diffusers VS fast-stable-diffusion

# Step 1: Install required packages pip install transformers>=4.51.3 pip install git+https://github.com/huggingface/diffusers pip install python-pptx torch pillow # Step 2: Verify CUDA availability (for GPU users) python -c "import torch; print(torch.cuda.is_available())"

Diffusers Documentation

pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu121 pip install einops timm pillow pip install git+https://github.com/huggingface/transformers pip install git+https://github.com/huggingface/accelerate pip install git+https://github.com/huggingface/diffusers pip install huggingface_hub pip install sentencepiece bitsandbytes protobuf decord numpy

System requirements: 24GB GPU memory and 64GB+ RAM > pip install git+https://github.com/huggingface/diffusers

pip install --upgrade pip pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu121 pip install git+https://github.com/huggingface/diffusers.git pip install transformers accelerate safetensors numpy pillow

I'm not a fan of Python, but it is the languange of choice for most Machine Learning code. I'm currently working on a NodeJS based project where I need to call the HuggingFace Diffusers python module. So I came up with an IPC wrapper around the the Python script.

!pip install torch torchvision torchaudio einops timm pillow !pip install git+https://github.com/huggingface/transformers !pip install git+https://github.com/huggingface/accelerate !pip install git+https://github.com/huggingface/diffusers !pip install huggingface_hub !pip install sentencepiece bitsandbytes protobuf decord ffmpeg-python imageio opencv-python

> All the self-hosted LLM and text-to-image models come with some restrictions trained into them

https://github.com/huggingface/diffusers/issues/3422

import modal image = modal.Image.debian_slim(python_version="3.10").apt_install( "libglib2.0-0", "libsm6", "libxrender1", "libxext6", "ffmpeg", "libgl1", "git" ).pip_install( "git+https://github.com/huggingface/diffusers.git", "invisible_watermark", "transformers", "accelerate", "safetensors", "sentencepiece", )

pip install torch==2.3.1 pip install git+https://github.com/huggingface/diffusers.git pip install transformers==4.43.3 sentencepiece==0.2.0 accelerate==0.33.0 protobuf==5

I tried using TheLastBen's fast dreambooth trainer. I managed to train a ckpt file but I can't run it.

You have a colab from ThelastBen It uses to be thes best at the time when auto1111 was working in google colab free. https://github.com/TheLastBen/fast-stable-diffusion

Using https://github.com/TheLastBen/fast-stable-diffusion

This repo offers a template how to start with SD on runpod https://github.com/TheLastBen/fast-stable-diffusion. But I know how to code, si I made my own solution.

I can confirm I'm using the latest version of the colab notebook of this repo (https://github.com/TheLastBen/fast-stable-diffusion). Anyone can point to any solutions to this problem? Thanks in advance!

TheLastBen's Fast DB SD Colabs, +25-50% speed increase, AUTOMATIC1111 + DreamBooth

CalledProcessError Traceback (most recent call last) in () 182 wget.download('https://github.com/TheLastBen/fast-stable-diffusion/raw/main/Dreambooth/det.py') 183 print('Detecting model version...') --> 184 Custom_Model_Version=check_output('python det.py '+sftnsr+' --MODEL_PATH '+MODEL_PATH, shell=True).decode('utf-8').replace('\n', '') 185 clear_output() 186 print(''+Custom_Model_Version+' Detected')

have you tried https://github.com/TheLastBen/fast-stable-diffusion ?