[Checkpoint] BBMIX-Anniversary
模型简介：BBMIX-Anniversary
It is a model for the purpose of base modeling to match well with Lora.
referral prompt (I used)
(masterpiece),(intricate details),1girl,mature female,pale skin,{large breasts|huge breasts},smile, brown eyes
BREAK
{1$$short sleeves polo collar|flounce|chiffon|lolita|tunic|tight long|wrap|slip|midi|blazer|virgin_killer}_dress,
{1$$((pantyhose,high heels))|((baggy socks,converse))},
(({1$$sit|standing|reclining|walking|lying} on the anywhere)),{1$$((full body))|((upper body,portrait))},from {1$$below|above}:{1$$1.1|1.2|1.3|1.4},depth of field,looking at viewer
BREAK
{1$$day,sun,rainbow|day,sun,raining,rainbow|day,snow,windy,blue sky,ice|moon,night,meteor,cinematic lighting|sunset,dusk},((cumulonimbus)),
negative
{1$$EasyNegative|verybadimagenegative_v1.3}
VAE
clearvae_main , clearvae_main2
vae-ft-mse-840000-ema-pruned
We will continue to add sample images after finding good Loras so that we can copy and use EXIF in the sample post.
Precautions (Be sure to observe this)
Models may not be traded or sold. Because this is free. .
Models are not available for online paid services. (Free service available)
In using the model, all responsibility lies with the user.
How to high quality
You can output an image like the sample by using an extension to increase the quality. (All sample images were used with the extensions below)
1. Hires.fix -> SwinIR_4x or R-ESRGAN 4x+ Anime6B
2. Dynamic Thresholding (CFG Scale Fix)
3. Detection Detailer (must use)
4. SD upscaler or https://oo.pe/https://www.upscayl.org/
1.Hires.fix ( built-in ) or
2. Dynamic Thresholding
https://github.com/mcmonkeyprojects/sd-dynamic-thresholding.git
3.Detection Detailer
https://github.com/Bing-su/dddetailer.git
Questions that do not use the above four cannot be answered. Please note that images printed withou* ***ng the four extensions may not look good.
TIP
In order to keep token 75, do not insert resolution, detail, or quality tokens. Since extension add-ons such as DD or DT handle it anyway, there is no need to insert tokens like the ones below.
bad prompt (do not use)
Because this modelbase is a 3D and semirealistic model, it excludes the 2D highlight prompt and the flat color highlight prompt.
Notice
The sample images are created with random prompts and are only examples of what these images can be generated for. Therefore, images and prompts may not match.
R1
~~~~~~~~~~~~~~~~~~~~~~~o(*￣︶￣*)o~~~~~~~~~~~~~~~~~~~~~~~
主图提示词和参数：
Prompt: (masterpiece),(intricate details),1girl,mature female,Long layered style,,smile,huge breasts,brown eyes BREAK short sleeves polo collar dress,pantyhose,high heels, BREAK moon,night,meteor,cinematic lighting,((cumulonimbus)),((standing on the Golf course: Clubs, fairway, putt, swing, hole-in-one)),((full body)),from below:1.4,depth of field,looking at viewer
Negative prompt: (worst quality:1.5),(low quality:1.5),strabismus,verybadimagenegative_v1.3,badhandv4,bad anatomy,((pencil)),crossed legs,letterboxed,cutting_legs ,mole,nipples,
Steps: 30, Size: 512x960, Seed: 1419759942, Sampler: DPM++ SDE Karras, CFG scale: 7
页:
[1]