|
--- |
|
library_name: diffusers |
|
pipeline_tag: text-to-image |
|
--- |
|
|
|
# LUSTIFY! [SDXL NSFW & SFW checkpoint] - v2.0 |
|
|
|
- **ID**: 573152 |
|
- **Author**: coyotte |
|
- **Type**: Checkpoint |
|
- **Base Model**: SDXL 1.0 |
|
- **Base Model Type**: Standard |
|
- **Model Version ID**: 708635 |
|
|
|
|
|
|
|
|
|
--- |
|
|
|
UPD 09\.08: V2 is out. |
|
What new: |
|
1\) I've trained the model for additional \~26 535 steps on a completely new set of pictures. |
|
2\) Better style variety, way better natural language prompt understanding, better prompt adherence, better SFW. |
|
3\) **BUT!** Hardcore scenes are now less consistent (you can still get them right, but it will take more rerolls). I wanted to fix that, but honestly I got too exhausted from working on V2\. Sorry guys, probably not the update you expected, but it's definitely the update the checkpoint needs. |
|
|
|
**LUSTIFY!** |
|
|
|
A photoreal checkpoint, capable of creating decent porn scenes without any loras (although, with just a little help of your favourite **NSFW** concept lora it can get even more consistent). But that's not the only use \- it can also create gorgeous **SFW** pics of objects/animals/fantasy creatures/you name it (you'll have to convince it tho \- the model is horny). |
|
|
|
"**LUSTIFY!**" understands both danbooru tags and natural language prompting, because it was trained like that. For V1 (not needed for V2\) I recomend putting "score\_9" tag into the begining of your prompt. Yes, the tag from the pony models. Yes, I am sure. |
|
|
|
A couple of things I need to make clear **before you download the checkpoint**: |
|
1\) All of my stuff is very opinionated. I create models mostly to suit my needs, my workflows, my prompting, etc. |
|
2\) Sometimes you can get bad hands and bad faces at distant shots. These are hard to fix with finetuning, but really easy with inpainting/adetailer. So, please, don't bother me with the complaints about this. Either adapt to the needs of this checkpoint, or use something else (spoiler, 99% of checkpoints suffer from that because of the limitations of this tech). |
|
3\) Everything I do is experimental, and I do a lot of dumb\-crazy stuff that in theory shouldn't work. So it's to be expected that *something,* what used to work with other checkpoint for you, might not work with this one. Let me know if there are such things, and I'd see if I can do something about it. |
|
|
|
**Recomended parameters:** |
|
Sampler: DPM\+\+ 2M SDE/DPM\+\+ 3M SDE, |
|
Scheduler: Exponential/Karras |
|
Steps: 30 |
|
Cfg: 4\-7\. |
|
Highres.fix: upscale by 1\.4\-1\.5, denoising \~0\.4 |
|
For the distant shots of people you probably wanna **use** highres.fix and/or adetailer. |
|
|
|
Also, use reasonable positive/negative prompts, shizo prompting does more harm than good (with any SDXL model). |
|
|
|
**FAQ:** |
|
1\. Q: Output is broken is Fooocus. A: Turn off "Fooocus Enhance" style. |
|
|
|
**Some tags that have a big visual impact with this model:** |
|
|
|
1. Camera type tags: "shot on Polaroid SX\-70", "shot on Kodak Funsaver", "shot on GoPro Hero", "shot on Canon EOS 5D", "shot on Leica T". |
|
2. Photography styles: "analog photo", "glamour photography", "street fashion photography". |
|
3. Lighting types: cinematic lighting, "neon lighting", "soft lighting", "dramatic lighting", "low key lighting", "bright flash photography", "warm golden hour lighting", "radiant god rays". |
|
4. Film types: "Ilford HP5 Plus", "Lomochrome color film", "Fujicolor Pro". |
|
5. Photographers: Alessio Albi, Martin Schoeller, Miles Aldridge, Oleg Oprisco, Tim Walker. |
|
6. Others: "bokeh", "dreamy haze", "technicolor", "underexposed". |
|
|
|
Alternatively, you can give a read to [this](https://civitai.com/models/118213/creating-photorealistic-images-with-ai-using-stable-diffusion) wonderful prompting guide by [PromptGeek](https://civitai.com/user/PromptGeek). It has A LOT of useful tips I didn't know about even after 2 years of using SD. |
|
|
|
**Work In progress:** |
|
Initially it started out as a mix of my personal unreleased SDXL finetune with such wonderful checkpoints as [bigASP](https://civitai.com/models/502468?modelVersionId=558487) and [Pyro's NSFW](https://civitai.com/models/133808?modelVersionId=324958). Then I've finetuned this mix on a curated dataset of 1000 pics for aesthetic tweak. |
|
The recipe was something like: 0\.55\*(my unreleased SDXL finetune)\+0\.45\*(0\.5\*(bigASP)\+0\.5\*(Pyro's NSFW)). |
|
For V2 I've merged V1 with [NatVis](https://civitai.com/models/617652?modelVersionId=690475) (20%) and then trained on new 1700 pics for additional 26 535 steps. |
|
|
|
|
|
|
|
|
|
--- |
|
|
|
1\) I've trained the model for additional \~26 535 steps on a completely new set of pictures. |
|
2\) Better style variety, way better natural language prompt understanding, better prompt adherence, better SFW. |
|
3\) **BUT!** Hardcore scenes are now less consistent (you can still get them right, but it will take more rerolls). I wanted to fix that, but honestly I got too exhausted from working on V2\. Sorry guys, probably not the update you expected, but it's definitely the update the checkpoint needs. |
|
|
|
|
|
|
|
--- |
|
|
|
*Content copied from Civitai: [LUSTIFY! [SDXL NSFW & SFW checkpoint]](https://civitai.com/models/573152) on 2024-08-09 17:51:49.124523+00:00* |
|
|
