Overview
This model was a commission.
A helper model to create bigger pregnant women (multiple pregnancy).
The trigger is pregnant as well as describing the size and shape of the belly.
This model cannot create NSFW on its own, but works with LoRAs like SNOFS (for Flux/Krea 2) or detailers on lower strength.
Krea 2 Turbo - V1
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: 0.3-1.0
Sampler: euler / euler a / euler+beta57
Steps: 8+
VAE: WAN 2.1
A photo of a pregnant woman standing in a dressing room, wearing a snug black dress. Her dress is stretched tight around her enormous protruding belly and torn at the front around her belly button. Side profile photo.Flux.2 [klein] 9B - V1
Training model: Flux.2 [klein] Base 9B
LoRA strength: 1.0
Sampler: euler / res_2s / res_multistep
Steps: 4-12
CFG: 1.0
A photo of a pregnant woman standing in a dressing room, wearing a snug dress. Her full breasts and huge belly are stretching her dress taut.ZIT - V1
Not compatible with Z Image Base.
Training model: Z Image De-Turbo
LoRA strength: 0.5-1.0
Sampler: euler / res_2s / res_multistep
Steps: 8+
CFG: 1.0
Prompt example:
A photo of a pregnant woman standing in a dressing room, wearing a snug black dress. Her dress is stretched tight around her huge belly and tearing open at the front. Side profile photo.Description
FAQ
Comments (6)
Your other Ideogram loras are great! Any chance of getting this one for Ideogram?
We have to see about that. People jumped off Id4 pretty much as soon as Krea 2 hit.
@cupra A shame... Ideogram seems much more capable when it comes to fine control of the image.
@randomaccount6894185 I guess the license, prompting style and now Krea 2 release killed it. Ideogram 4 can really produce better images than Krea 2, especially due to its superior VAE, but Krea 2 is just so much faster, learns better and is an overall better package.
@randomaccount6894185 use snofs or the realism engine and draw big enough boxes for the round stomach. idg4 already has a superior dataset knowledge. also try the new fast / instant idg4 models. those are great for finding good seeds first.
its just the license that isn't super friendly for lora makers, other than that its quality above quantity.
有個問題,如果拉遠,就會常常出現兩個人物,例如將人物站立,全身拍攝,1:1方形尺寸