cutemix-v1

CHECKPOINT
Original


Updated:

4.9K

Recommended plotting parameters

Sampling method (sampler)

):

euler a: 25~

30 steps

dpm++ sde karras

: 20 to 30 steps

dpm++ 2m karras

: 20 to 40 steps

ddim: 30-60 steps high resolution fix (hires. fix)

Cue guidance coefficient

(cfg scale)

: 3~7 portrait character resolution (character resolution): 512x768, 768x768,

512x1024

Background and landscape resolution (background and landscape resolution): 768x512, 1024x512

, 1536x512

HD fix (hires.fix): 4x-ultrasharp, r-esrgan 4x, High score iteration steps

10 to 15 redraw amplitude 0.3 to 0.5

Clip skip: 2

negative reminders

: It is

recommended to use easynegative in the embedded embeddings model or

easynegativev2 suggests starting ad facial repair

Version Detail

SD 1.5
https://www.shakker.ai/es/modelinfo/c82b218e768643f7a30c50c4daf28532/cutemix-v1?from=search

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

Describe the image you want to generate, then press Enter to send.