qchan Mix

There are currently 5 models (32 versions) in the qchan Mix series, including derivatives.

"qchan Mix" is for 2.5D style images.

v1.0: Basic 2.5D style (base model of all qchan Mix series)

v2.0: 2.5D Niji style

v3.0: Cute 2.5D style (bigger eyes, rounder face)

v4.0, v7.0: Basic 2.5D style (more variation and improved background)

v5.0: Elegant 2.5D style

v6.0: Fantasy 2.5D style

The top images were generated using the same prompts and conditions so that you can easily compare these models.

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

v7.0

"BRAVO - Arcane Fables Day" postbravo550 is one of my favourite models for image generaion with random prompts. So I considered merging it whith my qchan Mix series and the result was very nice.

BRAVO - Arcane Fables Day /model/1523005?modelVersionId=1723179

qchan Mix v3.0 /model/255778?modelVersionId=367119

qchan Mix v4.0 /model/255778?modelVersionId=384291

qchan Mix v6.0 /model/255778?modelVersionId=671370

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

v6.0

"NoosleepSweetdreams_v11" is a very unique model, full of fantasy and details, so I tried merging it with qcham Mix series together with other good models.

The models used are as follows (VAE is baked):

NoosleepSweetdreams_v11

Speculation (Model elements) Element splicing 6-28-30 /model/543552?modelVersionId=605677

qchan Mix v1.0 /model/255778?modelVersionId=288338

qchan Mix v5.0 /model/255778?modelVersionId=470497

realcartoon-Realistic v8 /model/97744?modelVersionId=161244

("NoosleepSweetdreams_v11" seems to have been deleted from Civitai.

If there is request from the owner of "NoosleepSweetdreams_v11" not to share merges, I will delete this version.)

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

v5.0

I was so impressed by the elegance of Kakarot 2.8D by vay_kakarot, I tried merging it with my qchan Mix series and found a very nice composition.

The models used are as follows (VAE is baked):

qchan Mix v4.0 /model/255778?modelVersionId=384291

Kakarot 2.8D V2024 /model/182723?modelVersionId=458684

qchan Mix v1.0 /model/255778?modelVersionId=288338

qchan Mix v2.0 /model/255778?modelVersionId=296919

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

v4.0

Variation and background of v1.0 was improved by merging some good models.

The models used are as follows (VAE is baked):

qchan Mix v1.0 /model/255778?modelVersionId=288338

porousdiamond v1.0.0 /model/303711/porousdiamond

wild_Fantasy_Mix v1.2 beta /model/270204?modelVersionId=315047

realcartoon-Realistic v8 /model/97744?modelVersionId=161244

qchan Mix v2.0 /model/255778?modelVersionId=296919

radiantrox v1.0 /model/207273?modelVersionId=233358

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

v3.0

I wanted cuter 2.5D model, so tried various recipes and found a satisfactory one.

The models used are as follows (VAE is baked):

qchan Mix v1.0 /model/255778?modelVersionId=288338

qchan Mix v2.0 /model/255778?modelVersionId=296919

CoharuMix v6 /model/198114?modelVersionId=352412

RealCartoon-Realistic v8 /model/97744?modelVersionId=161244

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

v2.0

I changed the taste of qchan Mix by merging with good 2.5D Niji type models.

The models used are as follows (VAE is baked):

qchan Mix v1.0 /model/255778?modelVersionId=288338

reQUIEM_lite /model/158526?modelVersionId=182937

nijiglee25D_eclipticV10 /model/235515?modelVersionId=265569

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

v1.0

There are already so many great models which are shared in Civitai, but I wanted to modify the appearance of the face just a little.

So I merged some of my favorite models (VAE is baked):

kawaiiRealisticAsian_v03 /model/83766?modelVersionId=100925

astranime_v5B /model/248011?modelVersionId=282308

majicmixFantasy_v20 /model/41865?modelVersionId=49055

majicmixFantasy_v30 /model/41865?modelVersionId=234105

realcartoonAnime_v7 /model/96629?modelVersionId=224080

beenyou_r13 /model/27688?modelVersionId=85614

Thanks to these models, the model I merged is highly versatile and can generate a variety of images.

If you like the faces of the images I generated, please try this model.

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

I usually enjoy random image creation using the "OneButtonPrompt" extension with the following conditions. (My PC isn't high spec so I haven't tried higher resolutions yet):

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 /model/116230?modelVersionId=125849

FastNegativeV2 /model/71961?modelVersionId=94057