Overview
A clothed version of my other macromastia LoRA. This one here cannot produce X or XXX reliably.
The model is pretty straight forward. Use the trigger early in your prompt. Further descriptions to the breasts position, framing and focus can help a lot to emphasize the effect.
Sometimes it creates thicker or chubby bodies, for that you can include descriptors like slim or skinny or use negative prompts.
Values over 1.0 may produce heavy artifacts. Decrease strength if you encounter artifacts. Most samples use a strength of 0.9.
For more, have a look at the example images/videos.
LTXV 2.3 (Sulphur 2) - V1
Coming in June...
Krea 2 Turbo - V1
Use the trigger mcrmst and describe the breast/cleavage in some detail. Use the WAN 2.1 VAE for more realistic outcomes. Use the filter bypass LoRA for better results.
Training model: Krea 2 Turbo + Training Adapter
LoRA strength: 0.5-1.3
Sampler: euler / euler a
Steps: 8+
VAE: WAN 2.1
mcrmst, A photograph of a woman with gigantic breasts, her voluminous, heavy breasts dramatically stretching and filling the soft beige cable-knit turtleneck sweater, creating deep curves and visible fabric tension despite the modest high neckline, sitting on a picnic blanket in a serene autumn forest.Ideogram 4 - V1
Experimental model. Things break and body horror may occur.
Trained on bounding boxes and JSON, but can be used without JSON structure prompts. Use the trigger gigantic breasts on a bounding box that should represent the woman's breasts. This way, the size and position can sort of be controlled.
Training model: Ideogram 4 fp8
LoRA strength conditional: 0.7-1.0
LoRA strength unconditional: 0.3-0.5
Sampler: euler / euler a
Steps: 20+
CFG: 3.0-6.0
{...} // have a look at the showcase promptsWAN 2.2 T2V - V1
After using the trigger macromastia, use additional triggers large, huge and gigantic to control the size further, see example video. Can be combined with Thiccification.
Training model: WAN 2.2 T2V
LoRA strength: 0.5-1.0
Sampler: euler / euler a
Use TripleKSampler with 1/4/4 steps or no lightning LoRAs at all for quality.
Use breast physics LoRAs to improve jiggle and motion for very large breasts. I highly recommend Huge Natural Breasts Physics at strength 0.3-0.5 for the high noise, no low noise needed or it will degrade texture quality.
macromastia, a 21-year-old ginger woman drinking a milkshake from a straw in a cafe. she's wearing a tight blouse and jeans. She has gigantic breasts and a large cleavage. Her face is pretty and freckled, she has big lips. Looking out the window, sitting at a table.Flux.2 [klein] 9B - V2
Use the trigger mcrmst and describe the breast/cleavage in some detail.
Training model: Flux.2 [klein] Base 9B
LoRA strength: 0.3-1.0
Sampler: euler / res_2s
Steps: 4+
CFG: 1.0
mcrmst, A photograph of a woman with gigantic breasts, her voluminous, heavy breasts dramatically stretching and filling the soft beige cable-knit turtleneck sweater, creating deep curves and visible fabric tension despite the modest high neckline, sitting on a picnic blanket in a serene autumn forest.Z-Image - V1
This model may also work with Z Image Turbo on higher strengths (1.0-2.0). You can also give Z Image Distilled a try.
After using the trigger macromastia, use additional triggers large, huge and gigantic to control the size further.
Experimenting with negative prompts and strengths can be very rewarding.
Training model: Z Image
LoRA strength: 0.3-1.0 (up to 2.0 on Turbo)
Sampler: res_2s+beta57 / euler / res_multistep / DPM++ 3M SDE
Steps: 40+ (8+ on Turbo)
CFG: 3.0-5.0 (1.0 on Turbo)
macromastia, A high quality photo of a beautiful young woman with long flowing auburn hair standing gracefully as the central figure in a vast field of tall sunflowers during golden hour sunset. She wears a light, flowing white summer dress that catches the warm breeze and is stretched over her large breasts, her skin glowing in soft natural light, subtle smile on her face.Z-Image Turbo - V2
Not compatible with Z Image Base.
Training model: Z Image De-Turbo
LoRA strength: 0.3-1.0
Sampler: euler / res_multistep / DPM++ 3M SDE
Steps: 8+
CFG: 1.0
Prompt example:
A photo of a cute woman with macromastia lying on a beach towel, wearing a yellow bikini revealing her breasts. Her breasts spill out the top of her bikini, forming a significant cleavage. She's bathing in the sun smiling at the camera. A summer day and warm candid setting.Description
FAQ
Comments (15)
Any chance of an LTX2.3 version?
The prompt understanding is awesome on it.
I was really disappointed with LTX2, but now with 2.3 I might give it a shot. After my next WAN update I'll tackle LTX2.3 :)
@cupraย Fair warning it's 95% identical. Quality falls off with distance by log^10 factor. Even more censored. Pretty much only good for close up face. For the quality to match WAN, it's generation time is actually higher.
@beqonyda467ย already did a few test and quick trainings. I can maybe get it done to a fun point, but not the quality of WAN or even Flux for that matter.
Thank you so much for this! It works wonderfully and has been a real problem before!
I wish it was Illustrious
Not really needed. In fact about 50% of the dataset was made with Illustrious.
@cupraย Really?
@cameronesmith0626357ย yes. I used a mixed dataset of real and AI generated images. The generated ones had multiple passes, but their anatomy was created with https://civitai.com/models/428826/damn-illustriouspony-realistic-model?modelVersionId=2041009
@cupraย Alright
For Flux, this lora changes the person appearance.
It does so for all models, unfortunately. Iโll try to improve on that with future versions.
@cupraย Please do, I love this lora ๐๐
If you're using ComfyUI and using something that can toggle blocks like the realtime-lora node pack, only having doubles 0, 1, 4, 5, 6, 7 and singles 0, 2, 3, 10, 11, 12, 13 enabled gives you most of the effects without doing things out-of-scope. It's a little finicky, and the first five singles are the most effecting blocks.
@kirhnย good point. Especially when mixing in other LoRAs it can help a lot.