After some experimentation with merging different models together, I've got a decent result on a few. The idea for these checkpoint merges was to work good with the Loras I've trained and was going to train.
The first one I've published is The Kiwi ? - more anime-like, more like a drawing.
This one is the second and it's The Kapina - more realistic and closer to a render.
The merge should output good results for both characters and landscapes. The style is semi-realistic. As with all AI art creation, and different models, my advise is to Experiment. Try out different settings (CFGs, sampling steps, etc.), see what works for you and for your purposes. Looking for too many specifics and details limits your options, and you never know what you might miss. Sure you might miss something horrendous, but that would just mean you've missed a good laugh.
Useful tools for any model:
If you (more like your GPU) are struggling with upscaling with Hires. fix, as an alternative I can recommend Ultimate SD upscale.
ADetailer. It should be used if you want a character's face to be detailed and not funky-looking. It could also be used to add a certain face to a character (by placing the Lora of said face in the ADetailer's prompt).
For good hands maybe pray to the Asgardian Pantheon, or to Cthulhu, I can't help you there. Sorry ?
描述:
训练词语:
名称: pulenkompotKapina_v10.safetensors
大小 (KB): 2246054
类型: Model
Pickle 扫描结果: Success
Pickle 扫描信息: No Pickle imports
病毒扫描结果: Success
