Downloads · 30 days
0
nai-lora-heavy-line
v2ray/nai-lora-heavy-line
nai-lora-heavy-line is a text-to-image model from v2ray. Use it when you need an image from a text prompt. It is set up for peft. The card lists the license as mit.
This LoRA is trained for 2 models, heavy-line.safetensors for v1.1 version of NoobAI XL, and heavy-line-mmh.safetensors for Vpred 1.1 version of MiaoMiao Harem.
Access
Public
Updated Sep 1, 2025
Repo size
395 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors394 MB · 100%
At a glance
- Task
- Text-to-Image
- Library
- peft
- License
- mit
- Access
- Public
- Created
- Aug 31, 2025
- Updated
- Sep 1, 2025
- SHA
- c9fbdc44
Base models
Model card
From the Hugging Face model README
NoobAI XL LoRA Heavy Line
This LoRA is trained for 2 models, heavy-line.safetensors for v1.1 version of NoobAI XL, and heavy-line-mmh.safetensors for Vpred 1.1 version of MiaoMiao Harem.
The dataset used to train this LoRA is scraped using LagPixelLOL/aisp, containing a total of 578 images, a total of 3 artists are used.
Big thanks to the artists for the very cute styles :3.
To use this LoRA, you can go without a trigger word, which will use all 3 artists' style together, or you can choose to specify which artist's style with a trigger word, note this model is mostly a foot model.
pixiv @くろやくそく: hei yksk
pixiv @leonzo030: leonzo
pixiv @フリザ: efreezerarts
This LoRA is trained using kohya-ss/sd-scripts, with rank 32, alpha 16, learning rate 1e-4, for 192 epochs with a total of 5184 steps, using a B200, took approximately 6 hours.
If you have any questions, suggestions, or just want to talk to me, you can add me on Discord with ID @v2ray.
Examples
- Task
- Text-to-Image
- Library
- peft
- License
- mit
- Languages
- en
- Created
- Aug 31, 2025
- Updated
- Sep 1, 2025