Add license, pipeline tag, and link to paper

#1
by nielsr HF Staff - opened
Files changed (1) hide show
  1. README.md +4 -1
README.md CHANGED
@@ -3,10 +3,13 @@ tags:
3
  - image-to-video
4
  - human-image-animation
5
  - video-diffusion-transformer
 
 
6
  ---
 
7
  # UniAnimate-DiT: Human Image Animation with Large-Scaled Video Diffusion Transformer
8
 
9
- This repo contains checkpoints for UniAnimate-DiT:
10
 
11
  - UniAnimate-Wan2.1-14B-Lora-12000.ckpt: the weights of LoRAs and additional learnable modules with 12000 training steps.
12
 
 
3
  - image-to-video
4
  - human-image-animation
5
  - video-diffusion-transformer
6
+ license: mit
7
+ pipeline_tag: image-to-video
8
  ---
9
+
10
  # UniAnimate-DiT: Human Image Animation with Large-Scaled Video Diffusion Transformer
11
 
12
+ This repo contains checkpoints for UniAnimate-DiT. The model is described in the paper [Replace Anyone in Videos](https://huggingface.co/papers/2409.19911).
13
 
14
  - UniAnimate-Wan2.1-14B-Lora-12000.ckpt: the weights of LoRAs and additional learnable modules with 12000 training steps.
15