sample	sample
threadguy, This is a photograph of a young threadguy taking a selfie in a modern, minimal…	threadguy, This is a photograph of a young threadguy standing in a modern, well-lit room,…
sample	sample
:---:	:---:
threadguy, The image is a photograph featuring a young threadguy standing in an indoor se…	threadguy, The image is a photograph featuring a young threadguy with a distinct, somewha…

Usage (Diffusers)

python

import torch
from diffusers import Flux2Pipeline

pipe = Flux2Pipeline.from_pretrained(
    "black-forest-labs/FLUX.2-klein-4B", torch_dtype=torch.bfloat16
).to("cuda")
pipe.load_lora_weights("noema-art/threadguyflux-klein")
image = pipe("threadguy, a character portrait", guidance_scale=4.0, num_inference_steps=25).images[0]
image.save("out.png")

Recommended Settings

LoRA strength	Guidance	Steps	Resolution
0.8–1.0	4.0	25	1024×1024

Training Details

Base: black-forest-labs/FLUX.2-klein-base-4B
Steps: 4000 · Network: LoRA rank 32 / alpha 32
Optimizer: adamw8bit, lr 1e-4 · Scheduler: flowmatch
Resolution: 512, 768, 1024 (multi-res bucketed) · Precision: bf16 train / fp16 save

Reproduction

This repo includes the full dataset/ (20 image-caption pairs) and the exact config.yaml so the LoRA can be retrained as-is.

About

NOEMA is a privacy-by-construction generative studio. Run this model — and the rest of the catalogue — privately at noema.art: no email to start, pay anonymously, go fully private anytime.

_{NOEMA · a complete studio, completely private · noema.art}