|
--- |
|
license: mit |
|
--- |
|
|
|
# This repo contains the pretrained checkpoints for Ctrl-Adapter |
|
|
|
|
|
CTRL-Adapter is an efficient and versatile framework for adding diverse |
|
spatial controls to any image or video diffusion model. It supports a variety of useful |
|
applications, including video control, video control with multiple conditions, video control with |
|
sparse frame conditions, image control, zero-shot transfer to unseen conditions, and video editing. |
|
|
|
See also: https://github.com/HL-hanlin/Ctrl-Adapter |
|
|
|
|
|
<br> |
|
<img width="800" src="assets/teaser.gif"/> |
|
<br> |
|
|
|
|
|
# Description of Model Checkpoints |
|
|
|
Ctrl-Adapter/i2vgenxl_depth/diffusion_pytorch_model.safetensors |
|
|
|
- The Ctrl-Adapter checkpoint trained on I2VGen-XL for video generation that uses depth map as control condition. |
|
|
|
|
|
More checkpoints trained on Hotshot-XL, Stable Video Diffusion, and SDXL will be updated soon. |
