File size: 7,777 Bytes
158667b 45bcb92 158667b 74b3e81 45bcb92 158667b fafaeda 158667b 74b3e81 158667b 45bcb92 fafaeda 158667b fafaeda 158667b |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 |
import argparse
import binascii
import glob
import openai
import os
import os.path
import numpy as np
import matplotlib.pyplot as plt
import random
import sys
import tempfile
import time
import torch
from PIL import Image
from IPython.display import Audio
from diffusers import StableDiffusionPipeline
from diffusers import DiffusionPipeline
from transformers import pipeline
from transformers import ViTFeatureExtractor, ViTForImageClassification
from audiodiffusion import AudioDiffusion
import requests
notes = ["C", "C#", "D", "D#", "E", "F", "F#", "G", "G#", "A", "A#", "B"]
def fake_gan():
images = [
(random.choice(
[
"https://images.unsplash.com/photo-1507003211169-0a1dd7228f2d?ixlib=rb-1.2.1&ixid=MnwxMjA3fDB8MHxwaG90by1wYWdlfHx8fGVufDB8fHx8&auto=format&fit=crop&w=387&q=80",
"https://images.unsplash.com/photo-1554151228-14d9def656e4?ixlib=rb-1.2.1&ixid=MnwxMjA3fDB8MHxwaG90by1wYWdlfHx8fGVufDB8fHx8&auto=format&fit=crop&w=386&q=80",
"https://images.unsplash.com/photo-1542909168-82c3e7fdca5c?ixlib=rb-1.2.1&ixid=MnwxMjA3fDB8MHxzZWFyY2h8MXx8aHVtYW4lMjBmYWNlfGVufDB8fDB8fA%3D%3D&w=1000&q=80",
"https://images.unsplash.com/photo-1546456073-92b9f0a8d413?ixlib=rb-1.2.1&ixid=MnwxMjA3fDB8MHxwaG90by1wYWdlfHx8fGVufDB8fHx8&auto=format&fit=crop&w=387&q=80",
"https://images.unsplash.com/photo-1601412436009-d964bd02edbc?ixlib=rb-1.2.1&ixid=MnwxMjA3fDB8MHxwaG90by1wYWdlfHx8fGVufDB8fHx8&auto=format&fit=crop&w=464&q=80",
]
), f"label {i}" if i != 0 else "label" * 50)
for i in range(3)
]
return images
def imageClassifier(inputImage):
#fn=artist_lib.imageClassifier,
#url = 'http://images.cocodataset.org/val2017/000000039769.jpg'
#image = Image.open(requests.get(url, stream=True).raw)
image = inputImage
feature_extractor = ViTFeatureExtractor.from_pretrained('google/vit-base-patch16-224')
model = ViTForImageClassification.from_pretrained('google/vit-base-patch16-224')
inputs = feature_extractor(images=image, return_tensors="pt")
outputs = model(**inputs)
logits = outputs.logits
# model predicts one of the 1000 ImageNet classes
predicted_class_idx = logits.argmax(-1).item()
#print("Predicted class:", model.config.id2label[predicted_class_idx])
return "Predicted class:", model.config.id2label[predicted_class_idx]
def audioGenerator(inputText):
device = "cuda" if torch.cuda.is_available() else "cpu"
dtype = torch.float16 if torch.cuda.is_available() else torch.float32
pipe = DiffusionPipeline.from_pretrained("teticio/audio-diffusion-256").to(device)
output = pipe()
from IPython.display import display
display(output.images[0])
display(Audio(output.audios[0], rate=pipe.mel.get_sample_rate()))
print("sample rate is ", pipe.mel.get_sample_rate())
#print(Audio(output.audios[0]))
sr=int(pipe.mel.get_sample_rate())
audio=Audio(output.audios[0])
#return int(pipe.mel.get_sample_rate()), Audio(output.audios[0])
return sr, audio
def generate_spectrogram_audio_and_loop(model_id):
audio_diffusion = AudioDiffusion(model_id=model_id)
image, (sample_rate,
audio) = audio_diffusion.generate_spectrogram_and_audio()
loop = AudioDiffusion.loop_it(audio, sample_rate)
if loop is None:
loop = audio
return image, (sample_rate, audio), (sample_rate, loop)
def generate_tone(note, octave, duration):
sr = 48000
a4_freq, tones_from_a4 = 440, 12 * (octave - 4) + (note - 9)
frequency = a4_freq * 2 ** (tones_from_a4 / 12)
duration = int(duration)
audio = np.linspace(0, duration, duration * sr)
audio = (20000 * np.sin(audio * (2 * np.pi * frequency))).astype(np.int16)
return sr, audio
def draw(inp, this_model, force_new):
device = "cuda" if torch.cuda.is_available() else "cpu"
dtype = torch.float16 if torch.cuda.is_available() else torch.float32
drawing = inp
if this_model == "stable-diffusion-2":
this_model_addr = "stabilityai/stable-diffusion-2"
images_dir = 'images2/'
elif this_model == "stable-diffusion-2-1":
this_model_addr = "stabilityai/stable-diffusion-2-1"
images_dir = 'images2-1/'
elif this_model == "stable-diffusion-v1-5":
this_model_addr = "runwayml/stable-diffusion-v1-5"
images_dir = 'images/'
else:
raise gr.Error("Unknown Model!")
mkdir_if_not_exist(images_dir)
drawing_filename = images_dir + drawing.replace(' ', '_') + '.png'
if os.path.exists(drawing_filename):
if force_new:
new_drawing_filename = images_dir + drawing.replace(' ', '_') + '.' + str(time.time()) + '.png'
os.replace(drawing_filename, new_drawing_filename)
else:
print("found drawing ", drawing_filename)
return Image.open(drawing_filename)
print("generating drawing '", drawing, "'", drawing_filename)
pipe = StableDiffusionPipeline.from_pretrained(this_model_addr, torch_dtype=dtype)
pipe.enable_attention_slicing()
pipe = pipe.to(device)
image = pipe(drawing).images[0]
image.seek(0)
image.save(drawing_filename)
return image
def write_blog(inp, this_model, min_length, max_length, force_new):
blog_post_name = inp
if this_model == "gpt-neo-1.3B":
this_model_addr = "EleutherAI/gpt-neo-1.3B"
text_dir = 'text1.3/'
elif this_model == "gpt-neo-2.7B":
this_model_addr = "EleutherAI/gpt-neo-2.7B"
text_dir = 'text2.7/'
else:
raise gr.Error("Unknown Model!")
mkdir_if_not_exist(text_dir)
target_filename = text_dir + blog_post_name.replace(' ', '_') + '.txt'
if os.path.exists(target_filename):
if force_new:
new_target_filename = text_dir + blog_post_name.replace(' ', '_') + '.' + str(time.time()) + '.txt'
os.replace(target_filename, new_target_filename)
else:
print("found drawing ", target_filename)
with open(target_filename, 'r') as file:
return file.read()
print("generating blog '", blog_post_name, "'", target_filename)
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
dtype = torch.float16 if torch.cuda.is_available() else torch.float32
#generator = pipeline('text-generation', model='EleutherAI/gpt-neo-2.7B', device=device, torch_dtype=dtype)
#generator = pipeline('text-generation', model=this_model_addr, torch_dtype=dtype)
#generator = pipeline('text-generation', model=this_model_addr)
generator = pipeline('text-generation', model=this_model_addr, device=device, torch_dtype=dtype)
# AttributeError: 'TextGenerationPipeline' object has no attribute 'enable_attention_slicing'
#generator.enable_attention_slicing()
res = generator(blog_post_name, min_length=min_length, max_length=max_length, do_sample=True, temperature=0.7)
blog_post_text = res[0]['generated_text']
with open(target_filename, 'w') as file:
file.write(blog_post_text)
return blog_post_text
def nameMyPet(inp):
animal = inp
response = openai.Completion.create(
model="text-davinci-003",
prompt=generate_prompt(animal),
temperature=0.6,
)
return response.choices[0].text
def mkdir_if_not_exist(path):
if os.path.exists(path):
return 0
else:
os.mkdir(path)
def generate_prompt(animal):
return """Suggest three names for an animal that is a superhero.
Animal: Cat
Names: Captain Sharpclaw, Agent Fluffball, The Incredible Feline
Animal: Dog
Names: Ruff the Protector, Wonder Canine, Sir Barks-a-Lot
Animal: {}
Names:""".format(
animal.capitalize()
)
|