Plask is an AI motion capture tool that turns ordinary video into 3D character animation. Upload footage from a phone or online clip, let the AI extract body motion, then preview, direct and export the result as FBX, BVH, GLB or video for Blender, Unreal Engine, Maya and other tools.

一個 API 串接 1500+ 可上線的生成式媒體模型
一組 API Key 即可呼叫 1500 多個圖像、影片、音訊、3D 與 world 模型,並隨新模型上線持續更新。
自研推論堆疊,官方稱擴散模型推論最高提速 10 倍,專為對延遲敏感的正式流量設計。
可部署自有或微調模型,包含私有 LoRA 與自訂端點,內建自動擴縮與可觀測性。
H100、H200、B200、B300 多節點叢集,用於訓練與微調等算力密集工作。
Plask is an AI motion capture tool that turns ordinary video into 3D character animation. Upload footage from a phone or online clip, let the AI extract body motion, then preview, direct and export the result as FBX, BVH, GLB or video for Blender, Unreal Engine, Maya and other tools.
Upload smartphone footage or online clips and Plask's AI extracts precise body and skeleton motion data without suits, markers or a studio.
Apply captured motion to your own characters, with blinking and physics simulation supported for VRM and MMD models.
Adjust lighting and camera with AI-assisted cinematography, then add motion blur, depth of field, vignettes and tone mapping for a polished render.
Export FBX, BVH or GLB assets, or render high-quality video, ready to continue in Blender, Unreal Engine, Maya or another animation pipeline.
專項更強Exceptional routing and multi-provider support primarily for language models rather than fal.ai's specialized generative media focus.
專項更強Exceptional routing and multi-provider support primarily for language models rather than fal.ai's specialized generative media focus.

為開源模型提供強大的 GPU 雲端與無伺服器推論,相比視覺媒體,它更專注於大語言模型(LLMs)。
兩者皆提供無伺服器架構來執行自訂模型,但 fal.ai 的框架支援更廣、多媒體最佳化較少。
提供多媒體與文字模型的統一 API,但開發者工具與生態系整合的成熟度較低。
Consolidates image, video, and audio models under single endpoints, but lacks fal.ai's advanced custom weight deployment.
把影片與文字變成 3D 角色動畫的 AI 動作捕捉