Pregnant AI Artwork
|
Training a new model
- 2 Vote(s) - 5 Average
- 1
- 2
- 3
- 4
- 5
|
|
Nope2468 (112)
November 17, 2022, 12:12 am
(Edited)
|
Posts: 58
Joined: Jan 2018
Reputation: 112
November 17, 2022, 12:12 am by Nope2468 (112)
(Edited)
So I've been messing around with Stable diffusion a lot and all the different models out there including NAI, F222, 1.5, the hpreg one on here, and some other mixes. I tend to lean towards realism style images and am currently testing the waters training yet another model on some images from the site. I'm not expecting it to work all that great as I've found that even though variety of photos helps to train new AI models it needs consistency in the focus. IE. Using photos of a woman with different makeup causes artifacting around the eyes etc... Anyways what I'm hoping to do is find a model either willing to help me out by getting a simple variety of photos while maintaining some consistency (Belly shape, belly button, body, etc) Either that or to find a good trove of a model to dig out pictures from. I'm ideally thinking nude but would like to train it on clothed photos as well after some experimentation. Unfortunately I am not in the position to pay for these photos but am completely willing to upload the model here after I work on it and get it to an adequate state.
Here is a list of what I am trying to accomplish:
-Better shape and size, Ideally a full term average pregnancy or multiples. Aiming for realism and not absurdity
-Consistency with belly buttons and anatomy of pregnant bodys as even the best anatomy models seem to struggle when it comes to pregnancy
-Want to start work with naked full term pregnancy and move from there to clothed and even first and second trimester concepts
-Any other recommendations will be taken into consideration.
Also of note- Face is not required at all for any photos. Actually it would be ideal not to have a face in most of them.
I am fairly new to this but have experienced success in training concepts before. Thank you for any help and feel free to message me/post here if there is anything I have missed. Depending on how this current model turns out I may wind up posting it for others to use.
I will also post generations depending on how the current model turns out.
|
Nope2468 (112)
November 17, 2022, 2:05 am
|
Posts: 58
Joined: Jan 2018
Reputation: 112
Liked by 25 members: Spongechu123 (Dec 23, 2023), Iganinjaartist (Sep 22, 2023), preggolover91 (May 18, 2023), Bellylord123 (Feb 9, 2023), Njameson (Jan 24, 2023), Tcorker (Dec 8, 2022), Ikru88 (Dec 2, 2022), Eskar13 (Nov 21, 2022), bumpbaker (Nov 20, 2022), mr-enigma (Nov 18, 2022), cripple135 (Nov 18, 2022), greatpix78 (Nov 18, 2022), JaxsonStark (Nov 17, 2022), Gymbo4Ever (Nov 17, 2022), KodiUser (Nov 17, 2022), peterwein (Nov 17, 2022), chops79 (Nov 17, 2022), deux_anges (Nov 17, 2022), Bred_anonymously (Nov 17, 2022), Fyra yu Chan 1999 (Nov 17, 2022), subthresh15 (Nov 17, 2022), jekneutron21 (Nov 17, 2022), (Nov 17, 2022), pacan1 (Nov 17, 2022), Baelthar (Nov 17, 2022)
|
User 70749 () November 17, 2022, 2:50 am
|
November 17, 2022, 2:50 am by User 70749 ()
Amazing outputs, and this is only the beginning. While vanilla SD can do passable photographic realism, all too often the details such as the pregnancy bellybutton or other subtle things just don't appear, and if they do they don't seem to upscale well using img2img. Anything generated beyond 512px height starts to get real weird real quickly. These are already so much better than that.
I've also noticed that any model trained on actual photos seems to improve the probability of better hands.
|
Nope2468 (112)
November 17, 2022, 2:59 am
|
Posts: 58
Joined: Jan 2018
Reputation: 112
Liked by 19 members: Spongechu123 (Dec 23, 2023), preggolover91 (May 18, 2023), Bellylord123 (Feb 9, 2023), Njameson (Jan 24, 2023), Tcorker (Dec 8, 2022), Ikru88 (Dec 2, 2022), Eskar13 (Nov 21, 2022), (Nov 20, 2022), mr-enigma (Nov 18, 2022), greatpix78 (Nov 18, 2022), (Nov 17, 2022), JaxsonStark (Nov 17, 2022), peterwein (Nov 17, 2022), KodiUser (Nov 17, 2022), chops79 (Nov 17, 2022), Dolphins66 (Nov 17, 2022), Bred_anonymously (Nov 17, 2022), Fyra yu Chan 1999 (Nov 17, 2022), subthresh15 (Nov 17, 2022)
|
subthresh15 (777)
November 17, 2022, 8:24 am
|
Posts: 136
Joined: Aug 2018
Reputation: 777
November 17, 2022, 8:24 am by subthresh15 (777)
very interesting. how many images were in your training set? been thinking about doing my own model, but unsure of how much finessing it requires. was this done using dreambooth?
|
Nope2468 (112)
November 17, 2022, 3:04 pm
|
Posts: 58
Joined: Jan 2018
Reputation: 112
November 17, 2022, 3:04 pm by Nope2468 (112)
(November 17, 2022, 8:24 am)subthresh15 very interesting. how many images were in your training set? been thinking about doing my own model, but unsure of how much finessing it requires. was this done using dreambooth? This was done in the google collab with 53 images. I've moved to A1111 dreambooth UI now. 6000 steps for training. The main thing that takes finessing is nowhere which photos to choose as that can cause a lot of issues. I'm hoping to get a slightly more refined model today and then to train in on other concepts such as clothes. I also have a 3090 in my own setup so training this at home is an option versus the google collab which can be frustrating. Will probably be uploading more images soon after the current dataset trains
|
Nope2468 (112)
November 17, 2022, 5:15 pm
|
Posts: 58
Joined: Jan 2018
Reputation: 112
Liked by 13 members: Spongechu123 (Dec 23, 2023), preggolover91 (May 18, 2023), Bellylord123 (Feb 9, 2023), Tcorker (Dec 8, 2022), Ikru88 (Dec 2, 2022), (Nov 20, 2022), DeadmanSenji (Nov 19, 2022), mr-enigma (Nov 18, 2022), LeeVining (Nov 18, 2022), JaxsonStark (Nov 17, 2022), peterwein (Nov 17, 2022), KodiUser (Nov 17, 2022), chops79 (Nov 17, 2022)
|
thojm (131)
November 18, 2022, 7:05 pm
(Edited)
|
Posts: 32
Joined: Jun 2012
Reputation: 131
November 18, 2022, 7:05 pm by thojm (131)
(Edited)
Hey, I trained the hyper sized models if you have any questions about training feel free to ask. I've lost count of how many I've trained at this point.
Glad to see a more realistic model too. The default belies in SD were pretty disappointing, but I found it didn't take too much training to fix up the belly buttons. The fingers attached to the bellies are a much harder problem XD
My dataset is all CGI and Digital art, so it was difficult to keep prevent the model from drifting away from realism, but found that you can still get away with lots of synthetic data before it got too un-realistic hence the v1 and v1.1 models
Liked by BiBeBel (Apr 14, 2023), (Nov 20, 2022)
|
|
Related Threads |
Author |
Replies |
Views |
Last Post |
New hyperpreg SDXL model! |
ImpossibleBard |
0 |
1,677 |
February 29, 2024, 7:58 am
Last Post: ImpossibleBard
|
Hyper Preg trained model |
thojm |
68 |
59,854 |
October 27, 2023, 6:17 pm
Last Post: User 36834
|
I think I got my model where I want it to be |
bo27 |
150 |
94,875 |
September 4, 2023, 5:06 pm
Last Post: Bellylovr1998
|
AI Edit/ AI model request |
Unreg-36377 |
0 |
1,183 |
June 6, 2023, 8:32 pm
Last Post: Unreg-36377
|
Users browsing this thread: 1 Guest(s)
|
|