Age | Commit message (Collapse) | Author |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
increase block size
|
|
Fix Approx NN not working on torch devices other than CUDA
|
|
at the same time and do not get previews of each other
|
|
|
|
|
|
Automatic setup for AMD GPUs on Linux
|
|
|
|
Fix Aspect Ratio Overlay / AROverlay to work with Inpaint & Sketch
|
|
|
|
|
|
|
|
|
|
Add server start time to state info
|
|
Exclude clip index from merge
|
|
|
|
|
|
election
rework VAE resolving code to be more simple
|
|
|
|
|
|
|
|
|
|
|
|
|
|
fix progress bar behavior for "Prompts from file or textbox" script
|
|
subject) and moves live preview settings to its own tab
|
|
add checkpoint hash to footer
|
|
|
|
This fixes the script on macos
|
|
|
|
|
|
|
|
|
|
|
|
This commit allows the launch script to automatically download rocm's torch version for AMD GPUs using an external GPU detection script. It also prints the operative system and GPU in use.
|
|
This commit adds a script that detects which GPU is currently used in Windows and Linux
|
|
This commit adds a few lines to detect if the system has an AMD gpu and adds an environment variable needed for torch to recognize the gpu.
|
|
|
|
|
|
Add support for Tensorboard (training)
|
|
|