Apple research model that generates 3D assets with view-dependent appearance from a single input image.
Updated EU status checked Last shown
Sources: the vendor's own pages (linked above) and creator videos at the linked timestamps. EU status is information, not legal advice; see how we check.
LiTo (Surface Light Field Tokenization) is a research model from Apple that generates 3D objects from an input image while also modelling view-dependent appearance, such as reflections and lighting effects, rather than baking in a single static colour per surface point.
According to a YouTube creator summary, it was reported as more accurate than Trellis, and code and training scripts were said to be released. The official project page was only available as a redirect stub, so details on architecture, benchmarks, license and weights could not be verified from the provided material.
It is aimed at researchers and developers working on image-to-3D generation. No hosted product, pricing or app was identified.
Watch the moment: the exact second top creators show it. Videos load only when you press play, via youtube-nocookie.com.
Generates 3D models from an input image while capturing view-dependent appearance like reflections and lighting. Reported as more accurate than Trellis; code and training scripts released.
Closest neighbours by meaning, not just by category.
Model · Hi3D
Open-source image-to-3D and text-to-3D generation model from Hi3D, formerly Sparc3D, trained on ~2M curated 3D assets.
Model · Bria AI
Open-weights text-to-image model from Bria AI, fine-tuned from FIBO, supporting structured JSON prompts and image editing.
Model
Image-to-3D generator from Tsinghua and Tencent ARC Lab that builds meshes pixel-aligned to the input view.
Model · Bria
Bria's open-weights image generation and natural-language editing model with multi-reference support, non-commercial license.
App
Open-source desktop app that generates 3D meshes from images using AI models running locally on your GPU.
Model · Google
Google's Gemini 3.6 Flash-based image generation and editing model, succeeding Nano Banana 2.
