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 →
2026-10-15
Tencent releases Hy-Memory-30B-A3B for external memory of AI agents
Tencent Hunyuan has published the Hy-Memory-30B-A3B model on HuggingFace with the text-generation task. It is a compact model with roughly 3B active parameters…
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
Tencent releases Hy-Memory-30B-A3B for external memory of AI agentsTencent Hunyuan has published the Hy-Memory-30B-A3B model on HuggingFace with the text-generation task. It is a compact model with roughly 3B active p…
Wind Comic v13.0.0 fixes aspect ratio at all generation stagesThe wind-comic tool has released Wind Comic v13.0.0. The release collects 13 intermediate versions from September 30 to October 9, 2026, plus this rel…
Microsoft releases UserRepGen-4B — a user description generator for simulatorsThe microsoft/UserRepGen-4B model with the text-generation task has been published on HuggingFace. It is a fine-tuned Qwen3.5-4B that, from a multi-tu…
Hermes Agent 0.22.0: Threshold release with local llama.cpp and guided setupOn October 14, 2026, Hermes Agent 0.22.0 — "The Threshold Release" — was released. It is an agentic environment from Nous Research with a built-in lea…