{"id":37121,"date":"2022-09-23T16:36:00","date_gmt":"2022-09-23T20:36:00","guid":{"rendered":"https:\/\/mjtsai.com\/blog\/?p=37121"},"modified":"2022-09-24T08:28:44","modified_gmt":"2022-09-24T12:28:44","slug":"midjourney-and-stable-diffusion","status":"publish","type":"post","link":"https:\/\/mjtsai.com\/blog\/2022\/09\/23\/midjourney-and-stable-diffusion\/","title":{"rendered":"Midjourney and Stable Diffusion"},"content":{"rendered":"

Ben Thompson<\/a>:<\/p>\n

\n

The initial roll-out of large language models seemed to confirm this point of view: the two most prominent large language models have come from OpenAI and Google; while both describe how their text (GPT and GLaM, respectively) and image (DALL-E and Imagen, respectively) generation models work, you either access them through OpenAI’s controlled API, or in the case of Google don’t access them at all. But then came this summer’s unveiling of the aforementioned Midjourney, which is free to anyone via its Discord bot. An even bigger surprise was the release of Stable Diffusion<\/a>, which is not only free, but also open source — and the resultant models can be run on your own computer.<\/p>\n<\/blockquote>\n\n

Divam Gupta<\/a> (via Hacker News<\/a>):<\/p>\n

\n

Introducing Diffusion Bee<\/a>, the easiest way to run Stable Diffusion locally on your M1 Mac. Comes with a one-click installer. No dependencies or technical knowledge needed.<\/p>\n<\/blockquote>\n\n

Steve Troughton-Smith<\/a>:<\/p>\n

\n

Stable Diffusion on my M1 is kinda neat, but slows the system to a crawl for a minute or two while it processes. Stable Diffusion on my 3080 Ti, however, is blisteringly fast. 3 seconds to produce an image in a batch.<\/p>\n<\/blockquote>\n\n

It sounds like it doesn’t yet use the M1’s Neural Engine.<\/p>\n\n

Andy Baio<\/a> (Hacker News<\/a>):<\/p>\n

\n

As AI-generated art platforms like DALL-E 2, Midjourney, and Stable Diffusion explode in popularity, online communities devoted to sharing human-generated art are forced to make a decision: should AI art be allowed?<\/p>\n<\/blockquote>\n\n

See also: Dithering<\/a>, which had an interesting discussion of Midjourney’s Discord-based interface.<\/p>\n\n

Author<\/a>:<\/p>\n

\n

<\/p>\n<\/blockquote>\n\n

Previously:<\/p>\n