We have moved to https://openmodeldb.info/. This new site has a tag and search system, which will make finding the right models for you much easier! If you have any questions, ask here: https://discord.gg/cpAUpDK |
Difference between revisions of "Joey's ESRGAN Tutorial"
Jump to navigation
Jump to search
(Moved from the links page top here) |
(De-Crigified guide) |
||
(One intermediate revision by the same user not shown) | |||
Line 2: | Line 2: | ||
=== How to use it === | === How to use it === | ||
− | # Put the pictures or textures you want to upscale into the <code>input</code> folder | + | # Put the pictures or textures you want to upscale into the <code>input</code> (found inside the <code>esrgan</code> folder) |
# Open a terminal window and navigate to the <code>esrgan</code> folder (the folder you cloned the fork into in the install guide) | # Open a terminal window and navigate to the <code>esrgan</code> folder (the folder you cloned the fork into in the install guide) | ||
#* For Windows Shift right click in your <code>esrgan</code> folder and select <code>Git Bash Here</code>. | #* For Windows Shift right click in your <code>esrgan</code> folder and select <code>Git Bash Here</code>. | ||
− | #* For Linux / MacOS users the | + | #* For Linux / MacOS users use either the equivalent feature in your file manager or the cd command. |
# Enter: | # Enter: | ||
## For Nvidia GPUs | ## For Nvidia GPUs | ||
Line 11: | Line 11: | ||
## For other GPUs / integrated Graphic | ## For other GPUs / integrated Graphic | ||
##: <code>python upscale.py --cpu models/${theModelYouWantToUse}</code> | ##: <code>python upscale.py --cpu models/${theModelYouWantToUse}</code> | ||
− | # | + | # Replace <code>${theModelYouWantToUse}</code> with the name of a model in the models folder. |
# That was it, the results will be in the <code>results</code> folder | # That was it, the results will be in the <code>results</code> folder | ||
Latest revision as of 21:10, 27 November 2021
How to use it
- Put the pictures or textures you want to upscale into the
input
(found inside theesrgan
folder) - Open a terminal window and navigate to the
esrgan
folder (the folder you cloned the fork into in the install guide)- For Windows Shift right click in your
esrgan
folder and selectGit Bash Here
. - For Linux / MacOS users use either the equivalent feature in your file manager or the cd command.
- For Windows Shift right click in your
- Enter:
- For Nvidia GPUs
python upscale.py models/${theModelYouWantToUse}
- For other GPUs / integrated Graphic
python upscale.py --cpu models/${theModelYouWantToUse}
- For Nvidia GPUs
- Replace
${theModelYouWantToUse}
with the name of a model in the models folder. - That was it, the results will be in the
results
folder
Other useful Command line switches are:
--input ./input
- Your Input folder--seamless
- For seamless textures (Textures that repeat without seams)--output ./output
- Your Output folder--skip_existing
- Skipps already upscaled images that are in your output and input folder--tile_size 512
- The tile size, if you run out of VRAM, decrease that value--binary_alpha
- If the alpha / transparency channel should be only black or white--alpha_threshold 0.5
Sets tha point at which alpha will be white instead of black if using binary alpha--alpha_mode 1
Different implementation for how Alpha works, if you use binary alpha, it must be 1 otherwise you can try 2.