{midiblender} is alive!

{midiblender} is an R package for experimental genRative MIDI mangling

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 = "blender on white background. blender blending musical notes. cartoon. 80s retro."

for s in range(30):
  for n in [5,10]:
    seed = s+21
    num_steps = n+1
    set_seed(seed)
    
    image = pipeline(prompt,height = 1024,width = 1024,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))

R stats package logo

A super quick post to say that midiblender is alive on github.

The github repo is: https://github.com/CrumpLab/midiblender

This is the beginnings of an #rstats package for experimental mangling of #MIDI files. TBH, it’s my personal experimental hacky-code base wrapped in R package clothing. I’m messing with it constantly, and sharing in case others are interested.

I wrote a getting starting vignette that could be helpful for others to try stuff out.

Otherwise, I’m planning to keep posting examples and experiments on this blog. So, more {midiblender} to come.