Midlibrary: Library of 4000 Midjourney artistic styles
1–10 of 143 posts
Re: Midlibrary: Library of 4000 Midjourney artistic styles
#2Site no longer loading (anyone else?). Possible hug of death from hn traffic:
> A timeout occurred. Error code 524. Visit cloudflare.com for more information. 2024-01-13 04:34:06 UTC
Wayback machine gives a snapshot as at a few days ago:
https://web.archive.org/web/20240113031449/https://midlibrar...
Re: Midlibrary: Library of 4000 Midjourney artistic styles
#3If you like anime artists, there is this: https://rentry.co/NAIDv3artisttagtest, a list of 470 artists using the last model of NovelAI (this time they trained their model without removing artist names).
Fun fact, this model is based on SDXL, finetuned probably on a cluster of H100s (from coreweave).
Re: Midlibrary: Library of 4000 Midjourney artistic styles
#4If you like anime artists, there is this: https://rentry.co/NAIDv3artisttagtest , a list of 470 artists using the last model of NovelAI (this time they trained their model without removing artist names). Fun fact, this model is based on SDXL, finetuned probably on a cluster of H100s (from coreweave).
The consensus seems to be that the lack of open source SDXL anime fine tunes is simply due to laziness and lack of resources from the interested parties in the community. Datasets like from the boorus are already floating around online to train on. Always funny to see that furries are ahead of weeaboos in the war for the best open source nsfw generator
Re: Midlibrary: Library of 4000 Midjourney artistic styles
#5If you like anime artists, there is this: https://rentry.co/NAIDv3artisttagtest , a list of 470 artists using the last model of NovelAI (this time they trained their model without removing artist names). Fun fact, this model is based on SDXL, finetuned probably on a cluster of H100s (from coreweave).
The consensus seems to be that the lack of open source SDXL anime fine tunes is simply due to laziness and lack of resources from the interested parties in the community. Datasets like from the boorus are already floating around online to train on. Always funny to see that furries are ahead of weeaboos in the war for the best open source nsfw generator
I think it’s more that SD 1.5 is already fine for most purposes (and much, much faster)
Just don’t see any difference in results except them taking 4x longer.
Re: Midlibrary: Library of 4000 Midjourney artistic styles
#6If you like anime artists, there is this: https://rentry.co/NAIDv3artisttagtest , a list of 470 artists using the last model of NovelAI (this time they trained their model without removing artist names). Fun fact, this model is based on SDXL, finetuned probably on a cluster of H100s (from coreweave).
The consensus seems to be that the lack of open source SDXL anime fine tunes is simply due to laziness and lack of resources from the interested parties in the community. Datasets like from the boorus are already floating around online to train on. Always funny to see that furries are ahead of weeaboos in the war for the best open source nsfw generator
Well to be honest I don't really know what's the best furry SD XL model out there but recently this model has been released: https://huggingface.co/cagliostrolab/animagine-xl-3.0, it's probably far from the NovelAI checkpoint but I would be curious to know how it compares to the furry model you're talking about.
Re: Midlibrary: Library of 4000 Midjourney artistic styles
#7I like how it's called "Midilibrary" so it's obvious what it is
"Midjlibrary" would have been so gauche and unclear
Re: Midlibrary: Library of 4000 Midjourney artistic styles
#8I like how it's called "Midilibrary" so it's obvious what it is "Midjlibrary" would have been so gauche and unclear
It's called midlibrary, not "midilibrary" fortunately or that would be very confusing.
Re: Midlibrary: Library of 4000 Midjourney artistic styles
#9Earlier quoted context omitted.
The consensus seems to be that the lack of open source SDXL anime fine tunes is simply due to laziness and lack of resources from the interested parties in the community. Datasets like from the boorus are already floating around online to train on. Always funny to see that furries are ahead of weeaboos in the war for the best open source nsfw generator
I think it’s more that SD 1.5 is already fine for most purposes (and much, much faster) Just don’t see any difference in results except them taking 4x longer.
It’s an interesting example of a new technology that is inferior to the old one because the old one is superior in important ways (speed, ease of manipulation, and established toolsets).
Re: Midlibrary: Library of 4000 Midjourney artistic styles
#10If you like anime artists, there is this: https://rentry.co/NAIDv3artisttagtest , a list of 470 artists using the last model of NovelAI (this time they trained their model without removing artist names). Fun fact, this model is based on SDXL, finetuned probably on a cluster of H100s (from coreweave).
Lots of people (including potential trainers) struggle with SDXL I think. It just doesn't give you good results if you shove it into SD 1.5 frameworks and prompt it like SD 1.5.