Am I able to request sdxl 1.0 webui, or can we use a sdxl model/checkpoint providing our own model?

[Irohika]

Am I able to request sdxl 1.0 webui, or can we use a sdxl model/checkpoint providing our own model?

[NUROISEA]

Yes you can use your own models by using this colab (PYOM) (direct colab link) just use the latest version of the web UI

Since this repository is on its "maintenance phase" meaning no major changes (or new notebooks in this case) I don't feel like adding a new notebook unless the demand is there (or if I feel like it lol)

[NUROISEA]

Quick update: I might be adding a notebook based on this model! It looks quite nice!

Probably I'm going to do this in a week or two.... probably

A test generation of my "mascot"/OC/whatever (large image)

1girl, blonde hair, blue eyes, short hair, wavy hair, hair ribbon, blue ribbon, detached sleeves, blue dress, portrait, smile

masterpiece, best quality, very aesthetic, absurdres

Negative prompt: nsfw, lowres, (bad), text, error, fewer, extra, missing, worst quality, jpeg artifacts, low quality, watermark, unfinished, displeasing, oldest, early, chromatic aberration, signature, extra digits, artistic error, username, scan, [abstract]
Steps: 28, Sampler: Euler a, CFG scale: 7, Seed: 3489155775, Size: 768x1344, Model: animagine-xl-3.1, Version: v1.8.0

[Irohika]

Let's gooooooooooooooooooooooooooooooooooooo
I loved the image

btw that size 768x1344 was with the upscale activated?

[NUROISEA]

Haven't used any upscaling, and it takes 1 step / second to generate.

[NUROISEA]

Added!

https://colab.research.google.com/github/NUROISEA/anime-webui-colab/blob/main/notebooks/animagine-xl.ipynb