I present the model Lora Carla, trained with 600 high quality images, generates realistic and photographic images, with lingerie, bikini, dresses and work clothes, Carla is a high standard model, has a lot of beauty, sensuality, natural breasts, slim body and thin waist.
Carla is a random person, she is not part of the real world, I created and designed her using images generated by other trained AI models, this Lora model complies with the new Civitai standards.
To activate the lora module you need to insert the token: owcal and class: woman
recommended to use this weight:
<lora:Carla:0.6>
<lora:Carla:0.8>
<lora:Carla:0.9>
The vae is already included in the model, or use the one of your preference
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 768, 768 x 512, 540 x 960, 640 x 960, 960x640 and 1024 x1024
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, body multiplication, arms multiplied, neck with, long neck, nude, naked, chinese, japanese, asian, colored background, multiplied fingers, bad fingers, multiplied head, duplicate tail,malformed ears, bad horns, red skin, clean clothing, smooth fabric, realistic folds, high detail, glasses
BadDream, easynegative, UnrealisticDream, bad-hands-5, Asian-Less-Neg, (loli, petite, short, childlike, teen), floating dicks, chubby, fat, BREAK (worst quality:2), (low quality:2), (normal quality:2), lowres, bad anatomy, bad hands, multiple limbs, extra limbs, deformed limbs, normal quality, ((monochrome)), ((grayscale)), FastNegativeV2, fcNeg, long neck, malformed neck;
(worst quality, bad quality, poor quality)+, easynegative, monochrome, watermark, label, signature, frames, text, earring, necklace, jewelry, female accessories, masculine, male, extra digit, fewer digits, disfigured, extra fingers, deformed hands, bad anatomy, (asian)0.6, deformed pupils, deformed iris, inaccurate eyes, (moles, scars, blemishes)0.6, (freckles)0.3, (((unprofessional-bodies))),cartoon, painting, illustration, (worst quality, low quality, normal quality:2), epiCPhoto-neg
Trained model, with 600 high resolution photos, generates images with consistency, realistic and photographic, works with my models and other models from the community, we are working to bring more realistic and performant models!