TOOLS

SDXL Model Guide: Image Generation, Inpainting, and Refinement Techniques

By

–

27 July 2023 20h14

This guide covers the basics, but also shows how you can use the SDXL model to: • make an image from another image (img2img)
• inpaint using a mask
• use a refiner to add fine-detail to your images

SDXL Open-Sourced: Run Generative AI with JavaScript, Python

By

–

27 July 2023 20h14

SDXL was open-sourced this week by @StabilityAI and it's already up on Replicate. You can run SDXL using JavaScript, Python, or any other language. Here's a guide to get you started running it with an API:

Python developers can now install Replicate via pip

By

–

27 July 2023 19h55

For you Python lovers, there's `pip install replicate`:

Installing Replicate with npm for Node.js

By

–

27 July 2023 19h55

If you're using Node.js, then `npm install replicate` and you're off to the races:

→ View original post on X — @lennysan

Tech Sponsors Supporting Podcast for Startups

By

@lennysan

–

27 July 2023 18h42

Thank you to our wonderful sponsors for supporting the podcast: @Mixpanel
—Event analytics that everyone can trust, use, and afford: https://
mixpanel.com/startups @HelloRound
—The private network built by tech leaders for tech leaders: https://
round.tech/apply @Get_Eppo—Run

→ View original post on X — @aiatmeta

Open Catalyst Demo: 100M Surface-Adsorbate Combinations Analysis

By

@aiatmeta

–

27 July 2023 18h14

The Open Catalyst demo supports adsorption energy calculations for 11,427 catalyst materials and 86 adsorbates, which amounts to ~100M catalyst surface-adsorbate combinations — a scale impossible to explore without machine learning.

→ View original post on X — @aiatmeta

Open Catalyst Demo Released for Accelerated Material Science Research

By

@aiatmeta

–

27 July 2023 18h13

Today we're releasing the Open Catalyst Demo to the public — this new service will allow researchers to accelerate work in material sciences by enabling them to simulate the reactivity of catalyst materials ~1000x faster than existing computational methods using AI.

Demo ⬇️
— AI at Meta (@AIatMeta) 27 juillet 2023

Today we're releasing the Open Catalyst Demo to the public — this new service will allow researchers to accelerate work in material sciences by enabling them to simulate the reactivity of catalyst materials ~1000x faster than existing computational methods using AI. Demo