This model is only great at profiles and half shots. Still a WIP and I plan on upgrading it to do body shots and distance shots more accurately.

The model can still do some full body generations as the sample images show, it just takes a bit more work and a decent understanding of the UI you are using.

Another LoRA for Pony XL!
Liking the model and sharing your generations is much appreciated :)

My models are not perfect by any means, but with the right workflow and prompting you can get some really great results.

All models I make in the future will likely be male.
Feel free to message me with any questions or potential requests.

LoRA was trained on Pony. Prompting is just like any other, with the triggers:
"1boy, Shinra Kusakabe, black hair, red eyes," I recommend all four.
"male, male child, sharp teeth, foot focus, fire at the soles of feet, fire" are also good to use.

I find that AutismMix gives the most consistent results, feel free to use any Pony model and share your results!
Recommended weight is 0.5-0.8, but as the sample pictures show you can adjust as needed for the model you are using.
The images generated were made with multiple parameters and a latent upscale, some of which include:
Cfg: 5.0 - 8.0
Steps: 25
Sampler(s): spmpp_3m_sde, EulerA,
Scheduler: Karras
Denoise: 1.00
Lora weight(s): 0.50-0.95

Happy generating!