RE-Imagine XL

CHECKPOINT
Original


Updated:

An attempt to do XL based checkpoint.

Based on Animagine4

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

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

Put in front for more highlight and glow, put at the back if you want a darker tone.

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 - 7 (Usually 5)

VAE: Auto

Image size: Around 1MP is best

Upscaler (optional): R-ESRGAN4x + Anime6B

Version Detail

SDXL 1.0
Changelog: >Some parameter changes >Addressing brightness and saturation issue Known Issue: > Somewhat blurry when using ADetailer and broken when generating + upscale (upscaling separately works though).

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