I am admittedly kind of a noob at this, but if you enjoy my humble work, any donations are greatly appreciated: https://ko-fi.com/insult_to_ninjary
Your generosity helps me stay motivated to keep improving and to keep trying new things!
At a Glance:
Style: Semi-real with a hint of anime
Works with LoRAs?: Maybe? (but not super well from my testing)
Use a VAE?: Yes! (it makes a HUGE difference)
Clip skip: 1 or 2 (experiment with both!)
Hires. fix: use non-default upscaler; denoising strength 0.5 - 0.4
Version 2 Description:
This is a re-merge of Version 1 with the LoRA merged in at a bit lower weight. This was done in an attempt to improve the stability of the model.
On the plus side, I do think the stability has improved a little bit. You'll get slightly fewer total abominations with v2.
On the minus side, being more stable than v1 is such a low bar. Essentially, v2, while improved, is still not a great model. It's better, but still might not be worth working with unless you're very patient. It also lost a little bit of style strength in exchange for the slightly improved stability.
As it stands, I don't consider v2 a direct replacement for v1.
If you want a stronger style, and don't mind having to deal with some instability in the model, use v1.
If you think the showcase images of v2 look good enough, and you just want a model that's a little easier to work with (but still don't mind having to be patient and do some fixing), use v2.
Another possibility is to just use the Real1 LoRA. This can be used with the base model of your choosing, and at the weight of your choosing, so in theory, it gives you a lot more flexibility and control. In practice, it's not as useful as it sounds, as the LoRA doesn't really have a strong effect unless it's used with certain base models (specifically ChilloutMix or checkpoints with a similar aesthetic).
For more potentially relevant information, see the original v1 description below.
Version 1 Description:
This is my second published checkpoint merge, but I made it at the same time as my first. It's just a simple merge of my Real1 LoRA and the Chilloutmix base model, which was one of the best base models to use with the LoRA. I made this merge partly because I wanted to be able to use my Real1 model as a base model, and partly just to practice merging a LoRA into a checkpoint, which I had never done before.
In the end, I don't think this checkpoint is very useful, unless you really like the style and you're willing to put up with the issues it has. In general, you're probably better off just using the Real1 LoRA because A) you can choose your base model for better flexibility, and B) you can adjust the LoRA weight if you're getting bad outputs. By using this checkpoint version, you're essentially stuck using the LoRA with Chilloutmix at a LoRA weight of 1.
Other than that, this checkpoint suffers from a lot of the same problems that the LoRA version does, namely bad anatomy (especially hands and fingers). For other issues, see below.
Troubleshooting:
Most importantly, to correct poor image output that is consistent, make sure you are using a VAE. I don't 100% remember, but I'm pretty sure I did not bake a VAE into the checkpoint, so you'll have to manually use one, and it can make a HUGE difference in quality! (colors, anatomy, etc.)
From my testing, this checkpoint doesn't work great with LoRAs. You can see that the LoRAs are having an effect, but usually they further degrade the already shaky coherence of the base model. So feel free to try, but it might get frustrating!
In general, the biggest issue you're going to come across is problems with anatomy - hands, fingers, etc. Just try your best with all the usual fixes - different prompting, use a VAE, try different clip skip values, use adetailer, inpaint, etc.
For some reason, this model is pretty horny, lol. I didn't intend for it to be like that, but it just kind of happened somehow! Anyway, if nsfw is not your bag, it should hopefully be easy enough to prompt away from it.
Outro:
If you make anything awesome, please consider posting them to the gallery! That goes for all of my models! I really like seeing what kind of stuff you all are able to make!
If you have any questions, feel free to ask! I will try my best to help! Also, if you have any ideas for future models, please don't hesitate to share them with me!