Model trained with 2250 high quality photos in 640x960 resolution, generates images in vertical format, this model generates images of beautiful slim girls, medium breasts, it is an extremely realistic and photographic model, it is a concept focused on beauty, intimate fashion, lingerie, bikinis, casual clothing
I recommend using the Adetailer extension.
Use this extension to fix hand errors:
https://github.com/licyk/advanced_euler_sampler_extension
It is strictly prohibited to distribute, inside and outside civit ai, this template or post it anywhere or on hosting services, on third party image generation services, you can use it for personal use, if you know who distributed it without my consent , report it immediately.
Resolution settings:
Standard resolutions 512 x 640, 640x 768, 640x960
Resolution: 540x540 select the Hires.fix checkbox, result 1080 x 1080 pixels
Note: I am testing the sampling methods and I will add the others to the settings.
Use these recommended settings for generation:
Sampling method: Restart
Sampling steps: 30-50
CFG Scale: 2.0 - 7.0
Skip clip: 1-2
Sampling method: Kohaku_LoNyu_Yog
Sampling steps: 30-50
CFG Scale: 2.0 - 7.0
Skip clip: 1-2
Sampling method: Euler_Max
Sampling steps: 30-50
CFG Scale: 2.0 - 7.0
Skip clip: 1-2
Sampling method: Euler_Smea_Dy
Sampling steps: 18-50
CFG Scale: 2.0 - 7.0
Skip clip: 1-2
Sampling method: Euler a
Sampling steps: 18-50
CFG Scale: 2.0 - 7.0
Skip clip: 1-2
Sampling method: LCM
Sampling steps: 18-30
CFG Scale: 2.0 - 7.0
Skip clip: 1-2
Sampling method: DDPM Karras
Sampling steps: 18-30
CFG Scale: 2.0 - 7.0
Skip clip: 1-2
Sampling method: DPM++ 2M
Sampling steps: 18-30
CFG Scale: 2.0 - 7.0
Skip clip: 1-2
Sampling method: DPM++ SDE Karras
Sampling steps: 18-30
CFG Scale: 2.0 - 7.0
Skip clip: 1-2
Sampling method: DPM++ 2M SDE Karras
Sampling steps: 18-30
CFG Scale: 2.0 - 7.0
Skip clip: 1-2
Use the recommended negative prompt:
(CyberRealistic_Negative-neg), cartoon, painting, illustration, (grayscale:1.4), (worst quality:2), (low quality:2), (normal quality:2), ugly, fat, 3D rendering, asian, chinese, japansese, bad hands, malformed hand, amorphous hand, multiplied fingers, nipples
Description
This model generates images of beautiful women with white hair, blonde hair, generates images of other hair colors, is extremely realistic and photographic, has very strong color tones, select clip skip 1 or 2, note the hands are not of good quality I consider it to be a flaw that will be corrected in the next updates
FAQ
Comments (5)
Amazing model. Beautiful images and no extra body part issues. Thank you you for keeping this an SD1.5
Your feedback is very important, when I joined civitai, I had no idea how to use the models, I learned to merge, from now on I will implement many models in sd15 and they will all be trained, and many lora models, I will correct many of my models and the new ones will be identified as model + name and ending sd
Im a little new at this, Ive been playing around with merging models to see what I get but Im reluctant to do so with yours, the models are beautiful and amazing detail. Ive noticed after awhile people have switch from SD 1.5 to other more demanding models. Im curious what the average systems people are running, seems like a ton of downloads back in 2023 to now for the SD 1.5 but less for other models. Plus, new people like myself just starting, you have less of a selection to choose from. I appreciate your work and the people that have the love for what the SD 1.5 has to offer
The model is good, the girls are beautiful, the most important thing is that they take up little space and work quickly on my laptop, but don't you think the detail in the hair and skin is weak?
Good morning, this model lacks those hair and skin details. The dataset for this model was generated by another trained AI model; I didn't use images of real people or any available databases. I understand that this detail is missing, and your feedback is very important. I will add skin and hair details in future updates.