For those who don’t know the tool: Beeble builds AI relighting and video transformation tools for VFX, post, and virtual production, and Canvas is its very new node based environment that wires SwitchX and SwitchLight into repeatable shot workflows.

A node graph, but for AI outputs you can wrangle

Canvas lands as a node based AI compositing environment aimed at complex workflows across VFX, post, and virtual production. The pitch is straightforward: put AI video models, compositing utilities, and workflow automation into one visual system so teams can iterate across multiple shots without rebuilding the same logic over and over.

In practical terms, it targets the part of the job where you already juggle plates, masks, reference stills, and multiple look directions, then repeat that dance across a sequence.

What is actually in the box

Canvas presents itself as a node graph workflow editor for final render, with a catalog grouped into Input, AI Tools, Edit, and Utility. Input supports text prompts plus image files in PNG, JPEG, or WebP, and video files in MP4 or MOV. In other words, it starts where most editorial and comp workflows already start: media in, decisions next.

https://digitalproduction.com/2026/05/20/beeble-canvas

The AI Tools section includes a node for SwitchX, the same model as the standalone product, with source and alpha handled as video inputs. It also includes an LLM node that can generate files from a prompt with up to four media inputs, plus image generation and video generation nodes that can route to external models. For rotoscoping style work, Canvas includes a Video Matte node that outputs an alpha matte plus RGBA, with an automatic mode and an interactive selection mode, plus options aimed at general footage and green screen keys.

On the classic comp side, the Edit nodes cover the expected utility moves: extract a frame, trim, crop, resize, curves, invert, flip, and morphology operations like erode and dilate. Utility nodes cover housekeeping: sticky notes, routing for cleaner graphs, a viewer, side by side compare, and export. It’s not fully Nuke yet, but…

That combination matters because it lets artists keep the media prep and look development steps next to the model calls, instead of bouncing between separate tools and hoping filenames stay honest.

Relighting and PBR passes, now wired into the graph

The system includes access to SwitchLight for generating physically based rendering passes. In the Canvas node catalog, the VFX Pass Generator extracts PBR material maps including BaseColor, Normal, Depth, Roughness, Specular, and Metallic from image or video using SwitchLight 3.0.

That puts relgihting adjacent tasks into the same graph where you also assemble mattes, feed references, and generate variations. It also matches the stated intent of supporting controllable, iterative pipelines across multiple shots, not one off experiments.

Automation, batches, and the part everyone really wants

Canvas claims to be built around repeatability: build workflows once, apply them to shot sequences, and automate iteration without rebuilding node logic shot by shot. It also calls out batch processing and maintaining scene consistency across projects.

Those claims describe the correct pain point. Anyone who has ever reconnected the same five nodes fifty times will understand why a programmable layer matters. Still, treat the automation story like any new tool claim: test it in your own pipeline with your own edge cases before you bet any delivery on it.

The API angle: SwitchX in your pipeline, with pricing details

SwitchX API for video transformations in YOUR pipeline

Alongside Canvas, the SwitchX API is positioned for studios and developers who want to integrate video transformation and relighting capabilities directly into custom pipelines and software environments.

The developer portal offers a REST style workflow with uploads, job creation, and polling, and it explicitly supports 720p and 1080p output. It also has pay as you go credits in US Dollar, and pricing can start at $0.10 per generation. That pricing applies to the API offering as described there, while Canvas pricing is not specified, since it is part of Bebble Online.

Beeble Studio: 4K AI relighting on YOUR desktop

Availability, media assets, and credits

Canvas is available now via the Beeble platform, with a launch video hosted on YouTube (The Video we embedded above…) .

The boring but necessary reminder

New tools and innovations should be tested before use in production, especially when they touch shot consistency, automation, and delivery formats. Run a small sequence through, break it on purpose, and see how it fails before you trust it on a deadline.

https://docs.beeble.ai/beeble/canvas
https://docs.beeble.ai/beeble/overview

The post Beeble Canvas first appeared on DIGITAL PRODUCTION and was written by Bela Beier.

Seamless 3D & AI Integration

The foundation of AI Render is built on Reallusion’s custom node for ComfyUI, enabling a seamless two-way connection between your AI workflow and Reallusion’s 3D tools. It transfers full 3D scene data—character poses, lighting, camera angles—from iClone and Character Creator, with no technical setup. Fully embedded in iClone and CC’s intuitive UI, it allows visual, interactive work while generating AI content with precision and control.

22 Built-In Style Presets

AI Render includes 22 professionally tuned presets across three categories: Realistic, 3D stylized, and 2D illustration. Each preset comes with optimized ControlNet settings, prompt templates, and rendering configurations for fast, consistent results.

Prompt + Reference-Based Customization

Users can guide AI results using traditional text prompts or reference images. The plugin supports IP Adapter, which allows AI to match the style and tone of any uploaded image without the need for complex prompt engineering.

Precise 3D ControlNet Guidance

Unlike AI tools that rely on 2D estimations, AI Render uses 3D-driven ControlNet inputs for stable, accurate generation across frames:

• Depth: Spatial layering and facial accuracy
• Pose: Reliable skeletal tracking, even with occlusion
• Normal: Surface lighting and shading
• Edge (Canny): Clean outlines for stylized renders

All inputs are generated directly from real-time 3D environments built in iClone and Character Creator, using Reallusion’s library of over 13,000 easily searchable, drag-and-drop assets, including characters, motions, lighting, and cameras. This makes it fast and intuitive to build structured scenes that provide AI with the consistent, frame-by-frame guidance it needs.

LoRA Dataset Creation for Character Consistency

To maintain consistent character appearances across AI videos, LoRA (Low-Rank Adaptation) training is supported. AI Render does not perform training directly but enables rapid dataset creation in iClone using batch rendering, pose libraries, and automated camera paths. Reallusion will provide project templates to assist in generating LoRA training sets for unique characters.

AI-Powered Storytelling for Character IP

AI Render is ideal for creators developing original IP characters. With Character Creator and iClone, users can design fully rigged, production-ready characters. It enables AI-generated movies, commercials, and storytelling, maintaining consistency in look and style. This isn’t just visuals; characters can now appear in AI content with real actor-like continuity and expressiveness.

Community Challenge: Win Character Creator 5

To celebrate the launch, Reallusion is hosting a public AI Makeover Challenge from July 28 to August 29, 2025. Participants can transform their Character Creator 4 (CC4) characters using AI Render and submit images or videos for a chance to win a free copy of Character Creator 5 (CC5). Check out the official discussion thread for more details.

Visit the Reallusion Official Forum now to download AI Render, follow setup guides, and connect with the community.

Reallusion Inc. provides innovative 3D character creation and animation platforms for entertainment, Metaverse, digital twinning, and AI simulation. Their flagship products—iClone, Character Creator, and Cartoon Animator—enable scalable digital human development across creative and industrial projects.

The post AI Render for iClone & CC with ComfyUI Integration, Available in Open Beta first appeared on DIGITAL PRODUCTION and was written by Bela Beier.

Available systems with artificial intelligence (AI) play to their strengths in different ways when creating images and videos. AI artists therefore use different solutions depending on the workflow. With “Flora Fauna AI”, you get a solution that combines popular AI systems and lets them interact with each other via a node network. No installation is necessary as the software runs completely in a compatible browser. Images and videos can be loaded into the workspace via the import function.

Nodes for text, images and videos are available for use. Notes can be inserted and linked in the workspace with a click of the mouse. Navigation in the network is simple and has many similarities to CG packages. Notes can also be inserted in boxes to describe the workflow. Work in groups is provided for and existing projects can be shared.

Nodes in Flora Fauna AI

Text nodes are a way to improve your own prompts, but also to analyse images. This can be style or colour schemes. This information can be incorporated into the process when generating and modifying motifs. This enables style transfers or the colouring of images or videos, for example. The user can choose from various AI modes for the text nodes:

• Claude 3 Sonnet
• GPT o4 mini
• Google Gemini 2.0 Flash

To create still images, simply type a prompt into the input field of the image node and start the calculation. Text or other images can also be used as input during this process. Two images with people can be combined to create completely new scenarios. The style option makes it easy to automatically change the result. This creates a great deal of flexibility when working.

The nodes can be quickly duplicated for different variants and the parameters or the AI engine for the calculation can be changed. “Flora Fauna AI” automatically generates variations of an image on request. When calculating the images, the system has support for various AI engines, including

• Flux Dev and Flux Pro 1.1
• Ideaogram 2.0
• Luma Photon
• Recraft V3 Stable Diffusion 3.5

If an existing image is linked to an image node, the context changes. The existing information can optionally be displayed with Google Gemini 2.0 Flash, Flux Canny, Flux Depth and Flux Redux. There is also an option to remove the background. In practice, the user can quickly change the perspective or view with “Gemini 2.0 Flash”, for example. Useful if you need different frames for video production later on.

The production of videos is part of the programme’s range of functions. This can be a simple prompt or you can combine images or descriptions via the node network. Depending on the instructions, the selected AI generates the clips. For the calculation, the user can choose between

• Hailou Minimax
• Kling 2.0 / Kling Pro 1.6 / Kling 1.5
• Luma Ray 2 / Luma Ray 2 Flash
• Pika
• Runway Gen-3 Alpha
• Tencent Hunyan
• Lightricks LTXV
• Google Veo2
• WAN 2.1

Create your own styles

Since the end of March 2025, the available styles for creating images can be expanded with your own entries. To do this, the user uploads a series of 20 to 30 images to “Flora Fauna AI”. Their content determines the new style. Training is started with one click and the style appears in the list after a short time. It is important here not to violate copyrights. The controversy surrounding the “Studio Ghibli” style in images and videos when “OpenAI ChatGPT 4o” was released shows how polarised this topic is.

Conclusion

With “Flora Fauna AI” you get a useful AI workspace for a wide range of tasks. The system can help with the development of designs, storyboards or concepts for games. The node network makes the work flexible and is a great help for the presentation of designs. Thanks to the broad support of various AI systems, there is no need to switch between different offers. The styling allows the generation of completely individualised images and videos. Many tasks can be realised directly in a project. “Flora Fauna AI” also eliminates the need to manage different subscriptions because the service manages the various AI systems under one roof.

Featured image: © Flora Fauna AI

The post AI-Workspace: Flora Fauna first appeared on DIGITAL PRODUCTION and was written by Jörn-Erik Burkert.

Adobe has released an update for its Premiere Pro software, integrating advanced AI features that promise to shorten video editing workflows. Central to this release is the incorporation of Adobe’s Firefly video model, an AI-driven toolset designed to simplify various stages of video production.

Adobe’s latest update also introduces the ability to adjust clip duration seamlessly using AI, making it easier to tweak the length of footage without losing important moments. If an Artist needs to add or remove a few seconds from a sequence, Premiere Pro now uses Firefly’s AI to intelligently fill or stretch the video to cover gaps, maintaining the flow without requiring complex manual edits. This is particularly useful in fast-paced edits where timing adjustments are common.

The newer Firefly models are noticeably faster, delivering results almost instantly, even on high-resolution video footage. This speed improvement means Artists spend less time waiting for renders or previews and can experiment with more creative options within tight production schedules.

Lastly, the update includes AI-driven tools for removing unwanted objects or distractions from video scenes. Whether it’s a microphone boom sneaking into the shot or an errant passerby in the background, Firefly analyzes the footage and automatically removes these elements while preserving the surrounding details, making cleanup work much simpler and less time-consuming.

Firefly, already familiar to many Artists from Adobe’s graphic and design tools, now extends into video with this new version. Firefly in Premiere Pro allows Users to generate, refine, and adapt video content using text prompts, effectively automating tasks that would otherwise require hours of manual labor. Adobe markets it as an innovation that will speed up production times, but for Artists, the real value lies in Firefly’s ability to automate mundane tasks while keeping creative control intact.

Another new feature in this update is the “Generative Fill” for video. This tool works much like its Photoshop counterpart, allowing Artists to fill gaps or remove unwanted objects from video scenes. Again, the workflow is text-based: you type in what you want, and Firefly suggests options. This feature is especially useful in post-production, where filling in backgrounds or adjusting objects can slow down projects.

Adobe has also introduced AI-Powered Color Correction, which uses machine learning models to analyze footage and suggest optimized color settings. This is an addition to the familiar Lumetri Color tools but aims to make the color grading process faster and more intuitive.

In terms of pricing, Premiere Pro continues with its subscription model. The standalone subscription costs $20.99 per month, with discounts available for those who bundle it with other Adobe Creative Cloud products. For professionals who want to test out the new features, Adobe offers a free trial version as well.

One key concern with any new tool is stability. While Adobe’s marketing highlights the benefits of AI-driven automation, Artists should approach these tools with caution. Early adoption of new technology always carries risks, especially when implementing them in active projects. Extensive testing is recommended before deploying Firefly-generated assets or relying on AI color correction for final deliverables. The tools show promise, but stability remains critical, particularly for professionals handling tight deadlines and high-profile projects.

For detailed information, Adobe has provided comprehensive documentation on the new features, accessible through the official Adobe Premiere Pro documentation. Those interested in the Firefly AI model can also check out Adobe’s Firefly page. While the excitement around new technology is high, experienced Artists know that adopting tools like Firefly must be balanced with caution, ensuring that new efficiencies don’t compromise quality or stability.

(P.S: The other Updates of Adobe during their Event Adobe Max will come in the next few days – we just started playing around with the new Frame Io, and haven’t even touched the other tools. )

The post What you need to Know: Premiere Integrates AI Video Generation first appeared on DIGITAL PRODUCTION and was written by Nils Calles.