For those who do not know the tool: SwitchX is Beeble’s image and video transformation system for prompt-driven and reference-driven visual changes such as lighting adjustment, background replacement and related compositing-style alterations. Until now, that workflow lived primarily in the web application.

Beeble has launched the SwitchX API in public beta, taking its browser-based image and video transformation tool and turning it into something developers and pipeline teams can actually integrate into production systems. That is the useful part of this release. The familiar launch language about cinematic transformation is there, of course, but the more relevant shift is structural: SwitchX is now available via a documented REST API rather than only through a web interface.

From web app to pipeline component

SwitchX API follows a fairly standard service model. Users authenticate via x-api-key, upload source media, start a generation job, then either poll the result endpoint or use a callback URL for webhook-based completion handling. In other words, it behaves like an API, which should not be remarkable, but in this market it sometimes still is.

That matters because it moves SwitchX from a browser-first tool toward something that can sit inside internal apps, automated workflows, or technical artist tooling. For teams trying to reduce manual handling between editorial, compositing, review and delivery, that is a more meaningful step than the launch itself.

What the API actually supports

The generation endpoint accepts both image and video jobs. Source material can be supplied from Beeble-hosted upload URLs, external HTTPS URLs, or inline base64 payloads up to 50 MB. Supported image formats include PNG, JPEG and WebP. Supported video formats include MP4 and MOV using H.264 or HEVC, with a maximum of 240 frames per job.

Output is (currently) limited to 720p and 1080p, with 1080p being the default. That does not place SwitchX in final-finishing territory, but it does make it usable for iteration, look development, internal tool integration, and some fairly direct production use where speed and automation matter more than absolute output scale.

Alpha handling

SwitchX supports four alpha modes: auto, fill, custom and select. Auto handles subject separation automatically. Fill keeps the full frame. Custom accepts a supplied alpha asset. Select allows users to define a first-frame alpha keyframe that the system then propagates across the shot.

Background replacement, relighting and subject isolation all sound smooth until edges, motion blur, hair and semi-transparent detail arrive and start asking difficult questions. The API exposes enough control to make the workflow more testable and less opaque.

Webhooks, retries and other unglamorous useful things

Beeble has also included a few details that make the SwitchX API more realistic for technical workflows. The start-generation endpoint supports callback_url for webhook-based completion and idempotency_key for safer retries. This suggests Beeble is not only targeting solo browser users but also teams that want to integrate SwitchX into repeatable systems. That does not automatically make it production-proven, but it does mean the API is designed with awareness of how production systems tend to break.

Pricing is prepaid and usage-based

Beeble is positioning the SwitchX API as a pay-as-you-go service with prepaid USD credits. The public pricing page lists Build-tier pricing at $0.10 per 30 frames for 720p video and $0.30 per 30 frames for 1080p video. Images are priced at the same two levels. The minimum top-up is listed at $50, and the default monthly spending cap is $5,000. At launch, the API appears to focus specifically on SwitchX. Other Beeble tools, including SwitchLight, are not currently presented as API-accessible products in the same way. We’ll see what happens :)

What this means in practice

The interesting part of the SwitchX API launch is not the promise of cinematic transformation without manual VFX work. The interesting part is that Beeble now offers a well-documented service with uploads, generation jobs, polling, callbacks, account controls and usage-based billing. That moves SwitchX from a browser feature to a pipeline candidate.

Whether it becomes a serious production tool will depend on output consistency, edge quality, latency, and how much cleanup still lands back on artists after the automated step has finished. That question remains open, which is normal. The difference now is that developers and technical teams can test it directly inside their own workflows instead of evaluating it from the sidelines through a browser demo.

https://developer.beeble.ai/

The post SwitchX API for video transformations in YOUR pipeline 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.

Photomontage lives or dies on perspective. If the camera does not match the photograph, everything downstream becomes a negotiation with angles, scale, and taste. CameraMatch AutoSetup v6 targets that first domino by generating an aligned 3D camera from a single photo, then setting up supporting scene items that normally take a few manual passes.

What CameraMatch AutoSetup v6 does

CameraMatch AutoSetup v6 is an automated camera-matching tool for photomontage work. It detects vanishing points and lines in photographs and uses that information to create a 3D camera aligned to the plate, aimed at architectural visualisation and general 3D scene setup.

Once the camera alignment happens, the tool also covers a set of setup chores that tend to get skipped until they break a comp. It can calculate and display the horizon line. It can create a physical camera with an accurate field of view. It can match the render output resolution to the background image resolution. It can set a viewport background overlay that shows vanishing point lines and the horizon. It can also export cameras using the FBX format so the camera can travel to other applications.

The overall pitch reads like a checklist of common photomontage necessities, bundled into a single automated pass. That pitch also includes marketing claims about ease and straightforwardness, which remain marketing claims.

Host apps today, and what is promised next

The currently available versions work with 3ds Max and Blender. A version for Maya is described as planned, and additional host versions are described as coming next week.

Camera matching tools often stumble on the unglamorous details of units and output sizing, so it is notable that the material calls out unit setup dialogs and scene unit contexts as part of the broader setup conversation. That framing keeps the tool squarely in production reality rather than demo land.

Why this matters for post and VFX

A good plate match is not just about placing geometry. It is about making every downstream decision cheaper. When the camera and horizon are consistent, the layout behaves. Lighting behaves. Shadow direction behaves. Reflections behave. Even simple matte work becomes more predictable because perspective lines agree across layers.

For photomontage-heavy teams, the time sink is usually not the final render. It is the first 20 minutes of making sure the camera is believable, the frame matches the plate, and the viewport does not lie. CameraMatch AutoSetup v6 positions itself as a shortcut through exactly that part of the day, with its strongest promise being camera alignment plus the surrounding setup steps in one go. If you have ever watched a project drift because two artists picked two slightly different horizons, you already know whcih argument this tool wants to prevent.

Availability, docs, and pricing reality

Documentation exists as a free manual hosted on Google Drive. The manual is covering the script for 3ds Max, Blender, and Maya. Distribution is offered through two storefront channels: Gumroad and Patreon. A one off purchase option for the Gumroad of 45USD, or through a

The download description also references a full script with files for 3ds Max and Blender, and it mentions direct contact as an option. The complete contents of the downloadable package are not listed in the provided material beyond that.

Practical notes before you point it at a deadline

Automation shines when you can trust the inputs. This tool relies on reading vanishing points and lines from photographs, so images with heavy lens distortion, weak straight line cues, or ambiguous architecture may still need human judgment and cleanup.

As always, new tools and innovations should be tested before use in production. Run it against known plates, compare results to your established camera match method, and confirm the exported camera behaves as expected in your pipeline before you bet a delivery on it. And yes, it can be both fast and correct, but only after teh boring validation pass that everyone wishes they could skip.

https://jamiecardoso.gumroad.com/l/boqjtv?layout=profile

The post CameraMatch AutoSetup v6 speeds photo matches first appeared on DIGITAL PRODUCTION and was written by Bela Beier.

For those who don’t know the tool: tamga is a quick sculpt plus vertex paint sketchpad that hands off via Wavefront OBJ to heavier DCCs like Blender when your scene stops being cute.

Small app, big get-it-done energy

tamga runs in a web browser, on desktop, and as an iPad app. The web version targets browsers with WebGPU. The iPad version requires iPadOS 26.0 or later. The design goes for minimal UI and a low friction workflow. There are no accounts, no subscriptions, and no ads stated for the tool. The tool is also described as offline by choice, with work staying on the device. This makes tamga a handy place to rough shapes, do quick paint passes, and spit out something presentable before you move to the usual monsters.

Sculpting that stays out of your way

Brushes include Clay, Smooth, Inflate, Flatten, and Drag. A modifier flips brush behavior into an alternate mode, and there is a smooth override that temporarily switches to the smooth brush at the same size. Dynamic topology is available per brush and is described as auto-splitting and simplifying as you sculpt. Remeshing rebuilds uniform topology at a chosen voxel density, and version notes mention a Close Holes button in the Remesh pop-up.

Symmetry support includes mirror sculpting across an axis, plus a symmetrize operation that applies symmetry to existing geometry. There are desktop shortcuts for undo and redo, and gesture based undo and redo on iPad.

Masks, booleans, and posing without the drama

You can paint masks to protect areas from other brushes, with an unmask action via the modifier concept. Masks also feed mesh creation. Extract Masked creates a new mesh from the masked region, and Extract Shell creates a thin shell from the mask boundary.

For fast shape bashing, there are primitives with boolean operations: union, subtract, and intersect. A smoothness slider controls how soft the boolean blend is. Positioning uses a gizmo, snapping is on by default, and a modifier disables snapping.

There is also a pose workflow built around placing anchors and dragging to deform, with options to remove anchors, freeze to bake deformation, and clear anchors. tamga comes from galata.ink, and it is a weekend project created outside professional VFX work.

Vertex paint, plus ink lines for style passes

Painting is vertex based, so paint lives on the mesh rather than in UV mapped textures. Channels listed include albedo, roughness, and metallic, with per channel toggles for painting, filling, and clearing.

Ink mode lets you draw ink like strokes on the 3D surface. View styles listed include paper mode, matcap, and PBR. Paper mode has controls such as valleys, peaks, chisel, and a mix control that blends between standard rendering and full paper mode. Render export formats listed are PNG, JPEG, and OpenEXR.

Export, pricing, and the reality check

Import and export uses Wavefront OBJ, so you can hand off to tools like Autodesk Maya or ZBrush when you need deeper pipelines. There is also export to a tamga format, plus auto recovery that saves work and restores after crashes, hopefully. Personal use is free, and personal, educational, and non profit use is free on most platforms. Commercial use requires one time payment of 12.99 USD.

A final note for people who ship frames for a living: test new tools and innovations before you rely on them in production, especially around OBJ round trips and vertex paint persistence. Do one quick scuplt, export it, reimport it, and check if the alebdo channel survives. If it does, you just bought yourself a nimble little idea machine.

https://tamga.galata.ink/

The post Galata.ink Ships Tamga Sculpt and Paint for Browsers first appeared on DIGITAL PRODUCTION and was written by Bela Beier.

Gaussian Splat Studio brings Gaussian splat point data into Cinema 4D as something you can actually work with, not just stare at. The tool is built to import, view, render, and export Gaussian splats directly inside the host app, while keeping viewport controls and render controls in their own lanes. That separation matters because splats tend to swing between two extremes: either they look great and crawl, or they move fast and look like a snow globe during an earthquake.

The core exchange format here is obviously PLY, the same file type commonly produced by mobile capture and processing services. The workflow shown starts with a real-world capture from a phone or camera, then a reconstruction step in a service such as Polycam, which outputs PLY splat data for the plugin to ingest. The result inside Cinema 4D is a splat object you can navigate around, tweak, and eventually render or export back out again.

Viewport control that admits splats can be ridiculous

Splat scenes vary wildly in scale and density. Different captures can come in at very different sizes (D’uh), so the plugin exposes world scale controls to get a scene into a sane range.

It also acknowledges the other common splat reality: point counts can be enormous. A referenced example uses 12 million points, and the plugin includes options meant to keep navigation responsive. One of the visible tactics is interactive splat reduction in the viewport, where quality deliberately drops while you navigate, then returns when you stop moving. The reduction can be turned off, but it exists specifically to keep the editor usable.

There is also a fast preview mode intended for heavy scenes, letting you switch to lighter display settings for camera setup, animation work, and general layout without changing the underlying splat source. The idea is simple: keep interaction smooth while you work, then restore full settings for final output.

Three looks, one splat

The plugin exposes multiple viewing and rendering looks for splat data. True Gaussian splat mode aims for a scan-faithful result. Point cloud mode is presented as both a stylized look and a faster way to iterate, with circular dot rendering as a deliberate aesthetic option. There is also a proxy geometry view described as a way to see what is happening under the hood, rather than a default look.

Alongside those modes, the plugin provides controls for splat size and for the minimum and maximum pixel radius of splats. The workflow frames these as practical dials for balancing detail versus fill. Smaller splats carry more detail, larger splats help fill larger areas. Push the balance too far and thin features can disappear or areas can open up into holes, so the controls exist to tune a capture into something that holds together under motion and framing changes.

A notey: not every PLY is oriented the same way. When a non-Gaussian splat PLY comes in on the wrong axis, the plugin includes a YZ flip option to correct orientation. That kind of messy reality is exactly what a production tool should deal with. If a format is technically correct but visually wrong, artists still have to ship.

Rendering paths and why the viewport can be the honest one

Gaussian Splat Studio supports rendering through the viewport as well as through Cinema 4D render modes, including Redshift and the Standard and Physical renderers.

The workflow shown treats the viewport render as a useful path for accuracy, while also outlining limitations. Native viewport rendering does not provide an alpha channel, so the tool includes an alpha mode that changes what the viewport output looks like. The result is not a perfectly white matte, and the explanation is that this is expected because semi-transparent values are part of how the splat output should composite more accurately. If a comp pipeline needs a harder matte, the suggestion is to adjust levels in the compositing step.

For Standard and Redshift rendering, the plugin builds what it needs in the background when you enable rendering, including generating a shader setup for the geometry it creates. Enabling rendering is off by default and is making the system a little slower while you work, so it is something you switch on when you actually need those render paths.

Relighting as a dial, not a fight

Splat captures often come with baked lighting characteristics. The workflow shown adds a relight blending control in the Redshift render appearance settings, letting the render transition between a fully luminescent look that preserves the captured lighting and a state that responds more to Redshift lights.

MoGraph-friendly splats are the real headline

Once a splat lives in Cinema 4D as something editable, it becomes available to the same ecosystem of tools artists already use to art direct motion graphics and look development. The plugin supports MoGraph-style controls through Effectors, Forces, and Fields, with a workflow that matches common object setups: select the splat object, add an effector or force, and it registers into the plugin’s control tabs. If you add tools out of order, the workflow shown notes you can drag them in manually.

This is the point where splats stop being a novelty and start being a production asset. If you can isolate, animate, and stylize parts of a capture with the same tools you use everywhere else, splats become another piece of the pipeline rather than a special-case import.

Export, cleanup, and downstream handoff

Gaussian Splat Studio supports exporting results back out as PLY, including exporting cleaned results and exporting as splat PLY.

If your pipeline depends on strict interchange, it is also worth remembering that PLY is a general container format used across different kinds of point data. The workflow explicitly differentiates between Gaussian splat files and regular splat files that can both be PLY, which is why orientation fixes and viewing modes exist in the first place. If you need a reference for the file format itself, the PLY format specification is hosted by Stanford.

Price and platform support

The price for Gaussian Splat Studio is $59.99. The product page lists compatibility for Cinema 4D versions 2024, 2025, and 2026, on Windows and Mac. As always, new tools and innovations should be tested before use in production, especially when they touch rendering, caching, and export handoffs that can ripple through an entire shot.

https://alphapixel.net/products/c4d-gaussian-splat-plugin/

The post Alpha Pixel adds Gaussian Splats to Cinema 4D first appeared on DIGITAL PRODUCTION and was written by Bela Beier.