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.

Re: Novation is now open for submissions from March 24, 2026 through June 9, 2026, with the submission cutoff set at 15:00 GMT. Judging starts June 10, 2026, and the winners are scheduled for announcement on June 24, 2026.

The core setup stays delightfully unforgiving: Everyone starts from the same base 3D building model. The job is to transform it into a finished scene that sells an idea through architecture, environment, and lighting. That can mean changing the purpose of the building, reshaping the facade, adding or removing floors, and building a world around it. The original structure still needs to remain recognizable, so this is a renvoation, not a witness protection program. There are great prizes and strong sponsor support: multiple prize categories, a cash component for top placements, and additional sponsor awards.

The rules focus on process, not just pixels

Participation starts with process proof. Artists are asked to publish a work in progress thread on a personal website, blog, portfolio, or social media page that clearly identifies them as a 3D artist. The first post needs to include the participation tag text for the challenge and a clickable link to the contest page or an at mention on social platforms. The intent is to show the work began during the challenge window and to support originality checks. The base model comes via a short form used to request the download. The model arrives in multiple formats: FBX, OBJ, 3DS, C4D, MB, and LWO. No premade Gaussian Splats, yet.

Scene freedom comes with a few hard stops. The rules allow third party assets such as vegetation, furniture, human figures, kitbash elements, and other asset library content. Post-production is allowed, but photobashing and paintovers are not. The final image must not show third party advertising, watermarks, or branding other than the provided sign that needs to appear visibly in the scene. The rule set also bans adult content, including blood, violence, eroticism, and politics.

The competition bans AI. The image must be created with 3D modeling software, and the rules also frame the work in progress requirement as part of verifying entries are original and not AI-generated.

Animation arrives, with guardrails

This edition introduces a dedicated Animation Category. Animation is optional, but entering it requires a still render submission as the main entry. Animation entries must run at least 15 seconds and must show the architectural scene, meaning the building and its environment.

The submission method routes animation through hosting platforms. Artists publish the final video on YouTube or Vimeo and provide the link with their submission. The minimum resolution is 1080p.

The animation must match the same scene as the still render. Work in progress recordings, timelapses, and screen captures do not qualify as animation entries. The animation rules also tighten the no AI stance further by banning AI-generated animation, motion capture from AI tools, and AI-assisted camera paths.

Animation judging criteria include camera work, pacing, lighting and mood transitions, storytelling, and technical quality. The broader judging criteria for the overall contest include visual appeal, concept originality, presentation, technical complexity of the model and scene, and overall execution quality.

Deliverables, specs, and the stuff that gets you disqualified

A finished submission needs a final render plus a clay or wire render of the scene. The render must be at least 1500 pixels on the longest side and must be delivered as JPG or PNG. File size should not exceed 5 MB.

The rules reject single-color background renders, test renders, unfinished work, pixelated or low-quality renders, screenshots, and models placed on wallpaper or photos. The rule text also states the contest model is for contest purposes only and cannot be used for other projects beyond the Re: Novation entry.

Entries can be updated during the contest, but the idea cannot change or be modified drastically, with only reasonable changes allowed. Artists can also correct the description and the tools list after submission by contacting the team.

One extra procedural detail matters for anyone trying to game the calendar. After sending the work via the contact form, a confirmation email is expected within one business day and includes a link to the gallery page. If that email does not arrive, participants are instructed to contact support.

Prizes and what is actually specified

The prize structure spans multiple categories: three main winners, one Animation Category winner, plus special sponsor award winners.

The top placements include cash prizes. First place lists a $1000 cash prize. Second place lists a $500 cash prize. Additional prizes include software licenses, subscriptions, training access, and render credits, along with challenge-time bonuses and discounts tied to participating sponsors. Some prizes may not be available in all regions.

The full details, rules, and sign-up sit on the official page at Re: Novation, and the organiser is 3DModels.org.

The post Re: Novation ArchViz Challenge opens first appeared on DIGITAL PRODUCTION and was written by Bela Beier.

For those who don’t know the tool: Dither Boy is a standalone dithering app that sits alongside Photoshop, Affinity Photo, and even MS Paint, and exports PNG, SVG, JPEG, and MP4. It also lives alongside sibling tool Flareware.

A rewrite, not a patch

Dither Boy version 6 is a complete rewrite of the app. Every part of the software got redone, changed, or optimized, including areas that behave similarly to earlier versions. The update targets faster iteration in the viewport. Algorithm browsing can now be stepped through with arrow controls, and common tweaks like brightness, contrast, saturation, midtones, and highlights are designed to update faster while you work. Blur and the D noiseise control can take longer to refresh because they are heavier effects combined with the rest of the stack.

There is also a new playback and update behavior control at the bottom of the viewport with three modes labeled full, live, and still. In a debounce style mode, the viewport waits until you stop moving a slider before it updates, which aims to help on older machines or when other heavy apps are open. That setting also appears in the settings area.

Updating and support without spelunking

Version 6 introduces a new update path tied to a web account. Signing into the website account and opening orders reveals a refresh software button that checks whether download links have been updated, then provides the new link when a newer version exists. The older update flow still exists inside the app. The help menu includes check for updates, which asks for your info to retrieve the update.

Color workflows move into the app

Version 6 expands the palette system with a source palette category intended to keep the colours of the original image closer to the output. Multiple options exist inside that category, and a complete option is presented as a strong starting point for retaining source colours.

Once you start from those source colours, the palette remains editable. Individual swatches can be adjusted,d and the image remaps live while you work. The broader palette system still includes importing and exporting palettes and allows editing colour depth and other related controls.

Controls previously handled in a companion palette app named Color Cat have been migrated into the main app interface in version 6. The companion tool may return in the future. // Not independently verified at press time.

There is also a quality-of-life feature for palette shuffling. Each swatch has a lock toggle. When you lock a color, then shuffle, that locked swatch stays while the rest randomize. The same lock and randomize idea applies to adjustments. You can lock an adjustment and randomize others.

Effects become a stack you can reorder

The effects workflow in version 6 shifts from a set of toggles to an add system. A plus control adds an effect by choosing it, rather than enabling everything at once. The stack is reorderable. Effects can be moved up or down in the pipeline and the viewport updates to reflect the new order. This ordering also interacts with animation.

Named effects called out for stacking include Epsilon Glow, JPEG Glitch, and Chromatic Aberration. Blur and sharpen are also described as post processing effects within the stack. The official product description states the app includes 63 dithering algorithms and supports stacking and reordering effects. Marketing claims appear in official copy around exclusivity and uniqueness of algorithms. Treat those as marketing claims, not measurable guarantees.

Animation arrives without needing a video file

Version 6 adds animation inside the app. You can animate from a still image without importing a video file, while video import remains supported. There are two ways to switch a still workflow into animation mode. One is a file menu option called convert to animation. The other is a still toggle near the bottom controls that switches you into animation mode. In animation mode, a timeline appears at the bottom of the interface.

Playback offers a quick mode and a rendered mode. Rendered mode loads frames for accurate playback and can display a settings changed warning because frames need to be prepared. Playback can also be set to looped. Animation is created by adding an animation layer, then selecting a category and property to animate. Adjustments are one such category, including brightness. An animation layer defines a from value and a to value, and offers ease methods including ease in, ease out, and linear. Multiple animation layers can be sequenced on the timeline to build a loop.

When a property is animated, the matching control becomes locked in the panel to prevent manual edits from fighting the animation. Exporting an animation is handled through an export video action, which processes frames and renders a video from the animated still image plus the active settings and effects stack.

Temporal Variation and better video handling

Version 6 introduces a new animated effect called temporal variation. It applies animated noise patterns to the input image, and nine controllable patterns are described. This effect is positioned as inspired by retro screens. Live video playback and preview are also added to the app in the 6.0 update as a free update.

Pricing and licensing

Pricing for Dither Boy is listed at £45.00 on the official product page, with an original price shown as £60.00. Delivery is an instant download access after checkout, also it is just one purchase that includes all future updates and no subscription is required.

If you ship animations or shortform clips, run a quick test suite before you commit. Try your typical content, your typical resolution, and your typical export formats, then review the results in the exact viewers and encoders your pipeline uses. That kind of boring discipline saves you from exciting surprises in prodcution.

https://studioaaa.com/product/dither-boy/

The post Dither Boy 6.0 brings animation and video polish first appeared on DIGITAL PRODUCTION and was written by Bela Beier.