Anime Girl (Art Style Transformation Model)

Welcome to use the MIAOKA_Anime Girl model. This model is a character model in the style of class two-dimensional and the MiaoKa_reality style transformation model.

Welcome to use the miaoka_anime girl model which is a secondary model of the class and the transformation of the miaoka_reality model

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

This model is intended to be a fine-tuning model to fit the MiaoKa_reality Checkpoint model.

This model can make MiaoKa_reality change the painting style to the two-dimensional painting style.

Of course, this fine-tuning model can be used alone with other Checkpoint models.

This model is intended to be a fine-tuning model to fit the MiaoKa_reality Checkpoint model.

This model can make MiaoKa_reality change the painting style to the two-dimensional painting style.

Of course, this fine-tuning model can be used alone with other Checkpoint models.

Painting Style Change Method:

If you need to change the painting style into the two-dimensional style when using the MiaoKa_reality Checkpoint model, select A model to add:<lora:MIAOKA_Anime Girl:1> + B model: for example:<lora:MIAOKA_Meidusha_v1.0:1> to transform the painting style into the two-dimensional style.

If you need to change the painting style into quadratic painting style when using MiaoKa_reality Checkpoint model, you need to add model A: <lora:MIAOKA_Anime Girl:1> + B model: for example:<lora:MIAOKA_Meidusha_v1.0:1> The painting style can be transformed into a secondary painting style

      Before Style Transformation⬆                         After Style Transformation⬆

Usage Recommendations

This model is based on MiaoKa_reality training. It is recommended to use it with MiaoKa_realityCheckpoint model.

This model is based on MiaoKa_reality training. It is recommended to use it with MiaoKa_realityCheckpoint model.

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

Recommended Parameters:

Sampling Method (Sampler)::

Euler a: 20~30 steps.

DPM++ SDE Karras: 20~30 steps.

DPM++ 2M SDE Karras: 20~40 steps.

Prompt Word Guidance Coefficient (CFG Scale): 7

Character Resolution: 512x768, 768x768, 512x1024

Background and Landscape Resolution: 768x512, 1024x512, 1536x512

High-Resolution Restoration (Hires.fix):

Scaling Algorithm: R-ESRGAN 4x+Anime6b 4x-UltraSharp,

High-Score Iterations: 10~15,

Redraw Range: 0.3~ 0.5

Clip Skip: 2

Negatives: Recommended to use EasyNegative from the embedded embeddings model, or combination (worst quality, low quality: 1.4), monochrome, zombie, (interlocked fingers: 1.2) together.

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

Model Feedback AI Technology Exchange QQ Group: 377209248

The image source and training code are from the Internet, and the model is only used for scientific interest exchange. If there is infringement, please contact to delete, thank you.

The image source and training code are from the Internet, and the model is only used for scientific interest exchange. If there is infringement, please contact to delete, thank you.