My first attempt at creating an action LoRA — it’s still difficult to train LoRAs for Z-Image Turbo, but the tests are promising. The big issue is that the size of the member is sometimes disproportionate, and you need to make several generations to get a realistic result. It doesn’t work well if you add other LoRAs.
It doesn’t have a trigger word as such, it just uses a prompt like: pov photo of a girl with curly hair, green eyes, wearing a white bride dress, doing a blowjob, she is sucking a penis, grab the penis with her hand. cinematic light from a window.
To generate these examples I used Euler with beta57 — it seems to give better results than other combinations.
Description
FAQ
Comments (2)
Might be helpful to give people more information - trigger words, strength, and include examples with prompts used. I'm using this at 1 strength alongside a character lora, and the results are less than impressive - deformed cocks and not in the mouth, as per all your examples.
If you actually read the text, there’s an example prompt to start from, It also says it does NOT have a trigger word. I also mention that it’s not compatible with other LoRAs (liker other Z image Turbo LoRAs yet). Strength 1 is basic, and I also recommend using Euler with beta57. My samples are exactly as they come out with that workflow.