My first Lora) I wanted to make it better, but it's really hard to find a good source images.
I recomend using weights somewhere between 0.6-1.
Tags
(!) FOR v5 if you can't make a good picture use this prompt:
(bent over:1.3), (bentover:1.3), (female on tiptoes:1.3), from side, full body, man behind woman, 1boy, standing sex, standing doggystyle, hetero
And add description of the scene and girl. It's working on every model I tried it to.
There are should be some differences when you'll use this words (you doesn't have to use it):
tiptoesFuck, from side, from front, from behind, bent, standing, penis
Also I recomend using:
sex, standing_doggystyle
And for the negatives:
Loli, dwarf, hug, 2girls, 2boys, threesome, yuri
There are lots of arm grab and hair pulling in the source images. But for some reason i couldn't been able to invoke them.
Versions differencies
v1 is generic version
v2 New verion, which is slightly better with limbs, charactrers bodies and position. (I haven't used upscale on the examples for this version)
v3 Just works better, but affects style much stronger. I don't know why, but it works bad in anything v4.5. You can use weight 0.8-1 for anything, and then use imgToimg for details. Worked out for me.
v4 Now it gives you more control but also it's much harder to trigger. HiresFix sometimes better. Sometimes not)
v5 Now it much more stable in depicting the pose itself, but not in every model. Realistic models are doable too. Also, I recomend using the prompt from sample images - works good.
I am done with that model, I think, I am happy with the results)
Enjoy)
You can try out this Lora online using Dazzle.ai
Feel free to ask any questions here in comments, or in my discord channel.
Also I am making games with AI arts. They will be free in the future, but if you want to participate in making or have an early access - you can support me on patreon)
Also my wet hair Lora was banned here, I dunno why. You can download the last version of it from my patreon for free.
Description
Retrained, less variebility, much more consistency
FAQ
Comments (16)
在我后来的测试中，我想办法让他稳定了下来，效果很不错了
可以做个从正面，男踮起脚操高个女吗？
@TABrobot Yeah, I think it's possible) I'll add this idea to my list of planned loras)
After adding the LORA, it makes the image extremally blurry, like an expressionism oil painting. This is the only variable I change in the prompt. What is going on?
@Infinitiv What model did you use? Are you using multiple Loras at the same time?
@aDDont Having the same issue. realvis, dreamshaper, and others all yield results as Infinitiv described
@ferut43 can you share the result? Here on my discord channel?
The pics always come out blurry as hell. It's a damn shame too since the pose works every time, it just looks like ass
What model do you use? Also have you tried updating the UI?
@aDDont mostly https://civitai.com/models/125189/epicdream
@Derpymoon have you tried lower the Lora weight? Also do you use any other Loras? They may affect too) I tried it, and on weight 0.5 it works decent)
Not working, makes some kinda vague artistic mess
Reducing the weight from <lora:TTF_6(v):1> to <lora:TTF_6(v):0.5> makes all the difference.
Would love something like this in Pony or XL!
Pony can do that without lora, just add "tiptoes" to the prompt)
Seems over trained, or not enough regularization, I cant lower weight to get any decent variation. Maybe it was my checkpoint.
Details
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.