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
We're getting really close to my ideal version of Chaos. The basic generations (without positive prompts) are amazing, and the model is still very obedient and (to me) balanced. I recommend low to no quality tags.
FAQ
Comments (5)
imho v11 is the most successful overall, and in terms of its maximum and detailed environment. The only thing I'd like to know is what methods (besides tags) can be used to soften the specific facial style. For example, using methods similar to the block weakening methods in the LBW node, strengthening the values of the blocks that influence the shape of the face, but setting negative weights for the connected LoRA itself.
Fuck man, I have no clue. I think you'd have to modify the model and then save that as a new checkpoint, but how to modify it precisely I'm not sure.
@_Kav_ For some reason v14.0 breaks clothing and has misalignments and such compared to v13.0, eg. side slit is much better in v13.0, v13.0 generations are more 'blended', you can create more natural cinematic scene without the character standing out.
However v14.0 has better prompt understanding in some aspect
@Lyralei It's a never-ending whack-a-mole game, you improve something, something else breaks.
@_Kav_ Exactly. Cannot pour more than it can hold. This is why the first versions are often better than the later ones, but this is not the case for this model.