AngelBottomless
AngelBottomless
 using Waifu-Vulkan mode, level 3, scale 2x, block size 10 and tested with same file and got some several different result: (happens independently) 1. grid is not sorted correctly...
Supports previously trained hypernetworks (1x -> 2x -> 1x simple networks) Tested creating / training hypernetwork with [1, 2, 2, 1] argument. Tested training from existing hypernetwork named 'anime' Does...
Loss is highly dependent on image itself. To track and not mislead users, we need either per-image loss trending information, or mean loss representing dataset itself. This method allows us...
Statistics logging is using {filename : list[losses]}, so it has to use loss_info[key].pop() This KeyError happened when files were over 1024 items.
As you expected, activation_dict was for variable activation functions, so it should offer any available activation functions.  Yes. (would people be interested in weird activation functions? 🤔 more ML...
### Task list **Pending tasks** - [x] Remove last layer activation and fix dropout silently https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/3698 - [x] Re-Add Linear option disappeared by mistake.https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/3717 **Done tasks** - [x] Disable unavailable...
Optimizers, especially [Adam](https://medium.com/analytics-vidhya/saving-and-loading-your-model-to-resume-training-in-pytorch-cb687352fa61) and its variants are recommended to save and load its state. This patch offers way to save / load optimizer state, also supports for user-selected optimizer types,...
Closes https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/3894 since its log is messed up. Optimizers, especially [Adam](https://medium.com/analytics-vidhya/saving-and-loading-your-model-to-resume-training-in-pytorch-cb687352fa61) and its variants are recommended to save and load its state. This patch offers way to save / load...
Since there are currently multiple HNs from single style / characters, we need to show the file hash. ([related korean issue](https://arca.live/b/hypernetworks/61868651?p=1)) 