seizaMix

CHECKPOINT
Original


Updated:

A simple mix I've been using for a little bit. I tried to go for a flatter, more colorful style than the usual models I've been using.

I'll probably try to tweak this a bit more in the future.

This model has a baked in VAE (vae-ft-mse-840000-ema-pruned).

Parameters

Samplers: DPM++ 2M Karras/DPM++ SDE Karras/DPM++ 2M SDE Karras; 25-30 steps

CFG Scale: 6-10

Resolutions: 512 x 768 / 768 x 512

Upscalers: 4x-AnimeSharp, 4x-UltraSharp

Clip Skip: 2

Positives: masterpiece, best quality

Negatives: (worst quality, low quality:1.4), bokeh, lowres, text, signature, sketch, watermark, artist name, speech bubble, blurry

Extensions: adetailer was used to upscale/enhance faces.

This mix is primarily comprised of Animelike 2.5D, Hassaku, and Galena Redux, with a bunch of other components. Thanks to @schneed for Galena Redux.

Version Detail

SD 1.5
<p>Formerly known as seizamix_ultra_v2. This is the dumbest name ever but I can't change it anymore. It's stuck.</p>

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.