---
license: cc-by-nc-nd-4.0
base_model: black-forest-labs/FLUX.1-Kontext-dev
library_name: diffusers
pipeline_tag: image-to-image
datasets:
  - deepmancer/baldy
tags:
  - flux
  - lora
  - diffusers
  - safetensors
  - image-to-image
  - inpainting
  - portrait-editing
  - hair
  - bald
  - bald-converter
  - bald-konverter
  - hairport
  - siggraph-2026
  - synthetic-data
  - arxiv:2606.12562
---

# Bald Converter LoRA Weights

[![Project Page](https://img.shields.io/badge/Project%20Page-HairPort-2ea44f)](https://deepmancer.github.io/HairPort/)
[![Code](https://img.shields.io/badge/Code-GitHub-181717)](https://github.com/deepmancer/HairPort)
[![Dataset](https://img.shields.io/badge/Dataset-Baldy-ff69b4)](https://huggingface.co/datasets/deepmancer/baldy)
[![arXiv](https://img.shields.io/badge/arXiv-2606.12562-b31b1b)](https://arxiv.org/abs/2606.12562)
[![Paper DOI](https://img.shields.io/badge/DOI-10.1145%2F3799902.3811046-2f6f9f)](https://doi.org/10.1145/3799902.3811046)
[![License](https://img.shields.io/badge/License-CC%20BY--NC--ND%204.0-dc6f35)](https://creativecommons.org/licenses/by-nc-nd/4.0/)

**Bald Converter** is the LoRA-based in-context bald-generation module used by **HairPort: In-context 3D-aware Hair Import and Transfer for Images**, an **ACM SIGGRAPH 2026** paper. The paper is available on arXiv ([arXiv:2606.12562](https://arxiv.org/abs/2606.12562)), and the ACM DOI is [10.1145/3799902.3811046](https://doi.org/10.1145/3799902.3811046).

This repository contains two FLUX.1 Kontext LoRA adapters for generating realistic bald versions of portrait images while preserving identity, facial structure, clothing, background, lighting, and camera style.

## What This Repository Contains

| File | Size | Variant | Purpose |
|---|---:|---|---|
| `bald_konvertor_wo_seg_000003400.safetensors` | 171,969,368 bytes | `wo_seg` | Fast two-panel bald conversion without segmentation preprocessing |
| `bald_konvertor_w_seg_000004900.safetensors` | 171,969,368 bytes | `w_seg` | Segmentation-guided four-panel refinement for higher-quality conversion |
| `hairport_data.zip` | ~222 MB | data | Pipeline + PEAR runtime assets (landmark embeddings and SMPL-X / FLAME models for `w_seg` / `auto` fitting) |

The filename uses `konvertor` for historical compatibility with the released checkpoint names. The model/component name in the paper and codebase is **Bald Converter** or **BaldKonverter**.

## Model Details

| Item | Value |
|---|---|
| Base model | [`black-forest-labs/FLUX.1-Kontext-dev`](https://huggingface.co/black-forest-labs/FLUX.1-Kontext-dev) |
| Adapter type | LoRA |
| Framework | Diffusers |
| Weight format | Safetensors |
| Training data | [`deepmancer/baldy`](https://huggingface.co/datasets/deepmancer/baldy) |
| Primary task | Portrait bald conversion / hair removal |
| Released with | HairPort, ACM SIGGRAPH 2026 |

These files are adapter weights only. They do not include the base FLUX model, preprocessing models, or the HairPort inference code.

`hairport_data.zip` bundles the data assets the HairPort pipeline and the PEAR fitting backend load at runtime; `scripts/download_assets.py` downloads it and places each file under `assets/` and `modules/PEAR/assets/`. The PEAR EHM checkpoint and the YOLO detector are fetched automatically on first use.

## Modes

| Mode | Checkpoint | Speed | Quality | Preprocessing |
|---|---|---|---|---|
| `wo_seg` | `bald_konvertor_wo_seg_000003400.safetensors` | Fast | Good | None |
| `w_seg` | `bald_konvertor_w_seg_000004900.safetensors` | Slower | Best | SAM3, BEN2, and PEAR (SMPL-X) fitting |
| `auto` | Uses both checkpoints | Slower | Best | Runs `wo_seg`, then refines with `w_seg` |

`wo_seg` assembles a two-panel image and asks FLUX to generate the bald version in the right panel. `w_seg` uses a four-panel layout with segmentation context to improve structure preservation and remove residual hair more reliably.

## Installation

The recommended way to use these weights is through the HairPort source checkout:

```bash
git clone https://github.com/deepmancer/HairPort.git
cd HairPort
bash scripts/install.sh
```

If the base FLUX model or related gated assets require authentication, log in to Hugging Face before running inference:

```bash
huggingface-cli login
```

The LoRA checkpoints are downloaded automatically from this repository on first use.

## Quick Start

Run Bald Converter from the HairPort repository root:

```bash
python -m hairport.bald_konverter.cli \
  --input photo.jpg \
  --output bald.png \
  --mode auto
```

Fast mode without segmentation preprocessing:

```bash
python -m hairport.bald_konverter.cli \
  --input photo.jpg \
  --output bald_fast.png \
  --mode wo_seg
```

Batch processing:

```bash
python -m hairport.bald_konverter.cli \
  --input-dir ./faces \
  --output-dir ./bald \
  --mode auto
```

Save intermediate masks and FLUX input grids:

```bash
python -m hairport.bald_konverter.cli \
  --input photo.jpg \
  --output bald.png \
  --mode auto \
  --save-intermediates
```

## Python API

```python
from hairport.bald_konverter import BaldKonverterPipeline

pipeline = BaldKonverterPipeline(mode="auto", device="cuda")
result = pipeline("portrait.jpg", return_intermediates=True)

result.bald_image.save("bald.png")

# Optional debugging / visualization outputs
if result.flux_input_wo_seg is not None:
    result.flux_input_wo_seg.save("flux_input_wo_seg.png")
if result.flux_input_w_seg is not None:
    result.flux_input_w_seg.save("flux_input_w_seg.png")

pipeline.teardown()
```

Use a custom local checkpoint path if needed:

```python
from hairport.bald_konverter import BaldKonverterPipeline

pipeline = BaldKonverterPipeline(
    mode="wo_seg",
    lora_path_wo_seg="/path/to/bald_konvertor_wo_seg_000003400.safetensors",
)
result = pipeline("portrait.jpg")
result.bald_image.save("bald.png")
```

## Download Checkpoints Manually

```python
from huggingface_hub import hf_hub_download

repo_id = "deepmancer/bald_konverter"

wo_seg_path = hf_hub_download(
    repo_id=repo_id,
    filename="bald_konvertor_wo_seg_000003400.safetensors",
)

w_seg_path = hf_hub_download(
    repo_id=repo_id,
    filename="bald_konvertor_w_seg_000004900.safetensors",
)

print(wo_seg_path)
print(w_seg_path)
```

## Requirements

For inference through HairPort:

- Python >= 3.10
- CUDA GPU recommended
- Approximately 24 GB VRAM recommended for FLUX inference
- `torch`, `diffusers`, `transformers`, `safetensors`, and `huggingface-hub`
- For `w_seg` / `auto`: SAM3, BEN2, and PEAR (SMPL-X + FLAME) fitting (`ultralytics`, `smplx`, `pytorch3d`)
- PEAR's SMPL-X / FLAME runtime assets ship in `hairport_data.zip` (placed by `scripts/download_assets.py`); the PEAR EHM checkpoint and YOLO detector auto-download on first use

Refer to the [HairPort README](https://github.com/deepmancer/HairPort#installation) for the current full dependency recipe.

## Training Data

The Bald Converter LoRAs were trained with **Baldy**, a 6,400-sample synthetic paired dataset of hair/bald portraits generated for HairPort.

- Dataset: [`deepmancer/baldy`](https://huggingface.co/datasets/deepmancer/baldy)
- Each sample includes paired `hair_image` and `bald_image` columns, plus hair renders, background images, camera metadata, and rendering parameters.

## Intended Use

These weights are intended for research and development in:

- bald conversion and hair removal
- hairstyle-transfer preprocessing
- 3D-aware hair import and transfer systems
- paired image-to-image generation experiments
- HairPort-style source-face preparation

## Limitations And Responsible Use

Bald Converter is designed for portrait preprocessing and research use. Outputs may contain artifacts, incomplete hair removal, identity drift, or failures under unusual poses, occlusions, lighting, accessories, or image crops.

The model should not be used to misrepresent people, produce deceptive identity edits, or infer sensitive attributes. Users should review generated outputs before downstream use.

## Related Resources

- **Paper (arXiv):** [arXiv:2606.12562](https://arxiv.org/abs/2606.12562)
- **Project page:** [deepmancer.github.io/HairPort](https://deepmancer.github.io/HairPort/)
- **Code:** [github.com/deepmancer/HairPort](https://github.com/deepmancer/HairPort)
- **Baldy dataset:** [deepmancer/baldy](https://huggingface.co/datasets/deepmancer/baldy)
- **Weights:** [deepmancer/bald_konverter](https://huggingface.co/deepmancer/bald_konverter)

## Citation

If you use Bald Converter, Baldy, or HairPort in your research, please cite:

```bibtex
@inproceedings{heidari2026hairport,
  title     = {HairPort: In-context 3D-aware Hair Import and Transfer for Images},
  author    = {A. Heidari and A. Alimohammadi and A. Mahdavi-Amiri},
  booktitle = {Special Interest Group on Computer Graphics and Interactive Techniques Conference Conference Papers (SIGGRAPH Conference Papers '26)},
  year      = {2026},
  isbn      = {979-8-4007-2554-8/2026/07},
  doi       = {10.1145/3799902.3811046},
  url       = {https://doi.org/10.1145/3799902.3811046},
  location  = {Los Angeles, CA, USA}
}
```

## License

The LoRA weights in this repository are released under the [Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License](https://creativecommons.org/licenses/by-nc-nd/4.0/) (CC BY-NC-ND 4.0).

Use of the base FLUX model, Baldy dataset, HairPort code, and any external preprocessing models is governed by their respective licenses and terms.