UPD 23.07: v5.0 (Illustrious) is OUT!
1) I've fixed what was wrong with v4.0 - the faces are now better on the distant shots even without ADetailer/FaceDetailer. The model will also no longer force the details where they aren't needed.
2) I've done additional training on a diverse dataset for A LONG time. Like, so long it turned out much more costly than I would've prefered...
3) THAT ONE pony/illustrious face is anihilated. Seriously, I'm about to throw up every time I see that "(gigachad chin, huge eyed, sweaty skin:10)" abomination on 90% of realistic illustrious merges/finetunes. This needed to be stoped, so I did it.

If you want to support me or help me cover the costs:
https://boosty.to/coyotte/donate or Bitcoin 1BiNMKwVADy68rUrRxCR3mr3TGewWvrtUV.
Every donation will go towards developing chekpoints, workflows and loras (this stuff is costly). I have big plans, but little means to fulfill them 💀

YOU ARE NOT ALLOWED TO USE THIS MODEL AS A PART OF YOUR MERGE, UNLESS YOU CREDIT ME IN THE DESCRIPTION.

Important prompt structure for Illustrious-based version.
Rule #1: More tags ≠ Better output.
Rule #2: If your prompt causes physical nausea to read - fix it.
Rule #3: DON'T use Pony loras on Illustrious

Positive prompt:
✅ Try: masterpiece, best quality, realistic, [your subject, actions, clothing, etc].
❌ Avoid: 3 paragraphs of random junk you saw in Discord

Negative prompt:
✅ Try: bad quality, worst quality, low quality, [something very specific to the prompt you're working on right now]
❌ Avoid: dozens of redundant anatomy tags like "missing limbs, bad eyes, floating limbs, etc", negative embeddings made for specific checkpoints

Pony's quality tags like "score_9, score_8_up, score_7_up" AREN'T doing anything on it.
If you choose to ignore the guide and are getting trash results - please also ignore the "rate" button.

My simple yet organized workflow I've used for creating the preview samples: https://files.catbox.moe/147f5i.json

RECOMENDED PARAMETERS FOR BEST RESULTS:
◦ Sampler: DPM++ 2M SDE / DPM++ 3M SDE / DPM++ SDE
◦ 30-40 Steps.
◦ CFG: 3-6 (low for more realism, high for more stylization)
◦ The model was on trained mostly on 1024x1024, 832x1216, 1216x832, 896x1152, 1152x896 resolutions, so it could help the quality if you used these (although that's not necessary - it behaves nicely on other aspect ratios as well).
◦ Highres fix: Upscale by 1.35-1.5, denoising strength ~0.4, upscaler - 4x NMKD Superscale or Siax.
For the distant shots of people you probably wanna use highres fix/upscaling and/or adetailer.

PARAMETERS FOR WORST POSSIBLE RESULTS:
◦ Sampler: Euler A
◦ 15 Steps.
◦ CFG: 11
◦ 512x768 resolution or whatever.
◦ No highres.fix/upscaling, no FaceDetailer/ADetailer