Not a member of Pastebin yet?
Sign Up,
it unlocks many cool features!
- Manual Install Method from my last Youtube Video: https://youtu.be/WA5xo7PLDsg
- Link to get the loras, workflow and installers : https://www.patreon.com/c/aitrepreneur
- 1. Install prereqs manually:
- – CUDA 12.8 (RTX-50) OR CUDA 12.6 (RTX-40/30/20/GTX)
- – Git, Python 3.10 64-bit, Node 18/20 LTS
- git clone https://github.com/ostris/ai-toolkit.git
- cd ai-toolkit
- python -m venv venv
- call venv\Scripts\activate.bat
- python -m pip install -U pip
- RTX-50 (CUDA 12.8)
- pip install --no-cache-dir torch==2.7.0 torchvision==0.22.0 --index-url https://download.pytorch.org/whl/cu128
- RTX-40/30/20/GTX 16/10 (CUDA 12.6)
- ip install --no-cache-dir torch==2.7.0 torchvision==0.22.0 --index-url https://download.pytorch.org/whl/cu126
- pip install -r requirements.txt
- cd ui
- npm install
- npm run build_and_start
- open localhost
- Optional password
- set AI_TOOLKIT_AUTH=mypwd && npm run build_and_start
- RUNPOD:
- Create account at: https://bit.ly/runpodAi
- 0) Optional: sudo apt update -y
- sudo apt install -y git python3 python3-venv python3-pip build-essential curl
- git clone https://github.com/ostris/ai-toolkit.git
- cd ai-toolkit
- python3 -m venv venv
- source venv/bin/activate
- pip install -U pip
- Pick one:
- • 5000-series (CUDA 12.8 wheels)
- pip install --no-cache-dir torch==2.7.0+cu128 torchvision==0.22.0+cu128 --index-url https://download.pytorch.org/whl/cu128
- • Older GPUs (CUDA 12.6 wheels)
- pip install --no-cache-dir torch==2.7.0 torchvision==0.22.0 --index-url https://download.pytorch.org/whl/cu126
- pip install -r requirements.txt
- curl -o- https://raw.githubusercontent.com/nvm-sh/nvm/v0.40.3/install.sh | bash
- source ~/.nvm/nvm.sh
- nvm install 22 && nvm use 22
- cd ui
- npm install
- npm run build_and_start
- Chatgpt prompt:
- I will upload a few images, wait until I finished uploading them all.
- These are photos of Margot Robbie, analyze those images and caption them correctly for a Lora training using "Margot Robbie" as the caption token and convert each single caption into a .txt file and name them all in the same order, Margot Robbie_0001.txt, Margot Robbie_0002.txt, etc... and then finally zip them up all into a single zip file I can download
Add Comment
Please, Sign In to add comment