Running SANA Text-to-Image locally on Windows

Render Realm · Beginner ·📰 AI News & Updates ·1y ago
SANA is the new, blazing-fast Text-to-Image model from NVIDIA, where you can create images with a size up to 4096x4096 pixel in just a few seconds. While an Online-Demo has been out for a little while, it's now possible to run it on a local machine with an NVIDIA-GPU. By this time, it's only meant to be for Linux, but in this tutorial I will show you how to run it on Windows, using the built-in Windows Subsystem for Linux (WSL). The installation process will be explained step by step and you can find the commands for each step further down below. Hope it can be helpful to you! Chapters: ==…
Watch on YouTube ↗ (saves to browser)

Chapters (10)

Intro, Requirements
0:55 Installing the Windows Subsystem for Linux (WSL)
1:29 Cloning SANA from Github
2:41 Installing Conda on WSL
4:16 Create and activate the virtual environment for SANA
4:36 Installing Cuda, Torch, xFormers and SANA libraries
5:20 Create and install Huggingface-Token
6:30 Starting SANA for the first time
7:10 Creating images with SANA
8:03 How to start SANA after the installation
MCP Dev Summit [Day 1] ft. Anthropic, Hugging Face, Open AI & Microsoft
Next Up
MCP Dev Summit [Day 1] ft. Anthropic, Hugging Face, Open AI & Microsoft
MLOps.community