Merge branch 'main' of https://github.com/victorchall/EveryDream2trainer into main
This commit is contained in:
Victor Hall
commit
e98aa90288
|
|
@ -30,22 +30,13 @@
|
|||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "0902e735",
|
||||
"cell_type": "markdown",
|
||||
"id": "5123d4e6-281c-4475-99fd-328f4d5df734",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# When running on a pod designed for Automatic 1111 \n",
|
||||
"# we need to kill the webui process to free up mem for training\n",
|
||||
"!ps x | grep -E \"(relauncher|webui)\" | grep -v \"grep\" | awk '{print $1}' | xargs kill $1\n",
|
||||
"# For best results, restart the pod after the next cell completes\n",
|
||||
"\n",
|
||||
"# check system resources, make sure your GPU actually has 24GB\n",
|
||||
"# You should see something like \"0 MB / 24576 MB\" in the middle of the printout\n",
|
||||
"# if you see 0 MB / 22000 MB pick a beefier instance...\n",
|
||||
"!grep Swap /proc/meminfo\n",
|
||||
"!swapon -s\n",
|
||||
"!nvidia-smi"
|
||||
"Here we ensure that EveryDream2trainer is installed, and we disable the Automatic 1111 web-ui. But the vram consumed by the web-ui will not be fully freed until the pod restarts. This is especially important if you are training with large batch sizes."
|
||||
]
|
||||
},
|
||||
{
|
||||
|
|
@ -58,13 +49,34 @@
|
|||
"import os\n",
|
||||
"\n",
|
||||
"%cd /workspace\n",
|
||||
"!echo pass > /workspace/stable-diffusion-webui/relauncher.py\n",
|
||||
"if not os.path.exists(\"EveryDream2trainer\"):\n",
|
||||
" !git clone https://github.com/victorchall/EveryDream2trainer\n",
|
||||
"\n",
|
||||
"%cd EveryDream2trainer\n",
|
||||
"%mkdir input\n",
|
||||
"!python utils/get_yamls.py"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "0902e735",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# When running on a pod designed for Automatic 1111 \n",
|
||||
"# we need to kill the webui process to free up mem for training\n",
|
||||
"!ps x | grep -E \"(relauncher|webui)\" | awk '{print $1}' | xargs kill $1\n",
|
||||
"\n",
|
||||
"# check system resources, make sure your GPU actually has 24GB\n",
|
||||
"# You should see something like \"0 MB / 24576 MB\" in the middle of the printout\n",
|
||||
"# if you see 0 MB / 22000 MB pick a beefier instance...\n",
|
||||
"!grep Swap /proc/meminfo\n",
|
||||
"!swapon -s\n",
|
||||
"!nvidia-smi"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "0bf1e8cd",
|
||||
|
|
@ -102,9 +114,9 @@
|
|||
"!python -m pip install --upgrade pip\n",
|
||||
"\n",
|
||||
"!pip install requests==2.25.1\n",
|
||||
"!pip install -U -I torch==1.13.1+cu116 torchvision==0.14.1+cu116 --extra-index-url \"https://download.pytorch.org/whl/cu116\"\n",
|
||||
"!pip install -U -I torch==1.13.1+cu117 torchvision==0.14.1+cu117 --extra-index-url \"https://download.pytorch.org/whl/cu117\"\n",
|
||||
"!pip install transformers==4.25.1\n",
|
||||
"!pip install -U diffusers[torch]==0.10.2\n",
|
||||
"!pip install -U diffusers[torch]\n",
|
||||
"\n",
|
||||
"!pip install pynvml==11.4.1\n",
|
||||
"!pip install bitsandbytes==0.35.0\n",
|
||||
|
|
@ -115,20 +127,8 @@
|
|||
"!pip install wandb==0.13.6\n",
|
||||
"!pip install colorama==0.4.6\n",
|
||||
"!pip install -U triton\n",
|
||||
"!pip install -U ninja\n",
|
||||
"\n",
|
||||
"from subprocess import getoutput\n",
|
||||
"s = getoutput('nvidia-smi')\n",
|
||||
"\n",
|
||||
"if \"A100\" in s:\n",
|
||||
" print(\"Detected A100, installing stable xformers\")\n",
|
||||
" !pip install -U xformers\n",
|
||||
"else:\n",
|
||||
" # A5000/3090/4090 support requires us to build xformers ourselves for now\n",
|
||||
" print(\"Building xformers for SM86\")\n",
|
||||
" !apt-get update && apt-get install -y gcc g++\n",
|
||||
" !export TORCH_CUDA_ARCH_LIST=8.6 && pip install git+https://github.com/facebookresearch/xformers.git@48a77cc#egg=xformers\n",
|
||||
"\n",
|
||||
"!pip install --pre -U xformers\n",
|
||||
" \n",
|
||||
"print(\"DONE\")"
|
||||
]
|
||||
},
|
||||
|
|
@ -184,6 +184,7 @@
|
|||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"%cd /workspace/EveryDream2trainer\n",
|
||||
"repo=\"panopstor/EveryDream\"\n",
|
||||
"ckpt_file=\"sd_v1-5_vae.ckpt\"\n",
|
||||
"\n",
|
||||
|
|
@ -230,16 +231,33 @@
|
|||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"!python train.py --project_name \"ft_v1a_512_15e7\" \\\n",
|
||||
"--resume_ckpt \"{ckpt_name}\" \\\n",
|
||||
"%cd /workspace/EveryDream2trainer\n",
|
||||
"!python train.py --project_name \"sd1_mymodel_000\" \\\n",
|
||||
"--resume_ckpt \"sd_v1-5_vae\" \\\n",
|
||||
"--data_root \"input\" \\\n",
|
||||
"--resolution 512 \\\n",
|
||||
"--batch_size 8 \\\n",
|
||||
"--max_epochs 100 \\\n",
|
||||
"--save_every_n_epochs 50 \\\n",
|
||||
"--lr 1.8e-6 \\\n",
|
||||
"--lr_scheduler cosine \\\n",
|
||||
"--sample_steps 250 \\\n",
|
||||
"--useadam8bit \\\n",
|
||||
"--save_full_precision \\\n",
|
||||
"--shuffle_tags \\\n",
|
||||
"--amp \\\n",
|
||||
"--write_schedule\n",
|
||||
"\n",
|
||||
"!python train.py --project_name \"sd1_mymodel_100\" \\\n",
|
||||
"--resume_ckpt \"findlast\" \\\n",
|
||||
"--data_root \"input\" \\\n",
|
||||
"--resolution 512 \\\n",
|
||||
"--batch_size 4 \\\n",
|
||||
"--max_epochs 200 \\\n",
|
||||
"--save_every_n_epochs 25 \\\n",
|
||||
"--lr 1.5e-6 \\\n",
|
||||
"--max_epochs 100 \\\n",
|
||||
"--save_every_n_epochs 20 \\\n",
|
||||
"--lr 1.0e-6 \\\n",
|
||||
"--lr_scheduler constant \\\n",
|
||||
"--sample_steps 50 \\\n",
|
||||
"--sample_steps 150 \\\n",
|
||||
"--useadam8bit \\\n",
|
||||
"--save_full_precision \\\n",
|
||||
"--shuffle_tags \\\n",
|
||||
|
|
@ -247,38 +265,6 @@
|
|||
"--write_schedule"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "ca170883-2d18-4f34-adbb-aca5824a351b",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## You can chain togther a tuning schedule using `--resume_ckpt findlast`"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "f39291ef-bea9-471e-bbc7-7b681fa87eb3",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"!python train.py --project_name \"ft_v1b_512_07e7\" \\\n",
|
||||
"--resume_ckpt findlast \\\n",
|
||||
"--data_root \"input\" \\\n",
|
||||
"--resolution 512 \\\n",
|
||||
"--batch_size 4 \\\n",
|
||||
"--max_epochs 50 \\\n",
|
||||
"--save_every_n_epochs 25 \\\n",
|
||||
"--lr 0.7e-6 \\\n",
|
||||
"--lr_scheduler constant \\\n",
|
||||
"--sample_steps 50 \\\n",
|
||||
"--useadam8bit \\\n",
|
||||
"--save_full_precision \\\n",
|
||||
"--shuffle_tags \\\n",
|
||||
"--amp \\\n",
|
||||
"--write_schedule\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "f24eee3d-f5df-45f3-9acc-ee0206cfe6b1",
|
||||
|
|
@ -320,8 +306,8 @@
|
|||
"!huggingface-cli lfs-enable-largefiles\n",
|
||||
"# fill in these three fields:\n",
|
||||
"hfusername = \"MyHfUser\"\n",
|
||||
"reponame = \"MyRepo\"\n",
|
||||
"ckpt_name = \"ft_v1b_512_15e7-ep200-gs02500.ckpt\"\n",
|
||||
"reponame = \"MyHfRepo\"\n",
|
||||
"ckpt_name = \"sd1_mymodel_000-ep100-gs01000.ckpt\"\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"target_name = ckpt_name.replace('-','').replace('=','')\n",
|
||||
|
|
@ -348,7 +334,7 @@
|
|||
],
|
||||
"metadata": {
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3 (ipykernel)",
|
||||
"display_name": "Python 3",
|
||||
"language": "python",
|
||||
"name": "python3"
|
||||
},
|
||||
|
|
@ -362,7 +348,7 @@
|
|||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.10.9"
|
||||
"version": "3.6.10"
|
||||
},
|
||||
"vscode": {
|
||||
"interpreter": {
|
||||
|
|
|
|||
Loading…
Reference in New Issue