( Not my Model )

https://civitai.com/models/693181?modelVersionId=884037

Instructions for use

This model integrates the Hyper-SDXL-8steps model, recommends Clip Skip = -2, CFG = 2, Step = 10-20, Resolution = 832* 1216, 768* 1344 .

V1.6

This version is optimized based on V1.5-beta, maintaining the style of V1.5-beta, but with more detailed graphics.

The overall configuration is common to the V1.5-beta configuration.

Some problems still occur in some scenarios:

• The background part is directly generated when the prompt word is not filled in, which may lead to a large difference between the background of the picture and the light and shadow of the characters, or the background is a realistic style and the characters are an animation style, resulting in a more fragmented picture as a whole.

• When using hand action prompts, poor results are prone to occur.

• Some prompt words are prone to overly realistic pictures.

• The generation effect of some clothes may be poor.

Recommend:

• After filling in the background information related prompt words, you can add "photo background", "blurry background", "depth of field" and other prompt words, which helps to optimize the background blur effect and improve the background authenticity.

• The number of generating steps can be increased to 15.

• Zoom in on the model You can choose to use the x2 model to speed up the generation.

• Personal test: Using the RealESRGAN_x2plus will make the background that should be blurred clear, so please test it first if you use it.

Here are the recommended prompt example:

Postive Prompt: 
1girl, medium breasts, 
blunt bangs, hair up, looking at viewer, 
frilled one-piece swimsuit, white swimsuit, 
outdoors, onsen, wooden floor,  water, 
partially submerged, leaning forward, 
day, cloudy sky, mountain, 
BREAK cowboy shot, photo background, blurry background, depth of field, 
BREAK score_9,score_8_up,score_7_up, 

Negative Prompt: 
score_6,score_5,score_4,source_furry,source_pony,ugly,bad feet,bad hands,