diffusion

An illustrated guide showing how Stable Diffusion generates images from text using a CLIP-based text encoder, an image information creator, and an image decoder (Jay Alammar)

October 6, 2022

[ad_1] Jay Alammar: An illustrated guide showing how Stable Diffusion generates images from text using a CLIP-based text encoder, an…

A New York-based artist received copyright registration on a comic featuring artwork by Midjourney, the first known US copyright for latent diffusion AI art (Benj Edwards/Ars Technica)

September 26, 2022

[ad_1] Benj Edwards / Ars Technica: A New York-based artist received copyright registration on a comic featuring artwork by Midjourney,…

Sources: Stability AI, the startup behind Stable Diffusion, is in talks to raise $100M; Coatue proposed a $500M valuation, Lightspeed discussed a $1B valuation (Kenrick Cai/Forbes)

September 9, 2022

[ad_1] Kenrick Cai / Forbes: Sources: Stability AI, the startup behind Stable Diffusion, is in talks to raise $100M; Coatue…

A look at 12M+ of the 2.3B images used to train Stable Diffusion reveals ~47% came from only 100 domains; the largest number or 8.5% originated from Pinterest (Andy Baio/Waxy.org)

August 31, 2022

[ad_1] Andy Baio / Waxy.org: A look at 12M+ of the 2.3B images used to train Stable Diffusion reveals ~47%…

Unlike DALL-E 2, Stable Diffusion is open source and can run on high-end consumer GPUs, while its CreativeML Open RAIL-M license "strives for" "responsible" use (Alberto Romero/The Algorithmic Bridge)

August 29, 2022

[ad_1] Alberto Romero / The Algorithmic Bridge: Unlike DALL-E 2, Stable Diffusion is open source and can run on high-end…

Stable Diffusion, a DALL-E 2-like system now available to 1K+ researchers, is raising tricky ethical questions by allowing depictions of public figures and more (Kyle Wiggers/TechCrunch)

August 13, 2022

[ad_1] Kyle Wiggers / TechCrunch: Stable Diffusion, a DALL-E 2-like system now available to 1K+ researchers, is raising tricky ethical…