nai-lora-iewa
Back

nai-lora-iewa
0 0 1

Manga

Illustration

2D

nai-lora-iewa

This is a LoRA for the v1.1 version of the NoobAI XL model.

The dataset used to train this LoRA is scraped using LagPixelLOL/aisp, containing a total of 46 images.

Big thanks to the artist for the very cute style :3, you can find the artist on X (Twitter) with ID @iewaaaaaa.

To use this LoRA, you can use the trigger word iewa.

This LoRA is trained using kohya-ss/sd-scripts, with rank 32, alpha 16, learning rate 1e-4, for 512 epochs with a total of 5120 steps, using a H100, took approximately 3 hours.

If you have any questions, suggestions, or just want to talk to me, you can add me on Discord with ID @v2ray.

This model is sourced from an external transfer (transfer address: https://civitai.com/models/1288179/noobai-xl-lora-iewa ）,if the original author has objections to this transfer, you can click，
Appeal
We will, within 24 hours, edit, delete, or transfer the model to the original author according to the original author's request

Lyra Y.

Lyra Y.

Manga

Illustration

2D

Model Information

Original author：
v2ray
Model Type：
LoRA
Basic Model：
SDXL 1.0
Trigger Words：
iewa

This is a LoRA for the v1.1 version of the NoobAI XL model.

The dataset used to train this LoRA is scraped using LagPixelLOL/aisp, containing a total of 46 images.

Big thanks to the artist for the very cute style :3, you can find the artist on X (Twitter) with ID @iewaaaaaa.

To use this LoRA, you can use the trigger word iewa.

This LoRA is trained using kohya-ss/sd-scripts, with rank 32, alpha 16, learning rate 1e-4, for 512 epochs with a total of 5120 steps, using a H100, took approximately 3 hours.

If you have any questions, suggestions, or just want to talk to me, you can add me on Discord with ID @v2ray.

This model is sourced from an external transfer (transfer address: https://civitai.com/models/1288179/noobai-xl-lora-iewa ）,if the original author has objections to this transfer, you can click，
Appeal
We will, within 24 hours, edit, delete, or transfer the model to the original author according to the original author's request