We install and run the generators ourselves — from 3D models and video to sound effects. We write down how much VRAM each needs, what runs on CUDA and what works on Apple MPS and AMD ROCm, which is open source and which is a cloud subscription.
We read visitors’ search queries and write about them — ask right here.
“a clay teapot
with a faceted lid,
low-poly”
“rain on a tin roof,
distant thunder”The illustrations are AI-generated — examples of what the catalogued tools do, not their live output. Memory thresholds come from the fact sheets.
What runs locally
The whole tool database →Pick a type, a chip — CUDA, Apple MPS or AMD ROCm — and a VRAM ceiling. What remains are the models that actually start. Requirements are as described by the authors, with a source and check date for every value.
| Tool | Type | Runs | VRAM | Backends | Formats |
|---|---|---|---|---|---|
| LTX-Videoimage-to-video | Video | open source | from 1 GB * | Apple MPS | — |
| ChatTTStext-to-audio | Audio | open source | from 4 GB * | — | — |
| Zero123++ | 3D | open source | from 5 GB * | — | — |
| Stable Fast 3Dimage-to-3d | 3D | open source | from 6 GB * | CUDAApple MPS | glb |
| threestudio | 3D | open source | from 6 GB * | CUDA | obj |
| TripoSRimage-to-3d | 3D | open source | from 6 GB * | CUDA | — |
| MMAudio | Audio | open source | from 6 GB * | CUDA | — |
| FramePack | Video | open source | from 6 GB * | CUDA | — |
Showing the most accessible by VRAM threshold. Cloud services need no VRAM — they need a subscription: they are in their own list.
AI news — every day
The whole feed →
2026-09-15
MoE-JEPA boosts V-JEPA with a mixture of experts for synthetic image detection
Researchers presented MoE-JEPA, an architecture for detecting generated and manipulated images based on V-JEPA 2 with an added Residual Mixture-of-Experts and a…
Fresh arXiv papers and model releases — briefly, with a note on what you can already run yourself.
From points to a model
This is how every 3D generator works: first a point cloud, then a surface, then materials. Click and we show it step by step. The page stays light when opened: the frames load only when you ask.
The frames load only now, not when the page opens. They are AI-generated illustrations — a real viewer will appear when our “3D from a picture” tool goes live.
Fresh generator reviews
LatestMost read
habitat-gs: 3D generator — what it does and what you need to run itHabitat-GS is an open source 3D generator from ZJU3DV. It is designed to create highly detailed scenes and dynamic avatars based on Gaussian splatting…
OOOSplat: 3D Generator — What It Does and What You Need to Run ItOOOSplat is an open-source local 3D generator from ooolab. It turns ordinary videos or image sequences shot around an object into 3D Gaussian Splattin…
MoE-JEPA boosts V-JEPA with a mixture of experts for synthetic image detectionResearchers presented MoE-JEPA, an architecture for detecting generated and manipulated images based on V-JEPA 2 with an added Residual Mixture-of-Exp…
llama.cpp v0.4.1: support for Maple 20B-A1B, Tencent Hy 4 and Spark2.5The llama.cpp v0.4.1 release came out on September 14, 2026. The update adds support for three new architectures: Maple 20B-A1B — a ternary MoE for CP…