Type | |
Stats | 395 11,882 3.4k |
Reviews | (57) |
Published | Mar 25, 2024 |
Base Model | |
Usage Tips | Clip Skip: 2 |
Trigger Words | sosukeponyo 1 boy, male child, black hair, yellow shirt solo focus, cliff side, ocean, barefoot, black eyes |
Hash | AutoV2 A8CD2F10B9 |
After seeing "The Boy and the Heron" I had to make a Ghibli model. Ponyo is one of my favorites, so here's Sosuke!
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:
"1 boy, male child, soskueponyo, black hair, yellow shirt".
If you're trying to recreate the exact character from the movie, I recommend all of them; otherwise adjust as needed.
Additional optional tags:
"solo focus, cliff side, ocean, barefoot, black eyes"
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. I've also noticed that this model performs well with low weight, depending on what you're trying to achieve.
The images generated were made with the following parameters and a latent upscale:
Cfg: 5.0 - 8.0
Steps: 25
Sampler(s): EulerA,
Scheduler: Karras
Denoise: 1.00
Lora weight(s): 0.50-0.95
Happy generating!