Views
No views yet
NOEMA · part of thekleinfamily — character & style LoRAs on FLUX.2 klein (4B).
Run it privately at noema.art — no email, pay anonymously.
lain
Retrained onto FLUX.2 [klein] 4B from ms2stationthis/lainflux (FLUX.1-dev). |  |
|---|---|
| lain, This is a digitally rendered image featuring a small, anime-style girl, referred to… | lain, This is a digital artwork depicting a young lain with a pale skin tone and short, d… |
 |  |
| :---: | :---: |
| lain, This is a digital anime-style illustration depicting a young girl, lain, with a fai… | lain, This image is a digital drawing in a stylized anime art style. It features the youn… |
1import torch
2from diffusers import Flux2Pipeline
3
4pipe = Flux2Pipeline.from_pretrained(
5 "black-forest-labs/FLUX.2-klein-4B", torch_dtype=torch.bfloat16
6).to("cuda")
7pipe.load_lora_weights("ms2stationthis/lainflux-klein")
8image = pipe("lain, a character portrait", guidance_scale=4.0, num_inference_steps=25).images[0]
9image.save("out.png")| LoRA strength | Guidance | Steps | Resolution |
|---|---|---|---|
| 0.8–1.0 | 4.0 | 25 | 1024×1024 |
dataset/ (20 image-caption pairs) and the exact config.yaml so the LoRA can be retrained as-is.