Extras

An API for accessing new AI models developed by OpenAI

We’ve created MuseNet, a deep neural network that can generate 4-minute musical compositions with 10 different instruments, and can combine styles from country to Mozart to the Beatles. MuseNet was not explicitly programmed with our understanding of music, but instead discovered patterns of harmony, rhythm, and style by learning to predict the next token in hundreds of thousands of MIDI files. MuseNet uses the same general-purpose unsupervised technology as GPT-2, a large-scale transformer model trained to predict the next token in a sequence, whether audio or text.

Scatena la tua immaginazione con le immagini generate dall'intelligenza artificiale create tramite contenuti concessi in licenza e usate in modo responsabile.

Point - E Github link: https://github.com/openai/point-e MeshLab (free) Download link: https://www.meshlab.net/#download Code used in the video (The two parts are split up by the ############): #1 ! pip install plotly -q #2 ! git clone https://github.com/openai/point-e #3 %cd point-e #4 ! pip install -e . #5 ! pip install open3d #6 import open3d import numpy as np ######################################################################################## #7 import plotly.graph_objects as go #8 fig_plotly = go.Figure(data=[go.Scatter3d( x=pc.coords[:,0], y=pc.coords[:,1], z=pc.coords[:,2], mode = 'markers', marker=dict(size=2, color=['rgb({},{},{})'.format(r,g,b) for r,g,b in zip(pc.channels["R"], pc.channels["G"], pc.channels["B"])], ) ) ], layout=dict( scene=dict( xaxis=dict(visible=False), yaxis=dict (visible=False), zaxis=dict(visible=False) ) ), ) #9 fig_plotly.show(renderer="colab") #10 pcd = open3d.geometry.PointCloud() pcd.points = open3d.utility.Vector3dVector(pc.coords) #11 open3d.io.write_point_cloud("FILENAME.ply", pcd) # After running this, Refresh directory and check for a file named FILENAME.ply ########################################################################################################## Thanks so much for watching this video about generating 3D models with Point - E AI! Music generated with Mubert: https://huggingface.co/spaces/Mubert/Text-to-Music Intro : 0:00 - 0:09 Point - e Setup: 0:09 - 1:08 Generating Point Cloud: 1:08 - 2:02 Downloading the Point Cloud: 2:02 - 2:20 Outro: 2:20 - 3:18