Agony | XL

CHECKPOINT
Original


Updated:

Another attempt to do XL based checkpoint. This one is on the brighter side of the spectrum (compared to RE-Imagine XL).

Based on Animagine4, merged with Pony based checkpoint. Still on experimental phase.

Prompting is roughly the same since it uses Animagine4's clip.

Quality prompt: masterpiece, best quality, high score, great score, absurdres

You can put them in front or at the back, but I usually prefer it in front.

Negatives: lowres, bad anatomy, bad hands, text, error, missing finger, extra digits, fewer digits, cropped, worst quality, low quality, low score, bad score, average score, signature, watermark, username, blurry, (interlocked fingers)

Usage:

Sampler: Euler A

Steps: 25-30

CFG: 5 or 5.5

VAE: Auto or you can try SDXL vae fp16 fix

Image size: Around 1MP is best

Upscaler (optional): R-ESRGAN4x + Anime6B

Many thanks to Cagliostro Lab for creating Animagine.

ps. Yes, I like Wuthering Waves.

Version Detail

SDXL 1.0
Changelog: -Reduce brightness a bit -Reduce noise a bit -Changes in composition

Project Permissions

    Use Permissions

  • Use in TENSOR Online

  • As a online training base model on TENSOR

  • Use without crediting me

  • Share merges of this model

  • Use different permissions on merges

    Commercial Use

  • Sell generated contents

  • Use on generation services

  • Sell this model or merges

Related Posts