This is it. The one you've been waiting for. We've retrained SDXL with 1.3M professional and amateur pornographic images. This model does softcore, hardcore, and everything in-between.
The model seems to do best with resolutions 832x1216 or 1216x832. My settings:
Sampler: dpmpp_2m_sde
Scheduler: Karras
Steps: 30
CFG: 7
The model isn't perfect. You'll get some strange anatomy at times. Experimentation says this is the result of TE2, which was likely trained without much NSFW content. Still, you can get great results with a bit of cherry-picking.
Recipe:
In each step, TE weights were frozen - this model modifies only the unet. Machine captioned images were used until the last step.
Retrained SDXL 1.0 on 1.3M images for eight epochs
bs=80, lr=1e-05, optimizer=AdamW8Bit, EMA=0.95
Finetuned on 50k images for ten epochs to help do some rebalancing
bs=80, lr=2e-06, optimizer=AdamW8Bit, EMA=0.95
Aesthetic training on 30k images for 14 epochs
bs=1, lr=1e-05, optimizer=Adafactor, no EMA
Final alignment using 600 hand-selected and captioned images
bs=1, lr=1e-05, optimizer=Adafactor, EMA=0.95
Feel free to make your own merges and finetunes based on this checkpoint for non-commercial purposes. I ask that, if you do, you include a recipe with a similar level of detail as what I provided above. There's too much secrecy around this topic.
I have made checkpoints from step 2 & 3 in the recipe above available. These are not recommended for general use - they do not make good images out of the box. They may be useful for model mergers and finetuners.
Description
This is the version that corresponds to step 3 in the recipe. It does not have the final alignment and is not recommended for most users. It's available here for model mergers and trainers in case they want to do their own refining.