---
license: apache-2.0
base_model: black-forest-labs/FLUX.2-klein-base-4B
base_model_relation: adapter
pipeline_tag: text-to-image
tags: [text-to-image, lora, diffusers, flux2, klein, flowmatch, noema]
instance_prompt: "threadguy"
training_steps: 4000
network_type: lora
library_name: ai-toolkit
widget:
- text: "threadguy, This is a photograph of a young threadguy taking a selfie in a modern, minimalist bedroom. Threadguy stands…"
  output:
    url: samples/sample_000.jpg
- text: "threadguy, This is a photograph of a young threadguy standing in a modern, well-lit room, taking a selfie in front of a…"
  output:
    url: samples/sample_001.jpg
- text: "threadguy, The image is a photograph featuring a young threadguy standing in an indoor setting, likely a room or studio…"
  output:
    url: samples/sample_002.jpg
- text: "threadguy, The image is a photograph featuring a young threadguy with a distinct, somewhat disheveled hairstyle. His ha…"
  output:
    url: samples/sample_003.jpg
---

<p align="center"><a href="https://noema.art"><img src="https://huggingface.co/noema-art/noema-brand/resolve/main/noema-banner.png" alt="NOEMA — run this model privately at noema.art" width="100%"></a></p>

# threadguyflux-klein

> **NOEMA** — privacy-by-construction generative studio.  
> Run this model privately at **[noema.art](https://noema.art)** · no email · pay anonymously.

FLUX.2 [klein] 4B conversion of ms2stationthis/threadguyflux (originally FLUX.1-dev). Trigger: "threadguy".

**Trigger word:** `threadguy`
_Retrained onto FLUX.2 [klein] 4B from [ms2stationthis/threadguyflux](https://huggingface.co/ms2stationthis/threadguyflux) (FLUX.1-dev)._

## Sample Outputs

| ![sample](samples/sample_000.jpg) | ![sample](samples/sample_001.jpg) |
|:---:|:---:|
| *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](samples/sample_002.jpg) | ![sample](samples/sample_003.jpg) |
|:---:|:---:|
| *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](https://noema.art)**: no email to start, pay anonymously, go fully private anytime.

<sub>NOEMA · a complete studio, completely private · <a href="https://noema.art">noema.art</a></sub>