pkhungurn / talking-head-anime-3-demo

Demo Programs for the "Talking Head(?) Anime from a Single Image 3: Now the Body Too" Project
http://pkhungurn.github.io/talking-head-anime-3/
MIT License
950 stars 101 forks source link

Unable to upload image #7

Open scapeXghost opened 2 years ago

scapeXghost commented 2 years ago

Hello! I got the code running on my computer and got as far as the imputing the image. However, for every image I attempt to load I get a "Could not load image..." message. I even tried the Kizuna AI image you used as demonstration in the article.

Thank you

DracheShiki commented 2 years ago

check if your torch version matched with CUDA version.

Fruitpex commented 1 year ago

I went through the exact same thing and figured out if you install them one by one you'll potentially face this issue. If you instead scroll down to the Automatic Environment Construction with Anaconda section and install with conda env create -f environment.yml (with Anaconda Navigator) that should fix your issue.

dragonmeteor commented 1 year ago

Sorry for not responding for a long, long time.

The images have to conform to several requirements written here: https://github.com/pkhungurn/talking-head-anime-3-demo#contraints-on-input-images. Do your images satisfy these requirements?

PortalTom commented 1 year ago

Hello! I got the code running on my computer and got as far as the imputing the image. However, for every image I attempt to load I get a "Could not load image..." message. I even tried the Kizuna AI image you used as demonstration in the article.

Thank you

Did you ever figure out what was wrong? I'm having the same issue.

linsamtw commented 1 year ago

I use lambda_00.png, but I can't load image

image

linsamtw commented 1 year ago

I use lambda_00.png, but I can't load image

image

after I install the torch version matched with CUDA version, I can upload image,

metanoder commented 1 year ago

Installing with conda env create -f environment.yml (with Anaconda Navigator) fixed my issue with uploading images. As fruitpex mentioned, it is in the Automatic Environment Construction with Anaconda section.