v3.20.0
This release strengthens platform security to protect user accounts.
This release strengthens platform security to protect user accounts.
This release introduces a new way to compose scenes around your 3D captures and adds a powerful video editing model to the canvas.
You can now open any Gaussian splat output directly in the 3D Scene editor to create a flythrough video. Use the “Build a scene around it” action on the splat output widget to launch the editor with your splat pre-loaded. The rendered MP4 will appear as an Import node connected to your original splat. This workflow complements the existing splat editor—while that tool focuses on rendering the splat itself at higher resolutions, the scene editor lets you compose your splat within a full 3D environment with primitives and eventually other assets.
A new Seedance 2.5 Video Edit node is now available. This node lets you edit existing videos using natural language prompts, similar to the Kling O3 workflow. Provide a source video and edit instructions, with optional reference images or audio for guidance. The node supports resolutions from 480p to 4K and includes synchronized audio generation by default. Pricing is based on your source video’s duration, with the final output matching the input clip length.
This release brings rendering directly from the SuperSplat editor, unified Kling O3 nodes, and smarter interface controls. You can now build scenes from 3D models and access context menus throughout the video compositor.
You can now render video flythroughs and still images directly within the SuperSplat editor. The Render Video and Render Still buttons appear in the editor header when these capabilities are available. Rendered outputs land on the canvas as new Import nodes, allowing you to use them in subsequent workflows without closing the editor. The editor’s own settings dialog handles resolution, codec, and projection options, keeping all rendering controls in one place.
A new “Build a scene around it” action is available on 3D model output widgets. This opens the Scene editor with the model pre-loaded, ready for camera animation and rendering. Once inside the editor, the Add button lets you pick additional assets like splats or other models from your library to combine in the scene. The rendered MP4 returns to the canvas as an Import node beside the original model.
The three separate Kling O3 nodes for text-to-video, image-to-video, and reference-to-video have been merged into a single unified node. The node automatically routes to the correct backend based on your connected inputs: reference images use the reference-to-video endpoint, a start frame uses image-to-video, and text alone uses text-to-video. Existing canvases with the old node types will migrate automatically.
Right-click context menus are now available throughout the video compositor editor. You can access actions on the layer list, timeline track headers, timeline clips, and viewport. These menus share the same action logic as the inspector buttons, ensuring consistent undo behavior.
This release introduces a new video generation model with extended capabilities and brings dedicated undo/redo to the Video Compositor editor.
A new Seedance 2.5 node is now available via WaveSpeed AI, offering text-to-video, image-to-video, and reference-guided generation. The model supports longer durations (4–30 seconds) at 480p and 720p resolutions with native audio generation. Duration selection has been updated from a dropdown to a slider with an accompanying number input for precise control.
The fullscreen Video Compositor editor now maintains its own undo/redo history, separate from the main canvas. Keyboard shortcuts (Cmd/Ctrl+Z, +Shift+Z, +Y) and toolbar buttons let you step through changes to layer properties, transforms, timing, z-order, and output settings without affecting your broader workflow history.
.ply files, matching the format available from node downloadsThis release adds 4K resolution support for Kling video editing, expands the Video Compositor with per-layer cropping and scaling modes, and improves element support in Kling workflows.
The Kling O3 Video Edit node now connects directly to Kling’s API 2.0 instead of using a fal.ai wrapper. This unlocks 4K resolution for video editing tasks — previously capped at 1080p. The Quality selector now includes Standard (720p), Pro (1080p), and 4K options, consistent with other Kling O3 generation nodes.
Existing workflows automatically migrate to the new node type while preserving quality settings. The native integration also supports the full Kling content specification, including base_video editing with proper audio handling constraints.
Add precise cropping to individual layers in the Video Compositor with a new on-canvas crop editor. Click the crop mode toggle in the inspector to reveal corner and edge handles that let you resize the crop rectangle while seeing the full source content dimmed outside the selection. The crop is applied before transformation, so rotated layers maintain correct cropping behavior.
Cropped content re-centers on the layer’s anchor point, and the transform gizmo, scaling presets, and size readout all operate on the cropped region rather than the full source.
Layers in the Video Compositor now support independent X/Y scaling with Fit, Fill, and Stretch presets. Toggle aspect ratio linking on or off to control whether scaling remains uniform or allows free distortion. Eight resize handles on the transform gizmo (corners and edges) let you interactively scale layers while maintaining the opposite handle’s position.
A live size readout shows the rendered dimensions in pixels, and quick-rotate buttons (+90°/–90°/reset) provide convenient rotation controls beside the rotation field.
@image_1/@element_1 tags that match Kling’s API requirements.ply files are automatically detected as splats or meshes based on their actual contentThis release introduces a powerful new Video Compositor for client-side video layering and adds MiniMax H3 video generation. The Image Compositor also gets a clearer label to distinguish it from its video counterpart.
Add a Video Compositor node to layer multiple video and image inputs into a single MP4 with AAC audio—all processed locally in your browser without using credits. The fullscreen editor provides a timeline with frame-accurate scrubbing, per-layer controls for blend modes, opacity, transforms, trimming, and positioning. Adjust output settings like resolution, duration, and frame rate before rendering. The compositor handles audio mixing from visible video layers and includes transport controls for previewing your edits.
Generate high-quality videos with MiniMax H3, now available via WaveSpeed. This model produces native 2K resolution video with stereo audio from text prompts, images, or reference videos. Find it under Video > MiniMax in the node menu.
Add markdown notes to your canvas and restore your preferred view when switching workflows. This release also brings advanced controls to Luma Ray 3.2 video-to-video jobs and improves asset management.
Add free-floating markdown notes to your canvas for documentation and collaboration. Notes are non-executable nodes that never enter the compute graph—perfect for explaining complex workflows to teammates. They support standard markdown formatting and maintain a sticky-note appearance with resizable dimensions.
The canvas now remembers your viewport position and zoom level for each workflow. When switching between projects, you’ll return to exactly where you left off, eliminating the disorientation of landing on empty space. The view state is stored per-device and adapts to your current window size.
Video-to-video jobs with Luma Ray 3.2 now expose per-signal conditioning controls and keyframe anchoring. Fine-tune pose, depth, normals, and trajectory signals individually, or pin guide images to specific frames using the new keyframe system. These advanced options appear when you set an explicit edit strength rather than using auto mode.
Asset selection now uses a single consistent model across the library. Selecting an asset automatically opens the details panel, while multi-selection shows bulk actions. The previous separate active item and multi-select states have been unified for a more intuitive experience.
This release sorts project favorites inline with the rest of your projects, creating a consistent experience across the app.
This release introduces a redesigned asset library toolbar and improves language detection to prevent crashes from browser translation features.
The asset library now features a refreshed toolbar with improved organization and clearer visual hierarchy. Sort options have been consolidated into a field picker with an attached direction toggle, while layout controls like thumbnail fit and card size have moved to a dedicated “View” popover. The toolbar adapts to different screen sizes, stacking vertically on narrow displays and splitting into two connected sections when space allows.
The app now properly detects browser language preferences and serves localized interfaces when available, preventing crashes that occurred when browsers attempted to translate the page. Users with browsers set to Japanese, French, Spanish, or Chinese will automatically see the app in their preferred language when those translations are available.
This release adds a new generative splatting node and resolves several workflow synchronization issues.
A new Gaussian Splat node lets you generate 3D splats from a single image using TripoSplat’s generative flow-matching model. Unlike reconstruction pipelines that require multiple input images, this creates a 262K-gaussian 3D scene in 1–2 minutes from just one photo. The node includes advanced diffusion controls for steps, guidance scale, flow shift, and seed parameters.