Hugging Face's logo

Spaces:
TIGER-Lab
/
T2V-Turbo-V2
Running on Zero

App Files Community
3
Ji4chenLi commited on
Commit
979e017
•
1 Parent(s): 9ada050

update description

Browse files
Files changed (1) hide show
  1. app.py +5 -2
app.py CHANGED
@@ -20,15 +20,18 @@ from pipeline.t2v_turbo_vc2_pipeline import T2VTurboVC2Pipeline
20
  DESCRIPTION = """# T2V-Turbo 🚀
21
 
22
  Our model is distilled from [VideoCrafter2](https://ailab-cvc.github.io/videocrafter2/).
 
23
  T2V-Turbo learns a LoRA on top of the base model by aligning to the reward feedback from [HPSv2.1](https://github.com/tgxs002/HPSv2/tree/master) and [InternVid2 Stage 2 Model](https://huggingface.co/OpenGVLab/InternVideo2-Stage2_1B-224p-f4).
 
24
  T2V-Turbo-v2 optimizes the training techniques by finetuning the full base model and further aligns to [CLIPScore](https://huggingface.co/laion/CLIP-ViT-H-14-laion2B-s32B-b79K)
25
 
26
  T2V-Turbo trains on pure WebVid-10M data, whereas T2V-Turbo-v2 carufully optimizes different learning objectives with a mixutre of VidGen-1M and WebVid-10M data.
27
 
28
  Moreover, T2V-Turbo-v2 supports to distill motion priors from the training videos.
29
 
30
- [Project page for T2V-Turbo](https://t2v-turbo.github.io) 😄
31
- [Project page for T2V-Turbo-v2](https://t2v-turbo-v2.github.io) 🛫
 
32
  """
33
  if torch.cuda.is_available():
34
  DESCRIPTION += "\n<p>Running on CUDA 😀</p>"
 
20
  DESCRIPTION = """# T2V-Turbo 🚀
21
 
22
  Our model is distilled from [VideoCrafter2](https://ailab-cvc.github.io/videocrafter2/).
23
+
24
  T2V-Turbo learns a LoRA on top of the base model by aligning to the reward feedback from [HPSv2.1](https://github.com/tgxs002/HPSv2/tree/master) and [InternVid2 Stage 2 Model](https://huggingface.co/OpenGVLab/InternVideo2-Stage2_1B-224p-f4).
25
+
26
  T2V-Turbo-v2 optimizes the training techniques by finetuning the full base model and further aligns to [CLIPScore](https://huggingface.co/laion/CLIP-ViT-H-14-laion2B-s32B-b79K)
27
 
28
  T2V-Turbo trains on pure WebVid-10M data, whereas T2V-Turbo-v2 carufully optimizes different learning objectives with a mixutre of VidGen-1M and WebVid-10M data.
29
 
30
  Moreover, T2V-Turbo-v2 supports to distill motion priors from the training videos.
31
 
32
+ [Project page for T2V-Turbo](https://t2v-turbo.github.io) 🥳
33
+
34
+ [Project page for T2V-Turbo-v2](https://t2v-turbo-v2.github.io) 🤓
35
  """
36
  if torch.cuda.is_available():
37
  DESCRIPTION += "\n<p>Running on CUDA 😀</p>"