 2026 update at no additional cost.

Reality check

While the AI-driven refinements and rebuilt Curve Editor mark significant usability improvements, studios should validate performance and matte accuracy in controlled conditions before integrating Mocha Pro 2026 into production pipelines.

The post Mocha Pro 2026: Refined, re-solved, re-edged first appeared on DIGITAL PRODUCTION and was written by Bela Beier.

Boris FX has unveiled Mocha Pro 2025, introducing improved planar tracking tools, USD file support, and enhancements to rotoscoping workflows. The latest version of the popular motion tracking and VFX tool focuses on production-friendly updates for compositors, editors, and VFX artists.

Open USD Integration: File Exchange Simplified

Mocha Pro 2025 now supports the USD file format (Universal Scene Description). This widens compatibility for data exchange across modern pipelines, particularly in VFX and animation. Users can import and export USD files to streamline workflows with other USD-supported applications.

Planar Tracking Gets Faster and Smarter

The core feature, planar tracking, remains a focus with speed and stability improvements. While no groundbreaking changes were listed, refinements ensure smoother motion tracking results in a shorter time—good news for artists on tight schedules. Think of it as a “SynthEyes Light” for quick tracks. For more complex shots, the “Full-Fat” SynthEyes remains one of the best trackers out there, but Mocha Pro 2025 offers a solid option for fast and reliable planar tracking within the Boris FX suite. Building on the recent addition of SynthEyes 3D tracking technology, Mocha Pro 2025 now adds 3D moving object solves, allowing artists to solve for moving objects within 3D scenes. By combining planar and PowerMesh tracking data, users can generate accurate meshes and point clouds for complex 3D tracking shots. Solve data integrates seamlessly with popular VFX applications via USD, Alembic, and FBX exports. After Effects users can export solve data in the Mocha Pro UI or generate it directly inside After Effects with the Mocha Pro plugin.

Rotoscoping: Tweaks to Streamline Precision

Mocha Pro’s rotoscoping tools receive practical upgrades, optimizing the precision of spline-based masking. Enhancements aim to simplify shape management while keeping the interface familiar for existing users.

OpenColorIO for Color Management

With OpenColorIO (OCIO) support, artists can match project color spaces between Mocha Pro and other software like Nuke, Resolve, or Blender. This is particularly useful when working on VFX-heavy projects requiring accurate color consistency across the pipeline.

Streamlined Data Exports

A redesigned export dialogue allows artists to export Mocha Pro tracking data more easily using a sleek interface that combines tracking, shape, and 3D data exports in one place. Users can select data export options by popular host application presets, save favorites, and work faster with an “Export Again” feature. Since the current version only offers a dropdown menu, this is an extremely useful update to the “bread and butter” workflow—a small but appreciated quality-of-life improvement for artists.

Compatible and Ready

As always, Mocha Pro integrates seamlessly with leading compositing and editing software, including Adobe After Effects, Premiere Pro, Nuke, and Avid. Licensing options remain flexible, with Mocha Pro available as a standalone application or as a plug-in for host software.

For pricing, head directly to the Boris FX website. (They have a free trial, if you want to see and test it for yourself) As always, test new features thoroughly before deploying them in live projects.

The post Mocha Pro 2025: Planar Tracking, USD, and Roto first appeared on DIGITAL PRODUCTION and was written by Bela Beier.

The newly released Howler 2025 brings a range of features targeted at professional users working in digital content creation. Developed by the Project Dogwaffle team, Howler is a digital painting software known for its versatility in animation, FX generation, and natural media simulations. The 2025 edition extends the software’s functionality by integrating AI-powered tools aimed at speeding up workflows, especially in animation and VFX tasks. Artists can now take advantage of machine learning to automate certain processes, though it is advised to verify results before using them in production.

The software introduces AI-driven Rotoscoping and Animation Prediction, allowing users to automate keyframing and frame interpolation for smoother transitions between frames. This feature leverages deep learning to predict motion paths based on existing frames. You can now skip the tedious manual interpolation of in-between frames, but as always, it’s a good idea to review the automated results for any corrections.

Howler 2025 also comes with GPU-accelerated FX rendering, improving the speed of rendering tasks significantly. This is particularly useful for users working with high-resolution media, as GPU acceleration helps to reduce bottlenecks during rendering, especially when generating complex effects like particle simulations, weather effects, and motion blur. GPU support extends to the Particle Modeler and Cloud Generators, offering real-time previews of these FX.

One of the new tools is the Image Stabilizer, which aids in reducing shakiness in animation sequences, making it a go-to feature for post-production professionals handling footage with camera shake. This stabilizer is particularly helpful for those dealing with live-action elements combined with CGI. You can apply these stabilizations globally or locally, depending on the sequence.

There’s also an expansion of the Brush Engine, which now includes dynamic brushes powered by AI that adjust to the user’s workflow. These brushes simulate various natural media effects in real-time, enhancing the user’s ability to create complex textures and paint effects with minimal manual adjustment. Howler has also introduced new 3D Paint Capabilities, enabling artists to paint directly onto 3D models and surfaces, offering more versatility in asset creation for 3D pipelines.

With regard to file management, Howler 2025 introduces Python-based scripting. This gives advanced users more control over automating workflows and integrating Howler with other production tools, pipelines, or custom plugins. Python scripting opens up new possibilities for tool customization, batch processing, and repetitive task automation, which will be a welcomed feature for anyone handling complex projects.

The update also includes new Video FX Filters that enhance post-processing. These filters allow for advanced color grading, noise reduction, and stylized looks that are typically used in final renders. Integrated GPU support ensures that these effects can be rendered in real-time, making it easier to preview the final output before committing to a render.

Pricing and Licensing
Howler 2025 is available under a one-time purchase model, with the base price starting at $99. Professional users can opt for an enhanced version with additional FX tools and AI capabilities for $149. Licensing is non-subscription-based, which could appeal to users looking for a more predictable, long-term cost structure.

You can learn more about Howler 2025 by visiting Project Dogwaffle and reviewing the full product documentation.

The post Howler 2025 Released first appeared on DIGITAL PRODUCTION and was written by Bela Beier.

In recent years, Foundry has not only tightened up the release schedule considerably, but also made it much more regular. Nevertheless, version 14 is not a maintenance update, quite the opposite. Not only are new features being added, but in some areas the existing ones are being shaken up. The biggest and most important area is probably the 3D system, which has been completely overhauled.

Cutting off old habits

Sometimes the time has come to make a clear cut. Even as a software developer, it becomes increasingly difficult over the years to work on the same old architecture. With version 14, Foundry therefore decided to rewrite the 3D system, which has always been one of the core elements of the software, from scratch. In order to be well equipped for the coming years, USD (Universal Scene Description) was chosen as the basis. USD not only offers massive leaps in performance, but is also being supported by more and more other manufacturers.

To accommodate larger pipelines, it will be possible to select your own version of USD to use, regardless of the version of Nuke you are using. However, those who do not use USD in their pipeline should not have any disadvantages compared to the previous system, as everything that the new 3D system requires is already fully integrated in Nuke. As such a changeover is of course a big step, the old 3D system is not being retired just yet. It is still available in Nuke for now and, perhaps more importantly, the new system is currently in beta.

Why USD?

Better performance alone is a nice effect, but there were more reasons for switching to the USD-based system. A major Achilles heel of the old system was the handling of large imported geometries, where there was no way to isolate individual parts and edit them individually. The new Scene Graph and Path and Mask Knobs form the basis for this.

The Scene Graph

To organise everything from objects and materials to cameras and lights effectively and uniformly, there is a new panel in Nuke 14 called “Scene Graph”. Here you can find all the objects in a scene in a hierarchical structure and can name them (with a new token system if desired), switch them on and off and create dependencies. The Scene Graph and Viewer are closely linked and objects selected in the Viewer are also selected in the Scene Graph and vice versa. A search function is also integrated.

Path and Masks Knobs

All nodes in the new 3D system that generate or import geometry now have a path as an entry, which simply refers to the name of the node by default. However, it is linked directly to the scene graph and can also access the token system. This means that more complex scenes can be named more quickly and cleanly and dependencies can also be created via the path without having to play connection limbo in the node tree.

The name “Mask Knob” is somewhat misleading, as it is actually a way of defining which objects in a scene should be influenced by a modifier node such as a GeoTransfom. The new default behaviour now looks like this: If you insert a node below another node, the result of the last node is affected – no longer the entire stream. However, if you want the new node to influence several objects, you can assign it to the mask knob from the scene graph or via an expression.

USD Lights and Materials

If USD-based geometries are imported into the new system, lights and materials are now displayed correctly and thus provide a better preview of the actual asset. The new Preview Surface Node is a new way to create more complex materials within Nuke and is seen by developers as the first step in a development that is progressing through beta. There are also new USD Lights. Unlike the old system, lights are no longer converted into Nuke’s own format, but are displayed exactly as they looked in the USD-based DCC software they came from.

Old and new

As already mentioned, the old and the new system will both populate the Node Graph for the time being. However, they are not compatible with each other. The old nodes retain both their name and their colour, while the new ones stand out with a new nomenclature (TransformGeo is now called GeoTransform) and a green that complements the old red. They also appear with a small “Beta” notice. Speaking of beta: Foundry wants to use this beta to actively incorporate feedback from the community, which is why there is now also a forum on the Foundry site for the new 3D system.

Unreal

The Unreal Reader Node for Nuke X and Nuke Indie is completely out of beta. It can be used to transfer maps and sequences directly from an Unreal Editor session to Nuke. To do this, a “Nuke Server” plugin must be installed in Unreal, which then provides the session for Nuke. From here, the artist can have exactly the channels and passes that he needs made available, as everything is provided “on-demand” by Unreal. Various types of crypto matte can also be requested. The current OCIO colour transforms are also supported.

Cameras can be synchronised with the Unreal session as well as replaced by Nuke. The whole thing works non-destructively for the Unreal session, so that you now have the freedom to position the camera slightly differently in Nuke than in Unreal. If you are happy with your result and want to make sure that further changes to the Unreal session are not passed on to Nuke, you can generate an EXR sequence of all requested channels and passes from the Unreal Reader Node.

A particularly nice feature is the stencil mode, which allows you to split individual objects in the Unreal scene into separate layers. Even shadows and occluding objects can be removed. You also have the option of rendering the Nuke scene as a CubeMap, which allows you to transform your scene into a Lat:Long image or an Environment Sphere in Nuke.

The cat gets a new home

The machine learning tool “Copycat” is getting a major performance boost. Ten to twenty per cent faster learning should be possible on current Nvidia cards. The automated rotoscoping of human bodies has been accelerated even further. New setting options should dramatically speed up training here. Finally, users now have the option of displaying only the thumbnails relevant to them in the LayerContactSheet view for training.
Outside of Nuke, Foundry has created the “Cattery”, a free repository where copycat files contributed by the community can be downloaded. The whole thing is sorted by category and will hopefully continue to grow over the coming months.

Bokeh

Foundry acquired the rights to PG Bokeh from Perigrine Labs. This popular depth of field tool is natively available in all Nuke versions from version 14.02 onwards. PG Bokeh has already been used in many major productions and is the only depth-of-field tool that can be combined with deep compositing.

Login-Based Licence

Nuke 14 offers Foundry customers a further option for managing their own licence or licences. In addition to the classic node-locked licence or an RLM-based server licence, you can now also opt for a login-based licence. Artists can log in with their email address and a password to activate their licence. This makes it much easier to take a licence to the home office.

The online platform also offers numerous options for managing multiple licences for teams. Foundry emphasises that this licence model is purely optional and anyone who doesn’t want to switch doesn’t have to. This is also important for anyone who still has to work in parallel with older versions of Nuke, as the login is only available with Nuke 14.

Subscription

Subscription is always a double-edged sword. Some see greater flexibility, more predictable costs and the opportunity to get started without a major investment, while others simply see subscriptions as a “money grab”. The Foundry is now also offering the Nuke Family as an annual subscription. The prices are as follows: Nuke costs customers 2,699 Eur per annum, Nuke X 4,099 EUR and Nuke Studio a whopping 4,999 EUR.

As with all Foundry products, there is no monthly subscription model and unfortunately – unlike other products – no monthly payment option. Although there is still the option of quarterly rental, the prices here are not really attractive – they are over fifty per cent of the annual subscription. Existing customers still have the option of purchasing the previous “perpetual licences” until the end of the calendar year and then continue to receive maintenance for them. However, Foundry has also tightened the price screw here: Nuke now costs EUR 5,118, Nuke X EUR 9,758 and Nuke Studio EUR 11,358.

Conclusion

With the new 3D system, Nuke 14 lays the foundation for the coming years and sets a future-proof standard with USD. The system of making a feature available to the user base as a beta for one release and then bringing it out as a final in the next release or the one after that has already worked well in the past with the Unreal Reader or with the sync sessions in Nuke Studio and Hiero(Player). The Unreal Reader may only be of interest to a certain target group at the moment, but the more popular virtual production becomes, the more comp artists will have to deal with Unreal. They have the basis now.

Copycat gets a nice, comprehensive product maintenance – important, because Nuke’s approach to machine learning only works as long as it is regularly updated. The fact that all Nuke users now have PG Bokeh on board is really pleasing – especially because of the support for deep compositing. The login-based licence system will certainly provide more flexibility in the medium term.

One criticism is that, once again, the small Nuke – without X – has hardly any features – of course the new 3D system is also being introduced here. But apart from the bokeh, all the new features are limited to Nuke X and Studio. Copycat is still a feature that is reserved for Windows and Linux users due to its close integration with NVIDIA.

It remains to be seen whether the announced port to Apple Silicone will also let the cats jump over the Mac. And last but not least, the switch to subscription will not be greeted favourably everywhere in the community. For larger VFX studios in the feature sector, an annual subscription may actually offer more flexibility in scaling the pipeline. Customers in the advertising sector and freelancers, on the other hand, will not find an attractive offer here to be able to react appropriately in an ever faster changing market.

The post What’s New in Nuke 14? first appeared on DIGITAL PRODUCTION and was written by Christoph Zapletal.

Multithreading is the buzzword for Flowbox 1.5, which not only increases the speed of the cache, but also of backgroun05d rendering. The new features also include the export of shapes to Adobe After Effects and improved display settings. In addition, users can now scale the interface in real time to get the best out of their HD displays.

Existing features are also improved with Flowbox 1.5

Flowbox 1.5 offers more user-friendliness. The developers have also improved the Shape Isolation Mode. It now isolates gizmos and only renders them in isolation. The rectangle selection has also been improved: It now automatically selects either shapes or points.

But that’s by no means all. A list of the features can be found here.

The post Flowbox 1.5 on the market first appeared on DIGITAL PRODUCTION and was written by Bela Beier.