Zongsheng
@OAOAOAOAOAOooo
Followers
12
Following
2
Statuses
6
Joined August 2022
RT @dreamingtulpa: its called InvSR and is a diffusion based upscale method which only requires one to five steps code:
0
18
0
Our new work InvSR: Image super-resolution via Diffusion Inversion. Welcome to have a try. @ccloy @KangLiao929 Project page: Hugging Face: Replicate:
0
0
1
Our work on image super-resolution has been accepted by NeurIPS 2023 as a spotlight. It achieves impressive SR results only with 15 diffusion steps. Welcome to try our demo. @_akhaliq @ccloy @Iceclearwjy Demo: Project page:
0
1
8
Welcome to try our demo!👉👈
The @Gradio Demo for DifFace: Blind Face Restoration with Diffused Error Contraction is out on @huggingface Spaces demo:
0
0
0
Our work devise a beautiful way to leverage the diffusion prior in the task of blind face restoration. The error contraction conducted by diffusion model makes our method very robustness to severe degradations.
0
0
1