Weekly stuff April 13

Basement jam notes

from diffusers import DiffusionPipeline
from transformers import set_seed
from PIL import Image
import torch
import random
import ssl
import os
ssl._create_default_https_context = ssl._create_unverified_context

#locate library
#model_id = "./stable-diffusion-v1-5"
model_id = "dreamshaper-xl-turbo"

pipeline = DiffusionPipeline.from_pretrained(
    pretrained_model_name_or_path = "../../../../bigFiles/huggingface/dreamshaper-xl-turbo/"
)

pipeline = pipeline.to("mps")

# Recommended if your computer has < 64 GB of RAM
pipeline.enable_attention_slicing("max")

prompt = "messy room full of synthesizers. wires going everywhere. musical chaos. modular synthesizers everywhere. cluttered music room of synthesizers."

for s in range(30):
  for n in [5,10]:
    seed = s+21
    num_steps = n+1
    set_seed(seed)
    
    image = pipeline(prompt,height = 1080,width = 1080,num_images_per_prompt = 1,num_inference_steps=num_steps)
    
    image_name = "images/synth_{}_{}.jpeg"
    
    image_save = image.images[0].save(image_name.format(seed,num_steps))

messy room full of synthesizers. wires going everywhere. musical chaos. modular synthesizers everywhere. cluttered music room of synthesizers.

The room of synthesizers isn’t quite this bad, but some changes are needed to make everything more playable.

---

I’ve been really enjoying this simple setup. The zoom h6 is recording the EP133 through channels 1 and 2, and the piano is recorded with the stereo x/y capsule on top. Fun times jamming with a killer ep-133 metronome. Also, do really long takes, not caring about getting anything perfect, just laying down things that might turn into ideas later.

---

It’s been ages since I used a proper looper and the time seemed right. Apparently this will be arriving sometime this weekend, looking forward to messing around.