Edit for 4.0
More realistic, less bright and saturated though. Still very creative. Not necessarily better than the previous versions, but it offers something different.
Edit for V3.5
After several rounds of internal merges, tuning, clip editing, many almost V3 versions, I've ended up further than I thought with what I call version 3.5. It's a general upgrade that fixes many of the issues of the previous V2 and V1 model, and so far I'm not sure what are its flaws. It's real fun to play with, the model is very creative, you often have to get out of its way and let it do its thing, although it will follow prompts closely.
Quite good at low inference steps.
Minimal prompting, minimal lora use seem to work best.
Please share your creations! I love to see them.
Edit for V2:
V2 is an overall, upgrade. It's more balanced, bolder, more detailed. Subjectively, it's better than V1, but you might think differently and that's legitimate.
Original post (V1):
This is an NSFW-focused model based on ten rounds of merges. I'd love to give credits, but at this point I've forgotten the contributors, sorry.
It'll do SFW, but it'll occasionally generate sexually explicit material on its own, even without a prompt.
The goal with this model was creating an Illustrious variant which would make great semi-realistic demi-humans, without a complex prompt, without a complex Lora stack, just the model, and you're good to go.
I'm personally pleased with the results, but more than anything, I'm curious about what people think, and how they'll merge it to make something new. If you do use this model for merges, let me know so I can see what you're up to. Just out of curiosity.
All the examples images I selected were created with relatively simple prompts, no loras, and in a few second per image. No complex workflows here. I'm 100% sure people will know how to have better results than me with it.
One last thing, the model is aimed for and biased to generating mature/adult characters. I cannot advise you strongly enough to not generate minor characters. Don't do anything illegal or amoral with it.
Description
V11 is a bit more realistic, with less failed generations. It follows prompt well but carries bias you may have to fight. It's ability to do realism is quite impressive, sometimes uncanny.
Making a better version than V10 has been difficult, this one stacks well against it, but I wouldn't say it's better. Just different.
FAQ
Comments (10)
V11 only produces a black screen for me?
Strange. I made this version like all the others... maybe the file was corrupted somehow? Or you could try a very minimal setup?
May i ask how do u merge?
ComfyUI built in nodes, modelmergesimple, loras, then saving the checkpoint.
The new v11.0 and v10.0 models don't seem to play well with ControlNet. They tend to cause some anatomical issues and are nowhere near as stable as v9. On the flip side, the hair/fur texture in 11 and 10 is a massive upgrade. But at the same time, the outputs look way more repetitive/homogenized now. It's such a tough trade-off...
Mmh. I don't use ControlNet so I don't tend to test that when making my merges. As you said though, there are always trade-offs made and a strictly better model is getting harder and harder to make.
@_Kav_ Bro, I have an idea. Since the recent 'versions' (like v9 to v11) feel more like distinct tuning styles rather than direct upgrades, how about changing the naming scheme? Maybe give them more 'parallel' names to show they just represent different stylistic directions? For example: Sapphire, Emerald, Opal, etc. Just my two cents as a layman, no offense intended at all!
@936402397721 None taken. I feel like the goal is still the same as the original project, but if I think I'm changing too much compared to the previous versions, It might be an interesting idea to change the naming scheme.