CPU3DAI tools for 3D, video and audio

AI tools on AMD ROCm

VRAM thresholds, backends and licenses come from the tool fact sheets: every value is collected by code from an official source and stamped with the date it was checked. Requirements marked with an asterisk * are the authors’ own description, not our measurement. Details are on each tool’s page.

TypeAll3DVideoAudio
RunsAllOpen sourceCloud
BackendAnyCUDAApple MPSAMD ROCm
VRAMAnyup to 6 GBup to 8 GBup to 12 GBup to 16 GBup to 24 GB

Showing 3 of 68

ToolTypeRunsVRAMBackendsFormats
Hunyuan3D 2.1 without CUDA (Mac and AMD)3Dopen sourcenot statedApple MPSAMD ROCmobj, glb, ply, stl, fbx, dae, 3mf
F5-TTStext-to-speechAudioopen sourcenot statedAMD ROCm—
MOSS-SoundEffect without CUDA (Mac and AMD)Audioopen sourcefrom 8 GB (8–10 GB) *Apple MPSAMD ROCm—

Cloud services — no VRAM needed

They compute on their own servers, so a hardware filter does not apply to them.

Luma GenieGeneration and editing of video, images, audio, and text using AI agents3Dcloudcloudnot neededJPG
Masterpiece XGeneration of 3D scenes and assets using AI3Dcloudcloudnot needed—
Meshytext-to-3D, image-to-3D, AI texturing, image generation, animation3Dcloudcloudnot neededGLB, FBX, OBJ, USDZ, STL
Polycam3D scanning, generation of 3D models, floor plans, reality capture3Dcloudcloudnot neededGLTF, OBJ, FBX, DAE, STL, USDZ, …
Rodintext-to-3D, image-to-3D, text-to-image, image-to-video, 3D avatar generation, texture generation, HDRI generation3Dcloudcloudnot neededGLB, OBJ, FBX
Tripo AItext-to-3D, image-to-3D, texturing, rigging, animation3Dcloudcloudnot neededJPG, PNG, WEBP
Dream Machinetext-to-video, image-to-video, video extension, video interpolationVideocloudcloudnot neededMP4
Hailuoimage-to-video, text-to-videoVideocloudcloudnot needed—
KlingVideo and image generation using AIVideocloudcloudnot needed—
PikaImage-to-Video, Video-to-Video, Text-to-VideoVideocloudcloudnot needed—
RunwayVideo avatar generation from audio or text, avatar creation and management, real-time conversationsVideocloudcloudnot needed—
Soratext-to-video, image-to-video, video-to-videoVideocloudcloudnot neededMP4
Veotext-to-video, image-to-videoVideocloudcloudnot neededvideo/mp4
ViduVideo generation: text-to-video, image-to-video, reference-to-video, start-end-to-video, upscaleVideocloudcloudnot neededpng, jpeg, jpg, webp

Requirements not stated by the authors

The official sources for these tools have no data for the selected filter — that means “unknown”, not “won’t work”.

CRM3Dopen sourcenot stated—obj
DreamGaussian3Dopen sourcenot stated——
Era3D3Dopen sourcenot stated——
Hunyuan3D 2.1image-to-3d3Dopen sourcefrom 10 GB (10–29 GB) *——
LGMtext-to-3d3Dopen sourcenot stated——
Michelangelo3Dopen sourcenot stated——
MVDream3Dopen sourcenot stated——
One-2-3-453Dopen sourcenot stated——
Point-E3Dopen sourcenot stated——
Shap-E3Dopen sourcenot stated——
Wonder3D3Dopen sourcenot stated——
Zero123++3Dopen sourcefrom 5 GB *——
ACE-Steptext-to-audioAudioopen sourcefrom 8 GB *——
ChatTTStext-to-audioAudioopen sourcefrom 4 GB *——
CosyVoicetext-to-speechAudioopen sourcenot stated——
DiffRhythmAudioopen sourcenot stated——
MOSS-SoundEffecttext-to-audioAudioopen sourcenot stated——
MusicGentext-to-audioAudioopen sourcenot stated——
OpenVoicetext-to-speechAudioopen sourcenot stated——
Stable Audio Opentext-to-audioAudioopen sourcenot stated——
YuEtext-generationAudioopen sourcenot stated——
AnimateDiffVideoopen sourcefrom 13 GB *——
Mochi 1text-to-videoVideoopen sourcefrom 80 GB *——
Open-SoraVideoopen sourcenot stated——
Open-Sora-PlanVideoopen sourcefrom 24 GB *——
Stable Video Diffusionimage-to-videoVideoopen sourcenot stated——
VideoCrafterVideoopen sourcenot stated——
Wantext-to-videoVideoopen sourcefrom 8.19 GB *——

Fact sheets are re-checked monthly; every value on a tool page has a source link and a check date. The asterisk * means “as described by the author”: a developer’s statement, not an independent measurement.