PixAI Membership

📢 Login Issue Resolved — Earlier today, some users may have unexpectedly been logged out of their PixAI accounts, and this was due to a known ser…

View details

SDXL

Animagine XL 3.1

Animagine XL 3.1 - AI Model cover image
Trained by
Avatar image of Cagliostro Research Lab

Cagliostro Research Lab

Uploaded at
Mar 20, 2024, 1:40 AM
Uses
29.4k
Reviews
Excellent  (10)
Sampling Steps

20

CFG Scale

6

Negative

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]

Permissions
  • Allow image generation & sharing
  • Allow users to download this model
  • Allow commercial use of generated images

Recommended LoRAs

Left 4 dead - Witch illusXL - AI Model cover image

User LoRA

Left 4 dead - Witch illusXL
8
Balls/Testicles sucking LoRa | PonyXL & Illustrious - AI Model cover image

User LoRA

Balls/Testicles sucking LoRa | PonyXL & Illustrious
14
VERA v2 - AI Model cover image

User LoRA

VERA v2
0
Studio Ghibli Style - AI Model cover image

User LoRA

Studio Ghibli Style
835

Description

To guide the model towards generating high-aesthetic images, use negative prompts like:

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]

For higher quality outcomes, prepend prompts with:

masterpiece, best quality, very aesthetic, absurdres

it’s recommended to use a lower classifier-free guidance (CFG Scale) of around 5-7, sampling steps below 30, and to use Euler Ancestral (Euler a) as a sampler.

https://huggingface.co/cagliostrolab/animagine-xl-3.1

Comments4

Artwork made by Animagine XL 3.1

1
HomeModelsMio.2Profile