qchan Variations

In this series, I will add some good and unique models to qchan mix models.

Since I'm not so concerned with retaining the atmosphere of qchan mix series, the merged models are expected to be more flexible.

My criterion for evaluating a model is whether it can generate exciting images from random prompts.

The top images are made from the same prompts so that you can easily compare the models. (The prompts are different from other qchan mix series)

------------------------------------------------------------------------------------------------------

realisticAsian1

Models used in the merge:

qchan Variations realistic1 https://civitai.com/models/755627?modelVersionId=950038

yayoi_mix v2.5 https://civitai.com/models/83096?modelVersionId=178711

DGirl v6.21 https://civitai.com/models/130304?modelVersionId=359842

------------------------------------------------------------------------------------------------------

anime2

Models used in the merge:

Nostalgia-mix Nostalgia https://civitai.com/models/16819/nostalgia-mix

Nostalgia-clear Nostalgia-clear https://civitai.com/models/17461?modelVersionId=20640

qchan anime Mix v2.1 https://civitai.com/models/257080?modelVersionId=331324

qchan anime Mix v1.0 https://civitai.com/models/257080?modelVersionId=289892

------------------------------------------------------------------------------------------------------

semireal1

Models used in the merge:

qchan Variations realistic1 https://civitai.com/models/755627?modelVersionId=950038

qchan Variations 25d1 https://civitai.com/models/755627?modelVersionId=898698

------------------------------------------------------------------------------------------------------

realistic1

Models used in the merge:

Uber Realistic Porn Merge (URPM) - v2.2 https://civitai.com/models/2661?modelVersionId=908394

qchan realistic Mix - v3.0 https://civitai.com/models/258175?modelVersionId=489345

------------------------------------------------------------------------------------------------------

25D1

Models used in the merge:

PorousObsidian - v1.0 https://civitai.com/models/274233?modelVersionId=309092

qchan Mix - v5.0 https://civitai.com/models/255778?modelVersionId=470497

qchan Mix - v4.0 https://civitai.com/models/255778?modelVersionId=384291

------------------------------------------------------------------------------------------------------

anime1

Models used in the merge:

ZenTypeW - V1 https://civitai.com/models/745763/zentypew

qchan anime Mix - v4.0 https://civitai.com/models/257080?modelVersionId=547819

------------------------------------------------------------------------------------------------------

I usually enjoy random image creation using Web UI A1111 and "OneButtonPrompt" extension with the following conditions:

Sampler: Euler A

Steps: 40

Width x Height: 512 x 768

CFG scale: 7

Denoising strength: 0.3

Clip skip: 1

Hires upscaler: 4x-UltraSharp

Hires upscale: 2

Hires steps: 10

Denoising strength: 0.3

OneButtonPrompt strength: 10

Common prompt (prefix): 1girl

Base negative prompt: bad-hands-5, FastNegativeV2

No auto generate negative

------------------------------------------------------------------------------------------------------

For negative prompts, bad-hands-5 and FastNegativeV2 seem to work with this model.

bad-hands-5 https://civitai.com/models/116230?modelVersionId=125849

FastNegativeV2 https://civitai.com/models/71961?modelVersionId=94057