Mirrors
/
EveryDream2trainer
mirror of https://github.com/victorchall/EveryDream2trainer.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Created using Colaboratory

This commit is contained in:
nawnie 2023-02-18 23:55:46 -06:00
parent bf2b128fd7
commit a397c4bb69
1 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
Train_Colab.ipynb
View File

@ -290,7 +290,7 @@
"\n",
"#@markdown * Batch size impacts VRAM use. 8 should work on SD1.x models and 5 for SD2.x models at 512 resolution. Lower this if you get CUDA out of memory errors. You can check resources on your instance and watch the GPU RAM.\n",
"\n",
"Batch_Size = 8 #@param{type: 'number'}\n",
"Batch_Size = 6 #@param{type: 'number'}\n",
"\n",
"#@markdown * Gradient accumulation is sort of like a virtual batch size increase use this to increase batch size with out increasing vram usage\n",
"#@markdown Increasing from 1 to 2 will have a minor impact on vram use, but more beyond that will not.\n",
@ -306,7 +306,7 @@
"\n",
"#@markdown * Max Epochs to train for, this defines how many total times all your training data is used. Default of 100 is a good start if you are training ~30-40 images of one subject. If you have 100 images, you can reduce this to 40-50 and so forth.\n",
"\n",
"Max_Epochs = 200 #@param {type:\"slider\", min:0, max:200, step:5}\n",
"Max_Epochs = 100 #@param {type:\"slider\", min:0, max:200, step:5}\n",
"\n",
"#@markdown * How often to save checkpoints.\n",
"Save_every_N_epoch = 20 #@param{type:\"integer\"}\n",