For the complete documentation index, see llms.txt. This page is also available as Markdown.

Release 0.14.0

NOTE

This release note includes all changes since 0.10.0 ! (we didn’t write release notes since then despite continuing releasing, so here goes a longer one).

Release Date: January 2026

Previous Version: v0.10.0 (December 1, 2025)

This release includes 137 commits with major improvements across nodes, AI assistant capabilities, UI/UX, pricing infrastructure, and backend architecture.


1. New Nodes & Backends

3D Generation & Mesh Processing

  • Multi-view to 3D Node – Converts multi-view images into 3D meshes with support for multiple backends

  • Fast Image to 3D Node – Quick image-to-3D conversion for rapid prototyping

  • Depth Estimation Node – Generates depth maps from images

  • Mesh Texture Extraction & Application Nodes – Extract textures from meshes and reapply them

  • Remesh Node – Refactored to support multiple backends (Hunyuan, Trellis2, etc.)

  • Preview Mesh Compression – Optimized mesh preview delivery

  • Hunyuan Parts Node – Separates 3D object parts using Hunyuan

  • Meshy Lowpoly Backend – Added support for low-poly mesh generation

Experimental Humanoid Animation Pipeline

  • Rig Humanoid Mesh Node – Automatic rigging for humanoid 3D models

  • Animate Rigged Mesh Node – Apply animations to rigged humanoid meshes

  • Split Character Sheet Node – Splits sprite/character sheets into individual frames

Image Generation Models

  • FLUX.2 Family – Added FLUX.2 Max, Turbo, and Flash models

  • ImagineArt 1.5 Pro Preview – New image generation backend

  • Z-Image & P-Image Family – Integrated additional image generation models

  • Kling O1 Image – Added Kling O1 image generation support

  • GPT-Image 1.5 – Upgraded with precise pricing support

  • Hunyuan Image 3.0 Instruct – Added Hunyuan Image 3.0 image generation support

  • Grok Imagine – Added Grok Imagine image generation support

  • Gemini Upscale Backend – Added preset with heavy image restoration

3D Model Backends

  • Hunyuan3D v3 & 3.1 – FAL backend with Tencent fallback

  • Trellis2 – New 3D generation backend

  • Hitem3D v2.0 – Upgraded backends with v1.5 retexture support

  • Other Multiview Backends – Extended multiview generation options

Utility Nodes

  • Extract Image Layers Node – Uses Qwen Image Layered for layer extraction

  • Video Models Update – Enhanced video generation capabilities

  • Image Description – Migrated to Gemini 3 Flash with minimal thinking


2. Conversational Agent / Assistant

Platform Agent (New)

  • Conversational Platform Agent – Fully revamped AI assistant that can help users build pipelines through natural language conversation

  • Agent Context Awareness – Improved understanding of platform usage and available features

  • API Export Awareness – Agent now understands and can guide users through API export functionality

  • Suggestion Engine Improvements – Better AI-generated node suggestions with output tokens limit

  • Vastly Improved Node Placement – Enhanced heuristics for AI-generated node positioning

Chat Interface

  • Auto-resizing Chatbot Textarea – Dynamic input field that grows with content

  • Revamped Sidebar – Cleaner integration of the chat panel with the main interface


3. UI Changes

Major Frontend Rewrite

  • Vue Flow Migration – Complete graph system rewrite using Vue Flow for significant performance improvements

  • Graph Speedup & Optimization – Faster node/edge rendering and manipulation

  • Tailwind CSS Integration – Modernized styling with Tailwind, removed redundant classes

User Experience

  • Onboarding Video Carousel – Interactive carousel with Stripe integration for new users

  • User Credit Management View – Dedicated interface for managing credits

  • Promo Banner System – Promotional banner with trigger logic

  • 3D Viewer Loading State – Visual feedback during mesh loading

  • Mesh Preview Pending Spinner – Loading indicator for mesh previews

  • Mobile Lock Page – Improved mobile experience with lock page

  • Subscriptions Order & Labels – Better organization of subscription tiers

  • Page Editor Colors – Enhanced visual differentiation

  • Frontend Restyle – General UI polish and consistency improvements

  • Contact Us Button – Added to TosFooter component

  • Legacy Stop Button Removed – Cleaned up deprecated UI elements

Performance

  • Browser Cache Headers – Added caching for file endpoints

  • Removed Loading Hint – Removed "This may take a few seconds to load" unnecessary message


Migration Notes

  • Breaking Changes: None expected for end users

  • API Changes: The exported API now uses billing; ensure adequate credits

  • Performance: Frontend graph operations should be noticeably faster due to Vue Flow migration

New Experimental Nodes

(These nodes need to be enabled by request)

  • Mesh Multi-View Render Node – Renders meshes from multiple viewing angles

  • Multi-View Projection Node – Projects multi-view images onto mesh surfaces

  • Occlusion Baking Node – Bakes ambient occlusion into mesh textures

Contributors

Thanks to all contributors who made this release possible across 137 commits spanning almost 2 months of development.

Last updated