Hotsquat XL [BETA v0.2]

LORA
Original


Updated:

No showcase images available, the model won't be visible to others.

SDXL LoRA Inspired by the original Hotsquat by @WaifuWizardWong

v0.2 retrained with Prodigy - MUCH better results.

Training Data

  • 62 images upscaled from SD1.5 generated images, 832x1216

  • 1984 steps, 12 epoch, Prodigy

Suggested Params

  • LoRA weight: 0.6-0.8

  • DPM fast or DPM++ 2M SDE Karras

  • 7-9 CFG scale

  • Res: 832x1216

USAGE AGREEMENT

This took an incredible amount of time and effort; please give proper credit when using. Other than that, go wild!

Donations always appreciated.

  • ETH / Any ERC20: 0x00eFf0937fC7468f76C299fc4A3c22CC9432757A

Leave a comment for a commissioned model.

The model deployment is abnormal, please re-upload/contact customer service.

Version Detail

SDXL 1.0
<ul><li><p>Standard LoRA trained w/ AdamW8bit</p></li><li><p>Needs heavy negative prompting</p></li></ul>

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