From 4e5903129c1c14f646709a8ec018c507d0db5e14 Mon Sep 17 00:00:00 2001 From: Sanster Date: Sun, 6 Mar 2022 20:43:12 +0800 Subject: [PATCH] update README --- README.md | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/README.md b/README.md index 9d36c8d..a717f58 100644 --- a/README.md +++ b/README.md @@ -31,6 +31,11 @@ python3 main.py --device=cuda --port=8080 --model=ldm --ldm-steps=50 Diffusion model is **MUCH MORE** slower than GANs(1080x720 image takes 8s on 3090), but it's possible to get better results than LaMa. +|Original Image|LaMa|LDM| +|--------------|------|----| +|![photo-1583445095369-9c651e7e5d34](https://user-images.githubusercontent.com/3998421/156923525-d6afdec3-7b98-403f-ad20-88ebc6eb8d6d.jpg)|![photo-1583445095369-9c651e7e5d34_cleanup_lama](https://user-images.githubusercontent.com/3998421/156923620-a40cc066-fd4a-4d85-a29f-6458711d1247.png)|![photo-1583445095369-9c651e7e5d34_cleanup_ldm](https://user-images.githubusercontent.com/3998421/156923652-0d06c8c8-33ad-4a42-a717-9c99f3268933.png)| + + Blogs about diffusion models: - https://lilianweng.github.io/posts/2021-07-11-diffusion-models/