Studio Ghibli
LORA
HiDream
LORA
HiDream
v2.0

Studio Ghibli

tarn59
Creator
⭐ 0.0
⬇ 486 Downloads
👁 1 Views
🖼 22 Images

Trained Words

Studio Ghibli style.

About this model

Used 's Ghibli dataset. 120 images, batch size 4, 100 epochs, 3000 steps. Learning rate: 1e-5. 13 hours running on 2 x rtx 5000 ada gpus. I used diffusion-pipeline since it allows distributing loads across multiple gpu's.

*Update V2.0 I doubled the lr rate to 2e-5 to make a more potent LORA.

Image2Image guidance: If you want to do img2img, I recommend setting sampler = lcm and scheduler = linear_quadratic. The denoise will be between .3 - .4 and steps around 5-10. Will need to adjust on a case by case basis.

Related Models

Similar AI models you may like