RE-Imagine | XL

CHECKPOINT
Original


Updated:

An attempt to do XL based checkpoint.

Based on Animagine4, merged with an Illustrious 0.1 based checkpoint.

Prompting should be the same since it uses Animagine4's clip. Check Cagliostro Lab's official guide here.

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

Put in front if you don't want certain artist tag, put at the back if you want to use artist tag. I personally don't know anything about artists so I usually put them 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

Usage:

Sampler: Euler A

Steps: 25-30

CFG: 5 (or 5.5)

VAE: Auto

Image size: Around 1MP is best. If you want to go higher (like 1024x1536), you'd better off doing upscale.

Upscaler (optional): R-ESRGAN4x + Anime6B

Many thanks to Cagliostro Lab for creating Animagine.

Version Detail

SDXL 1.0
This version might be very different from A1 because of my attempt to fix the blurry issue in A1. Result might be a bit lighter, not what I intended since originally this was on the darker side compared to Agony which is on the light/brighter side. Composition will also be different and you might not like it, but I do hope user experience can increase because I managed to address the blurry issue (at least locally, on a mid-entry GPU from 2019). Changelog: - Parameter change - Addressed the blurry issue

Project Permissions

Reprinting is strictly prohibited

    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