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

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

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