search

Algolzw / daclip-uir

[ICLR 2024] Controlling Vision-Language Models for Universal Image Restoration. 5th place in the NTIRE 2024 Restore Any Image Model in the Wild Challenge.
https://algolzw.github.io/daclip-uir
MIT License
582 stars 30 forks source link

test a image #29

Open luckysyj opened 4 months ago

luckysyj commented 4 months ago

Hi, How should I open the URL address The output is (DA-clip) root@autodl-container-4d6411b93c-2cb1d3b0:~/autodl-tmp/daclip-uir-main/daclip-uir-main/universal-image-restoration/config/daclip-sde# python app.py export CUDA_VISIBLE_DEVICES=0 OrderedDict([('name', 'Test'), ('mode', 'LQGT'), ('dataroot_GT', 'datasets/universal/deg_type/GT'), ('dataroot_LQ', 'datasets/universal/deg_type/LQ')]) Running on local URL: http://127.0.0.1:7860

To create a public link, set share=True in launch().

Algolzw commented 4 months ago

Hi, if you want to run it on a remote server you probably can login with: ssh -L 7860:127.0.0.1:786 username@serveraddress. Then you can open your local computer's webpage to access the URL (http://127.0.0.1:7860/)

luckysyj commented 4 months ago

Thank you for your reply I have another question for you to answer. Can grayscale image with noise be restored？

Algolzw commented 4 months ago

Hi, I'm not sure if the current model can restore grayscale images since we haven't used them in training. But thanks for your comment, next month we will release another weight that focuses on real-world image degradations (including restoring grayscale images).

luckysyj commented 4 months ago

OK! Thank you for your prompt response and kind explanation. 😄