Want to support me without Tipping? Here's how:
Liking my posts, collecting my images or collecting my models all generate buzz for me.
Generate more pictures of my models. I get a base commission from anyone who generates using my model, even without the tip.
Leave a like on my model. This helps me with the algorithm in reaching more people
Leave a review. I take all feedback very seriously, good or bad.
Consider using the 'add post' under gallery... if you are posting pictures of just my LoRA. This gives me A LOT of buzz, while you can also complete your daily post quest.
Cake4Daze was made with over 150 images of carefully curated art from various artists. This lora has not been trained on any anime or loli content, it works best when creating mature women, plus size women, and used to create western style images.
To boost your prompts with trigger: Cake4Daze_Style
Cake4Daze Style prompts:
Appearance: cute, pretty, beautiful,
Eyes: (color) eyes, pretty eyes, beautiful eyes,
Face Shape: fat face, round face, double chin
Hair: (color) hair, (length) hair, bangs, blunt bangs, bald, afro,
Skin: (color) skin, dark skin, pale skin, slime (substance),
Breasts: flat chest, small breasts, medium breasts, huge breasts, gigantic breasts, saggy breasts, puffy areolae, large areolae, erect nipples, inverted nipples,
Body: curvy, thicc, chubby, voluptuous, fat, plump, bbw, pawg, fat arms, fat rolls, back fat, belly, double belly, love handles, fat mons, fupa, thick thighs, wide hips, huge ass, booty (only use for describing someone from behind), cellulite,
Extras: glasses, retro glasses, (color) theme, pinup pose, sexy pose, lying, sitting, lewd eye contact, contrapposto, cowboy shot, high angle, low angle, front view, behind view,
Description
Keyword: C4k34D4z3StyleV2
"engine": "kohya",
"unetLR": 0.0001,
"clipSkip": 2,
"loraType": "lora",
"keepTokens": 1,
"networkDim": 32,
"numRepeats": 2,
"resolution": 1024,
"lrScheduler": "cosine",
"minSnrGamma": 0,
"noiseOffset": 0.03,
"targetSteps": 968,
"enableBucket": true,
"networkAlpha": 16,
"optimizerType": "AdamW8Bit",
"textEncoderLR": 0.00005,
"maxTrainEpochs": 4,
"shuffleCaption": false,
"trainBatchSize": 2,
"flipAugmentation": false,
"lrSchedulerNumCycles": 3
FAQ
Comments (6)
So awesome!
thank you!
This is awesome, my friend. I think I'm liking 80% of all your images. I think I'll spend a whole week working and remixing these images. Thanks so much for this incredible work!!!
Cake4Daze Version 3 is in the works.
I use this LoRa a ton. The prompting and image quality that come with it are top notch. Appreciate the hard work!
I'm working on version 3 at the moment, it's hard work cleaning and tagging training data but it's comments like this that keep me going.












