Tencent/MimicMotion
Source: https://github.com/tencent/mimicmotion
Structured fields
{
"archived": false,
"checked_at": "2026-10-17T00:00:00.000Z",
"usefulness": "Pose-guided human video generation (ICML 2025 per README) built on Stable Video Diffusion with confidence-aware pose guidance and progressive latent fusion for long clips; modest VRAM (8GB to 16GB) so it runs on consumer GPUs.",
"source_type": "repository",
"availability": "available",
"dependencies": [
"Stable Video Diffusion base model",
"DWPose"
],
"next_check_at": "2026-10-31T00:00:00.000Z",
"hardware_notes": "See evidence (8GB to 16GB).",
"upstream_updated_at": "2025-11-18T06:29:12.000Z"
}Evidence claims
- [upstream_claim] README: framework for controllable human motion video generation with confidence-aware pose guidance and progressive latent fusion for long videos; ICML 2025 acceptance noted. source
- [upstream_claim] README VRAM: 72-frame model needs 16GB (a 4060 Ti) for the 35s demo taking about 20 minutes on a 4090; 16-frame U-Net minimum 8GB; VAE decoder 16GB but can run on CPU. source
- [sourced_fact] LICENSE: Apache License 2.0 except third-party components (diffusers, DWPose modified by Tencent, transformers, decord Apache-2.0; torch, torchvision, numpy BSD-3; OpenCV and einops MIT). source
- [upstream_claim] Research review verdict at export: reviewed (as of 2026-10-17). Recorded by the research pipeline, not a hub review outcome; evidence.review stays unreviewed until an independent reviewer records one.
Rights
| component | license | hosting | redistribution | modification | training | Evidence and notes |
|---|---|---|---|---|---|---|
| code | Apache-2.0 | permitted | permitted | permitted | unknown | Apache-2.0 for the code with third-party components listed. |
| model_weights | unknown | unknown | unknown | unknown | unknown | Checkpoints on Hugging Face (MimicMotion_1-1.pth, DWPose models, Stable Video Diffusion) have their own terms; SVD base model terms were not read. |