Updates

OTOY Studio now includes five new Gaussian Splat pipelines for 3D reconstruction from images or video, plus streamlined bulk image inputs and a refreshed model catalog for Any LLM and Any VLM nodes.

Gaussian Splat pipelines

Five new canvas nodes under the 3D category reconstruct photorealistic 3D Gaussian splats from connected images or video: GSplat, Neural Harmonic Textures, GSplat 2DGS, InstantSplat, and Sharp. Each pipeline accepts up to 500 images via Element Builder or a video input, with live cost estimates displayed before running. Outputs include splat files, meshes, and rendered videos.

Bulk image inputs via Element Builder

Element Builder now supports up to 500 images, replacing the previous per-image Import node sprawl for large captures. Multi-selecting images automatically creates a single Element Builder node when you select five or more—keeping the canvas clean while preserving all inputs. Downstream nodes like Gaussian Splat and Kling consume the full image set from the element output.

Refreshed Any LLM and Any VLM models

The existing Any LLM and Any VLM nodes now route through updated backends with refreshed model catalogs. Any LLM includes Claude Opus 4.8, GPT-5.5, Gemini 3.5 Flash, Grok 4.3, and others. Any VLM adds vision-language models like GPT-5.5 Pro, Gemini 3.5 Flash, and Qwen3 VL. Existing nodes continue working without changes.

Quality of life

• On the canvas: Confirm before navigating to Jobs or Asset Library while editing a project.
• On the canvas: Smoother loading experience with no empty-state flash.
• In the asset library: Reverse sort order toggle now available on the Projects tab.
• Uploads: HEIC files automatically convert to JPEG across all upload surfaces.
• Billing: Top-up payments now surface in the Invoices section with Stripe-hosted receipts.

This release adds a streamlined billing path for new subscribers.

This release adds Luma Ray 3.2 with HDR video generation, Seedance 2.0 in 4K resolution, and improves media validation for Kling models. Downloads now use the browser’s native download manager for better progress tracking.

Luma Ray 3.2 with HDR and EXR export

Luma Ray 3.2 is now available as a unified video generation node that automatically routes between text-to-video and image-to-video modes based on your inputs. The model supports HDR video generation and EXR frame sequence export for high dynamic range workflows. When you enable HDR and EXR options, the EXR download appears alongside the MP4 in both the node preview and media lightbox. Note that HDR/EXR features require HDR entitlement on your Luma account, and certain parameter combinations like HDR with Loop are mutually exclusive.

Seedance 2.0 in 4K resolution

Seedance 2.0 now supports 4K (3840×2160) resolution for standard-tier generations. The resolution selector includes the new 4K option alongside existing resolutions, with pricing automatically calculated based on pixel count. Note that 4K resolution is not available when Fast Mode is enabled.

Input validation for Kling video models

Kling video models (v3 image-to-video, o3 image-to-video, and o3 reference-to-video) now validate image inputs before submission to prevent server-side failures. Uploaded images must be under 10MB, at least 300×300 pixels, and have an aspect ratio between 0.4 and 2.5. Invalid inputs will show warnings when you attempt to run the generation.

Quality of life

• Downloads: File downloads now use your browser’s native download manager with progress tracking and pause/resume support
• Node organization: Image and video nodes are now organized more logically in the add-node menu with primary models appearing directly under their modality
• Topaz nodes: Topaz upscale nodes have been moved to Image Tools and Video Tools categories with updated labels and icons

Otoy.studio has a fresh coat of paint. There are a few changes worth knowing about.

The legacy otoy.studio website is now located at sandbox.otoy.studio and is unchanged — everything you had there continues to work as before.

The new otoy.studio, accessible at app.otoy.studio, is a rebuilt product and requires a new subscription. It does not utilize the old billing methodologies, so your previous billing details do not carry over.

If you have any questions about the transition, reach out at support@renderlabs.com.

This release adds Topaz Upscale for images and videos, a Video Compare node, and multi-select asset picking for workflows that need many inputs. You can now see detailed progress for multi-stage jobs and automatically load more assets as you scroll.

Topaz Upscale for images and videos

Add Topaz Upscale nodes from the Image Tools or Video Tools sections under their respective modality categories. The image upscaler works on a flat rate, while video upscaling cost scales with the duration of your input clip. Video outputs default to H.264 for broad compatibility, with H.265 available as an option for smaller file sizes.

Video Compare node

Compare two videos side-by-side with a draggable split slider. This standalone utility node uses the same comparison component as the SwitchX preview mode, now with improved synchronization that keeps both videos aligned during playback and seeking.

Multi-select asset picker

When adding images to a multi-input handle—like those on Gaussian Splat nodes—you can now select multiple assets at once. Use shift-click or the select-all checkbox to pick many images, then attach them all in a single action. Each image becomes its own Import node connected to the handle.

Inline status timeline for multi-stage jobs

Jobs that report progress through distinct stages—such as Gaussian Splat’s booting, COLMAP, training, rendering, and uploading—now show an inline timeline below the node. Completed stages display with their duration, while the active stage shows a live elapsed time. Single-stage jobs continue to show the standard status text.

Quality of life

• Asset library: Pages now load automatically as you scroll near the bottom, in addition to the existing Load More button.
• On the canvas: When “Show connected inputs” is enabled, selected nodes also display a read-only preview of their primary prompt.
• Large assets: Signed URLs for 3D outputs and other large files are now cached, preventing re-downloads when panning through the output carousel.
• Image tools, video tools, and 3D utility nodes have moved from the Utility section to their respective modality categories (Image, Video, 3D) for quicker access.

We’ve added support for Decart Lucy 2 and Lucy 3 in OTOY Studio’s Realtime nodes. Both models are available today across all Studio plans.

What’s new

Realtime nodes let you stream live generation output directly into your canvas — prompts resolve as you type, reference inputs update on the fly, and changes propagate through downstream nodes without a manual trigger. The workflow is less about discrete generation steps and more about continuous refinement.

Decart’s Lucy models were built for exactly this kind of tight feedback loop. Lucy 2 offers low-latency responses with strong prompt adherence, making it well-suited for iterative exploration where you’re adjusting composition or style on the fly. Lucy 3 extends that with higher output fidelity and better handling of complex scenes — useful once you’ve locked a direction and want to push the detail.

How to use them

Open any canvas workflow and add a Realtime node. In the model selector, you’ll now see Lucy 2 and Lucy 3 listed alongside existing real-time options. Connect your prompt, reference image, or control inputs as usual — the node will stream output using whichever Lucy model you’ve selected.

Both models support the same input types as other Realtime nodes: text prompts, image references, depth maps, and mask inputs. Existing workflows that use Realtime nodes don’t require any changes; you can swap the model in place and the rest of the graph stays intact.

When to use each

Lucy 2 is the right default for early-stage exploration — the latency is low enough that you can scrub through prompt variations in real time and get a clear read on what the model responds to.

Lucy 3 is better suited to the refinement pass: once the composition and style are locked, it produces output detailed enough to use as a strong base for any downstream upscaling or post-processing nodes downstream.

Both are available now. Open Studio and give them a try.

This release introduces durable server-side orchestration for multi-node runs, a new empty-canvas preset picker, and Alt+drag duplication for faster canvas workflows.

Durable server-side graph runs

Multi-node runs now optionally execute server-side, making them resilient to browser tab closure or navigation. When enabled via the server-graph-runs feature flag, the server orchestrates the entire run sequence—dispatching each node job and advancing the workflow automatically as jobs complete. This ensures long-running processes continue even if you close the window or navigate away from the canvas. Runs appear in the same interface with real-time status updates, and can be canceled at any point.

Empty-canvas preset picker

New users now see a curated selection of starter presets when opening a blank canvas. Choose from single-click defaults for each modality: Generate Image, Generate Video, Generate 3D, or Generate Audio. Each preset drops the recommended model for that modality directly onto the canvas, providing an immediate starting point without needing to browse the full node library. The picker automatically dismisses when you add any node or press Escape.

Alt+drag to duplicate nodes

Hold Alt (or Option) while dragging selected nodes to create duplicates Figma-style. The original nodes move with your cursor while copies remain in their starting positions. This uses the same duplication logic as Ctrl+D, preserving all connections, widget states, and styling. The entire duplicate-and-move operation is batched as a single history step for easy undo.

Quality of life

• Asset sidebar now mirrors the library modal layout at wider widths, with folder tree and two-row toolbar
• Hunyuan3D 3.1 node picker labels now distinguish between image-to-3D and text-to-3D endpoints
• Long child node titles in group parameter panels now properly truncate with ellipsis
• OTP code fields are now visible in dark mode
• Asset cards show “Source unavailable” for expired signed URLs instead of endless loading
• Plans tab CTA buttons now share consistent vertical alignment across all tiers

This release introduces hierarchical job lineage tracking, multi-node graph execution, and the ability to pipe any job output as input for new jobs. You can now run selected canvas nodes sequentially and explore job history with per-version diffs.

Hierarchical job lineage

Jobs are now grouped by lineage in a new List view on the jobs page. Each lineage collapses to a single row showing the latest version, which expands to reveal a nested tree of ancestor jobs with per-version diffs and thumbnails. The lightbox navigates through the visible expanded set, making it easy to track iterations and compare changes across versions.

Use any output as input

Right-click any image, video, audio, 3D model, or text output on a job card and select “Use as input” to pipe it directly into your next run. If your current model doesn’t accept the output type, the model picker will automatically open with compatible options filtered and ready. The system preserves lineage when piping outputs, treating the source job as the parent of the new submission.

Sequential multi-node runs

Select multiple connected nodes on the canvas to run them sequentially in dependency order. A new selection-run panel shows the execution plan with per-task costs and a total estimate. Connected chains run upstream to downstream with fresh inputs resolved from the graph store, while independent components run concurrently. Failed nodes skip their dependents, and you can run the entire selection multiple times with regenerated random seeds.

Output history (beta)

Behind an opt-in flag in Preferences → Canvas, nodes can now browse their output history across past runs. This experimental feature lets you cycle through previous outputs while maintaining downstream connections, though it’s currently dark until several UX questions are resolved.

Quality of life

• Auto-generated titles now apply to nodes run via the multi-node selection panel
• Batch-reconnect ghost links render correctly even when endpoints are scrolled out of view
• Video model families are reordered with Kling O3 and 3.0 separated into distinct groups
• The navigation rail includes quick-launch shortcuts for Image, Video, 3D, and Audio modalities
• Page titles now follow the format “Page Name | OTOY Studio”

This release focuses on media playback reliability for older jobs and fixes a display issue for custom models.

Quality of life

• Media from older jobs with legacy URLs now loads correctly in the feed.
• Custom model jobs are now clearly marked with a badge in the jobs list.

This release introduces a redesigned model picker with favorites and modality filtering, plus a new default for dimming unselected edges on the canvas.

Model picker with favorites and modality filtering

The model picker has been redesigned from a scrolling popover into a full modal dialog with improved organization. You can now filter models by modality using the left rail, which includes categories for All, Favorites, Video, Image, Audio, 3D, Text, and Utility. Each model row includes a star icon that lets you mark favorites, which persist across sessions and appear in the dedicated Favorites filter category. The search functionality now displays results as a flat list with breadcrumbs showing the modality and model family.

Dim unselected edges enabled by default

The canvas now dims unselected edges to 25% opacity by default, helping you focus on the currently selected nodes while maintaining context of your overall workflow. This setting has been promoted from experimental to stable status in Preferences, where you can toggle it on or off based on your preference. Existing user settings remain unchanged—only new users and those who hadn’t adjusted the setting will see the new default behavior.

Quality of life

• Straight edges between aligned nodes now render correctly with their gradient styling
• Unselected edges maintain consistent visibility when dimmed, making complex workflows easier to navigate