Ive been trying to get bigger bellies with XL, so far no luck, sad too, because nobody has made a pregnancy lora for xl yet.

use hyperfusion prompt

that's a lora for 1.5, not a prompt.

(November 24, 2023, 7:02 pm)Justaperv that's a lora for 1.5, not a prompt.

try comically large belly or big round belly,that's what i use

https://preggophilia.com/civitai-creations-t

Well one possiblity is generate with 1.5 for a high percentage of the steps, then SDXL for the remaining steps. Or do the reverse, use SDXL initially to get the consistent prompting with just enough of the composition, and finish off with a realistic 1.5 model (plus upscale I guess) plus lora.

Personally I haven't really been using SDXL, least with my GPU generations take slightly too long for experimenting with. You can still get good milage from 1.5 with a good model, and IPAdapter.

(November 25, 2023, 11:38 am)mimmiberg Well one possiblity is generate with 1.5 for a high percentage of the steps, then SDXL for the remaining steps. Or do the reverse, use SDXL initially to get the consistent prompting with just enough of the composition, and finish off with a realistic 1.5 model (plus upscale I guess) plus lora.

Personally I haven't really been using SDXL, least with my GPU generations take slightly too long for experimenting with. You can still get good milage from 1.5 with a good model, and IPAdapter. 

i would do that but i can't download stabble difussion whenever i try something goes wrong

There's one SDXL pregnancy lora on civitai, it's for photorealism but could help with artistic SDXL models as well. It's not great but it's better than the base models. There's still no hyperpreg SDXL model on there so getting bigger bellies is a challenge.
 
Switching models gets great results but it's either a lot of extra work in a1111, or it takes a bit of setting up in comfyUI. And the extra power needed for SDXL pushes it out of reach for a lot of people, I've only just started to work with it after upgrading my pc. 

If you're having trouble installing Stable Diffusion try the Stability Matrix installer/manager.

I've just uploaded a Lora! - PreggoXL on civitai.com
alt link: PreggoXL on huggingface.co

It does big bellies, I haven't tried it for hyperpreg sizes.

Here's a few example pics using different SDXL base models, generation parameters are in the metadata:

   
   
   
   
   
   
   
   

Can anybody give an example prompt for such images? I've been trying for some time and images are worse than terrible :|

Those were just test outputs so they're pretty simple; SDXL responds well to simple prompting, not as well as Midjourney/Dall-e 3 but far better than SD1.x/2.x. The following uses the syntax from A1111 to invoke the lora within the prompt. (it's all the same lora).

Image 1:

Quote:Prompt: your pregnant big tiddy goth GF wearing a sheer gothic lace dress <lora:preggoXL_v0.1a:0.7>
Negative prompt: crosseyed
Steps: 32, Sampler: DPM++ 3M SDE, CFG scale: 4, Size: 768x1024, Model: xl_realismarkPlus_realismarkPlus, VAE: sdxl_vae_fp16fix.safetensors,  Lora hashes: "preggoXL_v0.1a: 780246d31fe8"

Image 2:

Quote:Prompt: pregnant clubgirl friends dancing under disco lights wearing party dresses <lora:preggoXL_v0.1a:0.4>
Negative prompt: blurry, blurred, painting, illustration, cartoon, 3d, cgi, render, vagina, explicit, porn, young, teen
Steps: 20, Sampler: Restart, CFG scale: 4, Size: 1024x768, Model: Photosomnia XL v0.9, VAE: sdxl_vae_fp16fix.safetensors, Denoising strength: 0.3, NGMS: 0.2, Hypertile U-Net: True, Hypertile VAE: True, Hires sampler: DPM++ 2M, Hires upscale: 1.5, Hires steps: 12, Hires upscaler: 4x-UltraSharp, Lora hashes: "preggoXL_v0.1a: 780246d31fe8", Discard penultimate sigma: True, Extra noise: 0.02

Image 3:

Quote:Prompt: pregnant woman at the park<lora:pxl2:1>
Steps: 32, Sampler: DPM++ 2M SDE, CFG scale: 4, Size: 768x1024, Model: Photosomnia XL v0.9, VAE: sdxl_vae_fp16fix.safetensors, Denoising strength: 0.2, NGMS: 0.2, Hypertile U-Net: True, Hypertile VAE: True, Hires upscale: 2, Hires steps: 16, Hires upscaler: 4x-UltraSharp, Lora hashes: "pxl2: 780246d31fe8", Discard penultimate sigma: True, Eta: 0, Sigma noise: 0.9, Extra noise: 0.02

Image 4:

Quote:Prompt: a pregnant female ww2 fighter pilot propaganda poster <lora:pxl2:0.8>
<no negative prompt>
Steps: 30, Sampler: Restart, CFG scale: 4, Size: 1024x768, Model: xl_realismarkPlus_realismarkPlus, VAE: sdxl_vae_fp16fix.safetensors, NGMS: 0.2, Hypertile U-Net: True, Hypertile VAE: True, Lora hashes: "pxl2: 780246d31fe8", Discard penultimate sigma: True

Image 5: 

Quote:Prompt: pregnant preggo catgirl wearing a traditional french maid costume patrolling the postapocalyptic wasteland with a wolf <lora:SDXL pregnancy v0.1a:0.4>
<no negative prompt>
Steps: 32, Sampler: DPM++ 3M SDE, CFG scale: 4, Size: 768x1024, Model: xlm2.fp16, VAE: sdxl_vae_fp16fix.safetensors, NGMS: 0.2, Hypertile U-Net: True, Hypertile VAE: True, Lora hashes: "SDXL pregnancy v0.1a: 780246d31fe8", Eta: 0, Sigma noise: 0.9

Image 6:

Quote:Prompt: pregnant preggo babe at the poolside <lora:SDXL pregnancy v0.1a:0.4>
Negative prompt: crosseyed
Steps: 32, Sampler: DPM++ 3M SDE, CFG scale: 4, Size: 768x1024, Model: xlm2.fp16 VAE: sdxl_vae_fp16fix.safetensors, NGMS: 0.2, Hypertile U-Net: True, Hypertile VAE: True, Lora hashes: "SDXL pregnancy v0.1a: 780246d31fe8", Eta: 0, Sigma noise: 0.9

Image 7:

Quote:Prompt: pregnant babe at the poolside <lora:preggoXL_v0.1a:0.6>
Negative prompt: crosseyed
Steps: 32, Sampler: DPM++ 3M SDE, CFG scale: 4, Size: 768x1024, Model: caroselloxlOldFlat_10, VAE: sdxl_vae_fp16fix.safetensors, NGMS: 0.2, Hypertile U-Net: True, Hypertile VAE: True, Lora hashes: "preggoXL_v0.1a: 780246d31fe8", Eta: 0, Sigma noise: 0.9

Image 8:

Quote:Prompt: pregnant blonde woman in a one-piece swimsuit at the poolside <lora:preggoXL_v0.1a:0.7>
Negative prompt: crosseyed
Steps: 32, Sampler: DPM++ 3M SDE, CFG scale: 4 Size: 768x1024, Model: xl_realismarkPlus_realismarkPlus, VAE: sdxl_vae_fp16fix.safetensors, NGMS: 0.2, Hypertile U-Net: True, Hypertile VAE: True, Lora hashes: "preggoXL_v0.1a: 780246d31fe8", Eta: 0, Sigma noise: 0.9