CPU3DAI tools for 3D, video and audio

Video generators

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.

Showing 44 of 96

ToolTypeRunsVRAMBackendsFormats
4DAnyoneVideoopen sourcefrom 24 GB *CUDA—
AI Comic BuilderVideoopen sourcenot stated——
AlayaRendererimage-to-imageVideoopen sourcenot stated——
Allegrotext-to-videoVideoopen sourcefrom 9.3 GB (9.3–27.5 GB) *CUDA—
AnimateDiffVideoopen sourcefrom 13 GB *——
CogVideoXtext-to-videoVideoopen sourcenot statedCUDA—
Cosmos3-Super-Image2Videoimage-to-videoVideoopen sourcenot statedCUDA—
Dream MachineMultimodal creative agent for creating and editing images, video, audio and textVideocloudcloudnot neededMP4
forge-filmVideoopen sourcenot statedCUDA—
FramePackVideoopen sourcefrom 6 GB *CUDA—
GAE-GeometricAutoEncoderimage-to-videoVideoopen sourcenot stated—ply
HailuoVideo and image generationVideocloudcloudnot needed—
HelixWorldVideoopen sourcefrom 80 GB *CUDA—
HunyuanVideotext-to-videoVideoopen sourcefrom 45 GB (45–60 GB) *CUDA—
Infinite WorldVideoopen sourcenot stated——
KlingImage and video generationVideocloudcloudnot needed—
Lanceany-to-anyVideoopen sourcefrom 40 GB *CUDAobj
LatteVideoopen sourcenot statedCUDA—
LingBot-VideoVideoopen sourcenot stated——
LTX-Videoimage-to-videoVideoopen sourcefrom 1 GB *Apple MPS—
Maestroimage-text-to-videoVideoopen sourcefrom 12 GB (12–24 GB) *CUDA—
Mochi 1text-to-videoVideoopen sourcefrom 80 GB *——
nano-world-modelVideoopen sourcenot statedCUDA—
object-permanencevideo-to-videoVideoopen sourcenot stated——
Open-SoraVideoopen sourcenot stated——
Open-Sora-PlanVideoopen sourcefrom 24 GB *——
PikaVideo, image and audio generationVideocloudcloudnot needed—
Pyramid Flowtext-to-videoVideoopen sourcefrom 8 GB *Apple MPS—
RefAlignimage-text-to-videoVideoopen sourcenot stated——
RunwayVideo, image, speech, sound effect, avatar generation and other tasksVideocloudcloudnot neededMP4, MOV, ZIP, PNG, WAV, EXR
SkyReelsVideoopen sourcefrom 18.5 GB *CUDA—
SoraVideo generation from text, images or videoVideocloudcloudnot neededMP4
SparkDiffusiontext-to-videoVideoopen sourcenot statedCUDA—
Stable Video Diffusionimage-to-videoVideoopen sourcenot stated——
TE-Speed-MiniMaxH3-OSSVideoopen sourcenot stated——
VeoVideo generationVideocloudcloudnot needed—
video-generator-clientVideoopen sourcenot stated——
VideoCrafterVideoopen sourcenot stated——
ViduVideo generation: Reference2Video, Image2Video, Start-End2Video, Text2Video, Upscale, TemplateVideocloudcloudnot neededpng, jpeg, jpg, webp
ViMaxVideoopen sourcenot stated——
Wantext-to-videoVideoopen sourcefrom 8.19 GB *——
Wan-Dancer-14Bimage-to-videoVideoopen sourcefrom 80 GB *CUDA—
wind-comicVideoopen sourcenot stated——
WorldCrafterimage-to-videoVideoopen sourcenot statedCUDA—

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.