Before we start: Check out all versions of these LoRAs, each version is a different face.
Who is the girl??? She is No one. You might think she looks like someone you know but she is not.
There are a few things you should know before using these LoRAs.
1: DO NOT USE THEM FOR NSFW OR COMMERCIAL USE.
2: These LoRA files are small in size but if you use them properly they will work really great.
3: Best way to use these LoRAs is to mix them and get interesting results, like using multiple LoRAs in additional networks and giving them different strengths. Eg. No-one1:0.25, No-one2: 0.35 etc.
4: These work great with Hires.Fix if you are trying to get a medium or full body shot, otherwise it will come with disfigured eyes, nose etc.
5: While using close up or extreme close up, lower the upscale in Hires.Fix or it will distort face.
6: These are somewhat flexible LoRAs which work great between CFG 2-10, but you will have to play with sampling steps, sometimes lower steps give good results, sometimes higher steps give better results. In general if CFG is low then keep Steps around 30-90. If CFG is high then keep steps around 10-60.
7: Sometimes fingers and hands turn out weird, better to avoid them in Positive prompt and be sure to add them in negative prompt.
8: Model used for training LoRAs is Protogen 3.4, and for generating images I used MoistMix V1. It should work with most of SD 1.5 models.
I would really like to see what you make with these models.
Please feel free to Post your creations and suggestions.
I hope you enjoy using these as much as i do.
Description
Keep the lora strength between 0.8-0.95 for good results. And with this i will take a break from making loras for a while and learn a few new things. I will be back after gaining some new skills, meanwhile stay creative and take care.
FAQ
Comments (8)
Wow, this is like mega release. Some of newer ones look really awesome. I will rate them once I have checked them all.
How do you use them? am I crazy? I keep putting no-one(with number) but it sometimes works and sometimes doesnt. do I have to put the <Lora: bla bla bla> on the end like others? if so, what is it?
<Lora:No-one11:0.8> something like that. the last part is its weight that is 0.8 in this example. also include No-one11 in your prompt. Like No-one11, a woman wearing black jacket etc. You can also use lora extension on automatic1111 if you dont like typing <Lora: name: weight> part.
@Bolly_Diffusion They don't seem to be working. Tried doing 23, so I put no-one23, as well as <lora:no-one23:0.8> and it doesn't seem to work. Am I doing something wrong??
@confettibearr well there are many things which can go wrong, this works perfectly for me, tried it on 2pcs without any problem. If you are using additional network for lora then make sure it is enabled. Also i posted another image generated on realistic vision 2.0 checkpoint, you can copy the metadata and try it on PC and see if it can replicate the same. At time of posting this lora i wanted them to be semirealistic so i kept the lora weight fairly low and thats why you might see the generated images more influenced by checkpoint used.
no one 9, very nice, you good.
Thank you for your kind words, though these are very old loras, the method making them has changed a lot since that time, some of them are still usable, but with newer methods loras are more consistent and give better outcome.
You should do volume zipz, so like Volume 1 - Noone 1-15, Volume 2 - 16-30
Details
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.