qchan anime Mix

詳細

ファイルをダウンロード

モデル説明

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

"qchan anime Mix" is for 2D anime style images.

v1.0, v3.0, v5.0: Basic 2D anime style

v2.0, v2.1, v4.0: Cute 2D anime style (bigger eyes, rounder face)

v6.0: Vivid 2D anime style

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

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

v6.0

NeoSD by aueki4g467 is a unique and vivid anime style model.

I tried merging it with qchan anime Mix series and the result was very nice.

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

qchan anime Mix 1.0 /model/257080?modelVersionId=289892

NeoSD v0.31 /model/1967523?modelVersionId=2288017

qchan anime Mix 3.0 /model/257080?modelVersionId=373667

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

v5.0

Yet another anime style version.

(v4.0 was too streched out so I moved back to a more basic style)

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

1610cute /model/347157/1610cute

qchan anime Mix 1.0 /model/257080?modelVersionId=289892

ZavyComics b1 /model/107613?modelVersionId=115754

porousdiamond v1.0.0 /model/303711/porousdiamond

qchan anime Mix 2.0 /model/257080?modelVersionId=293440

reweik_Uni023 Uni023 /model/329487?modelVersionId=369212

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

v4.0

This is another cute 2D anime style, a little more stretched out than the other qchan anime Mix models.

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

1610cute /model/347157/1610cute

CoharuMix v6 /model/198114?modelVersionId=352412

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

qchan anime Mix 3.0 /model/257080?modelVersionId=373667

AnimeChaotic v2 /model/269490?modelVersionId=317742

1610cute- /model/347203/1610cute

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

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

v3.0

I wanted to add more variation to qchan anime Mix, so I merged it with two good models, reweik_Uni023 and CoharuMix.

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

qchan anime Mix 1.0 /model/257080?modelVersionId=289892

reweik_Uni023 Uni023 /model/329487?modelVersionId=369212

CoharuMix v6 /model/198114?modelVersionId=352412

It seems that the NSFW capability has also increased.

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

v2.1

The cuteness of v2.0 has been improved by adjusting the merge composition.

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

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

AnimeChaotic v2 /model/269490?modelVersionId=317742

qchan anime Mix 1.0 /model/257080?modelVersionId=289892

Featureless Cute Mix v1.0 /model/149907?modelVersionId=167499

manmaruMix_v20 /model/86277?modelVersionId=116017

HotaruBreed Type D v5.0 /model/191365?modelVersionId=278870

Blazing Drive V08c /model/121083?modelVersionId=157358

ZavyComics b1 /model/107613?modelVersionId=115754

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

v2.0

This is a cuter version of qchan anime Mix.

Eyes of the characters tend to be bigger and faces rounder.

This was done by merging cute type anime models to qchan Mix.

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

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

CuteYukiMix Adorable Style SpecialChapter /model/28169?modelVersionId=195410

HotaruBreed Type D v5.0 /model/191365?modelVersionId=278870

qchan anime Mix 1.0 /model/257080?modelVersionId=289892

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

v1.0

After I launched my first merge model "qchan Mix", I wanted a new model with a more anime taste. So I merged some good anime models to qchan Mix.

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

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

Blazing Drive V12g /model/121083?modelVersionId=245691

HotaruBreed Type D v5.0 /model/191365?modelVersionId=278870

Blazing Drive V08c /model/121083?modelVersionId=157358

This model is also highly versatile and can generate a variety of images.

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

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

このモデルで生成された画像

画像が見つかりません。