|
--- |
|
license: mit |
|
--- |
|
<div align="center"> |
|
|
|
# StableV2V: Stablizing Shape Consistency in Video-to-Video Editing |
|
|
|
Chang Liu, Rui Li, Kaidong Zhang, Yunwei Lan, Dong Liu |
|
|
|
[[`Paper`]](https://arxiv.org/abs/2411.11045) / [[`Project`]](https://alonzoleeeooo.github.io/StableV2V/) / [[`GitHub`]](https://github.com/AlonzoLeeeooo/StableV2V) / [[`DAVIS-Edit (HuggingFace)`]](https://huggingface.co/datasets/AlonzoLeeeooo/DAVIS-Edit) / [[`Models (wisemodel)`]](https://wisemodel.cn/models/Alonzo/StableV2V) / [[`DAVIS-Edit (wisemodel)`]](https://wisemodel.cn/datasets/Alonzo/DAVIS-Edit) / [[`Models (ModelScope)`]](https://modelscope.cn/models/AlonzoLeeeoooo/StableV2V) / [[`DAVIS-Edit (ModelScope)`]](https://modelscope.cn/datasets/AlonzoLeeeoooo/DAVIS-Edit) |
|
</div> |
|
|
|
Official pre-trained model weights of the paper titled "StableV2V: Stablizing Shape Consistency in Video-to-Video Editing". |
|
|
|
# Model Weights Structure |
|
We construct our model weights following the structure below: |
|
``` |
|
StableV2V |
|
├── controlnet-depth <----- ControlNet (depth), required by CIG |
|
├── controlnet-scribble <----- ControlNet (scribble, needed in sketch-based editing application) |
|
├── ctrl-adapter-i2vgenxl-depth <----- Ctrl-Adapter (I2VGen-XL, depth), required by CIG |
|
├── i2vgenxl <----- I2VGen-XL, required by CIG |
|
├── instruct-pix2pix <----- InstructPix2Pix, required by PFE |
|
├── paint-by-example <----- Paint-by-Example, required by PFE |
|
├── stable-diffusion-v1-5-inpaint <----- SD Inpaint, required by PFE |
|
├── stable-diffusion-v1.5 <----- SD v1.5, required by CIG |
|
├── 50000.ckpt <----- Shape-guided depth refinement network |
|
├── README.md |
|
├── dpt_swin2_large_384.pt <----- MiDaS, required by ISA |
|
├── raft-things.pth <----- RAFT, required by ISA |
|
├── u2net.pth <----- U2-net, required by ISA |
|
└── 50000.ckpt <----- Shape-guided depth refinement network, required by ISA |
|
``` |
