---
license: cc-by-nc-4.0
base_model: black-forest-labs/FLUX.1-Kontext-dev
library_name: diffusers
pipeline_tag: image-to-image
tags:
  - flux
  - flux-kontext
  - lora
  - thermal
  - face-recognition
  - biometrics
  - image-to-image
  - rgb-to-thermal
  - synthetic-data
extra_gated_heading: "Request access to the PUCV thermal FR LoRA weights"
extra_gated_description: "Access is granted automatically once the form is
  submitted. Your name and email are shared with the authors and access can
  be revoked at any time."
extra_gated_prompt: "These LoRA weights are released for academic and
  non-commercial research on data scarcity in thermal-face biometrics ONLY.
  They are a Derivative of FLUX.1 Kontext [dev] and are therefore also subject
  to the FLUX.1 [dev] Non-Commercial License and its Acceptable Use Policy
  (https://huggingface.co/black-forest-labs/FLUX.1-Kontext-dev). By requesting
  access you agree not to use these weights to impersonate any individual
  outside the enrolled cohort, to fabricate biometric samples, or for any
  unlawful, defamatory, or abusive purpose."
extra_gated_fields:
  Full name: text
  Affiliation / Institution: text
  Country: country
  Intended use:
    type: select
    options:
      - Academic research
      - Education
      - label: Other
        value: other
  I will use these weights for non-commercial research purposes only: checkbox
  I will not use them to impersonate individuals or to fabricate biometric samples: checkbox
  I agree to the upstream FLUX Kontext dev Non-Commercial License and Acceptable Use Policy: checkbox
extra_gated_button_content: "Acknowledge terms and request access"
---

<div align="center">

# 🔥 Thermal Face LoRA — FLUX.1 Kontext (I2I)

**Visible → Thermal (RGB-to-TIR) facial translation that preserves subject identity**

[![License: CC BY-NC 4.0](https://img.shields.io/badge/License-CC%20BY--NC%204.0-lightgrey.svg)](https://creativecommons.org/licenses/by-nc/4.0/)
[![Base model](https://img.shields.io/badge/base-FLUX.1--Kontext--dev-blue)](https://huggingface.co/black-forest-labs/FLUX.1-Kontext-dev)
[![Code](https://img.shields.io/badge/code-GitHub-black?logo=github)](https://github.com/GbrlOl/thermal-fr-lora)
[![Gated](https://img.shields.io/badge/access-gated%20(research%20only)-orange)](#-license--intended-use)

</div>

---

A LoRA adapter that specializes **FLUX.1 Kontext [dev]** for **visible-to-thermal
facial translation** under an explicit image-to-image (I2I) scheme. A real visible
face acts as the structural and identity anchor while a fixed text prompt steers the
thermal appearance — so the generated thermal face keeps the subject's identity
instead of merely looking realistic.

These weights were used to generate **PUCV-TER-S**, a synthetic thermal face dataset,
and accompany the code released at 👉 **[github.com/GbrlOl/thermal-fr-lora](https://github.com/GbrlOl/thermal-fr-lora)**.

> ⚠️ **Gated, non-commercial research release.** These weights are a **Derivative of
> FLUX.1 Kontext [dev]**; the upstream **FLUX.1 [dev] Non-Commercial License** and its
> Acceptable Use Policy apply in addition to the `cc-by-nc-4.0` label on this repo.
> See [License & intended use](#-license--intended-use).

## 📦 Model summary

| | |
|---|---|
| **Type** | LoRA adapter for FLUX.1 Kontext [dev] |
| **Task** | Image-to-image, visible → thermal (RGB-to-TIR) facial translation |
| **Base model** | [`black-forest-labs/FLUX.1-Kontext-dev`](https://huggingface.co/black-forest-labs/FLUX.1-Kontext-dev) |
| **Backbone** | Multimodal diffusion transformer (flow matching) |
| **Adapter target** | All linear projections (attention + feed-forward) of the double-stream and single-stream blocks |
| **LoRA rank / alpha** | r = 128 / α = 128 |
| **Training pairs** | 50 synchronized visible–thermal pairs (PUCV-VTF) |
| **Weights file** | `Flux_ter_50_redo_seed42.safetensors` (≈1.37 GB, bf16) |

## 🎯 Intended use

- Generating **synthetic thermal face datasets** from consented visible-face images,
  for research on data scarcity in thermal-face recognition.
- Studying **synthetic-to-real transfer** and **cross-sensor** robustness in thermal
  biometrics.

**Out of scope / prohibited:** any commercial or production use; generating thermal
representations of individuals without consent; impersonation; fabrication of biometric
samples; any unlawful, defamatory, or abusive use.

## 🚀 How to use

You must be authenticated on the Hugging Face Hub and have accepted the terms of **both**
this repository **and** the base model
[`black-forest-labs/FLUX.1-Kontext-dev`](https://huggingface.co/black-forest-labs/FLUX.1-Kontext-dev)
(which is itself gated).

```bash
huggingface-cli login
pip install -U diffusers transformers accelerate peft safetensors facenet-pytorch
```

```python
import torch
from diffusers import FluxKontextPipeline
from diffusers.utils import load_image

# 1) Base FLUX.1 Kontext model
pipe = FluxKontextPipeline.from_pretrained(
    "black-forest-labs/FLUX.1-Kontext-dev",
    torch_dtype=torch.bfloat16,
).to("cuda")

# 2) Attach this LoRA adapter
pipe.load_lora_weights(
    "GbrlOl/thermal-fr-lora",
    weight_name="Flux_ter_50_redo_seed42.safetensors",
)

# 3) Preprocessed visible face (MTCNN-cropped, 512x512) as the I2I condition
visible = load_image("visible_face_512.png")

prompt = (
    "convert this image to a high-contrast thermal (8-12 µm) infrared view, "
    "monochrome grayscale, black background, preserve face structure, "
    "no visible-spectrum colours"
)

# Deterministic generation settings used to build PUCV-TER-S
thermal = pipe(
    image=visible,
    prompt=prompt,
    guidance_scale=4.0,
    num_inference_steps=20,
    generator=torch.Generator("cuda").manual_seed(42),
).images[0]

thermal.save("thermal_face.png")
```

### Input preprocessing

For results consistent with the paper, preprocess visible images as in training: detect
the face with **MTCNN** (first / highest-confidence detection, 10-pixel margin), crop, and
resize to **512×512**. The prompt above is fixed and was used for all generations. The full
generation and evaluation pipeline is on
[GitHub](https://github.com/GbrlOl/thermal-fr-lora).

## 🧪 Training details

- **Base model:** FLUX.1 Kontext [dev] (flow-matching, I2I conditioning).
- **Adaptation:** LoRA (rank 128, α 128) on all attention and feed-forward linear
  projections of the double-stream and single-stream blocks; base weights frozen.
- **Optimization:** learning rate 1e-4, batch size 1, 3000 steps, single fixed prompt, seed 42.
- **Data:** 50 synchronized visible–thermal pairs from PUCV-VTF; thermal captured with a
  FLIR Tau 2 640 (LWIR, 14-bit), contrast-normalized to 8-bit via per-image min–max scaling.
- **Hardware:** 2× NVIDIA H100 (80 GB).

## 📊 Evaluation (summary)

Synthetic thermal faces from this adapter preserve subject identity at **99.87% rank-1**
(d′ = 13.6) against real-thermal templates, versus 11.4% (Pix2Pix) and 3.5% (CycleGAN)
under an identical 50-pair budget. An ArcFace recognizer trained **only** on the synthetic
data transfers to real thermal benchmarks, including unseen-identity cross-sensor settings.
Full protocol, confidence intervals and open-set results are in the code repository.

## 🔁 Reproducibility & code

Training, generation and evaluation code, plus the generation prompt and configuration:
**[github.com/GbrlOl/thermal-fr-lora](https://github.com/GbrlOl/thermal-fr-lora)**

The synthetic **PUCV-TER-S** dataset and the source **PUCV-VTF** recordings are available
from the corresponding author upon reasonable request, subject to the consent conditions of
the original captures. With the released code and these weights, the synthetic dataset can
be regenerated exactly from the source visible images.

## 📜 License & intended use

This repository is labeled **`cc-by-nc-4.0`** (attribution, non-commercial). Because the
weights are a **Derivative of FLUX.1 Kontext [dev]**, the upstream
**[FLUX.1 [dev] Non-Commercial License](https://huggingface.co/black-forest-labs/FLUX.1-Kontext-dev/blob/main/LICENSE.md)**
and its Acceptable Use Policy also apply, and its restrictions (including non-commercial use
only) propagate to these weights. In case of any conflict, the more restrictive terms govern.
Commercial use of the base model requires a separate license from Black Forest Labs.

## 🔒 Ethical considerations

The synthetic images derive from **consented** captures (PUCV-VTF) and are intended solely
for research on data scarcity in thermal biometrics. Identity-preserving generative models
can, in principle, be misused to fabricate biometric samples; access is therefore gated,
redistribution is non-commercial and attribution-bound, and downstream users are expected to
adopt equivalent safeguards. No model capable of impersonating individuals outside the
enrolled cohort is distributed.

## 📖 Citation

```bibtex
@article{11683418,
  author={Hermosilla, Gabriel and Jara, Ashley and Olmos, Gabriel and Soto, Lisa and Cocca-Guardia, Giovanni},
  journal={IEEE Access}, 
  title={Thermal Face Recognition From Synthetic Data: FLUX.1 Kontext Image-to-Image Adaptation and Cross-Sensor Evaluation}, 
  year={2026},
  volume={14},
  pages={137824-137840},
  doi={10.1109/ACCESS.2026.3731153}
}
```

## 🙏 Acknowledgements

Funded by ANID (FONDECYT Grant 1240573; ANID Magíster Nacional 2025-22251171; ANID Doctorado
Nacional 2025-21251472), Pontificia Universidad Católica de Valparaíso (PUCV), Chile.