autotrain-advanced

autotrain-advanced copied to clipboard

I setup autotrain-advanced on my local machine Windows11 with 12GB GPU Memory

Run the following commands

1. pip install -U autotrain-advanced
2. autotrain setup --update-torch
3. autotrain dreambooth --train --model stabilityai/stable-diffusion-xl-base-1.0 --image-path images --prompt "photo of Narendra Modi" --resolution 1024 --batch-size 1 --num-steps 500 --gradient-accumulation 4 --lr 1e-4 --project-name "text-to-image" --mixed-precision fp16

The images on which I'm training my text-to-image model is present under the 'images' folder in current directory.

@abhishekkrthakur I followed your YouTube Tutorial
https://youtu.be/gF078Lhnr94?si=JDbFwW9FLjbFhX5h

Getting this errors, pls help me resolve this

https://huggingface.co/docs/autotrain/faq#is-windows-supported

Setup this on Ubuntu 20.04.6 LTS

$ conda create -n autotrain python=3.10 $ conda activate autotrain $ pip install autotrain-advanced $ conda install pytorch torchvision torchaudio pytorch-cuda=12.1 -c pytorch -c nvidia $ conda install -c "nvidia/label/cuda-12.1.0" cuda-nvcc $ conda install xformers -c xformers $ python -m nltk.downloader punkt $ pip install flash-attn --no-build-isolation # if you want to use flash-attn $ pip install deepspeed $ export HF_TOKEN=your_hugging_face_write_token (added Token ) $ autotrain --help

getting same error for " autotrain setup "

@abhishekkrthakur

youtube tutorials are outdated. please follow docs: https://hf.co/docs/autotrain

https://huggingface.co/docs/autotrain/quickstart

Yes, followed the same, still getting those errors

This issue is stale because it has been open for 30 days with no activity.

This issue was closed because it has been inactive for 20 days since being marked as stale.