README.md

metadata

license: mit
base_model: black-forest-labs/FLUX.2-klein-9B
tags:
  - lora
  - flux
  - flux.2
  - flux.2-klein-9b
  - image-to-image
  - text-to-image
  - font
  - typography
  - atlas
  - comfyui
  - safetensors

Ref2FontV1 — Contextual LoRA for FLUX.2 Klein 9B

Ref2FontV1 is a contextual LoRA trained for black-forest-labs/FLUX.2-klein-9B. It generates 1024×1024 font atlases from a single reference image, following the same layout as the provided examples.

Disclaimer: it works well, but not perfectly. Expect occasional artifacts and minor alignment issues.

Examples

Guide

The full usage, installation guide and detailed workflow live in the GitHub repo:

https://github.com/SnJake/Ref2Font

What’s included

• Ref2FontV1.safetensors (LoRA weights)
• Example Workflow/ (ComfyUI workflow with notes inside nodes)
• Example/ (input images and their atlases)
• Post-processing scripts (flux_pipeline.py, flux_grid_to_ttf.py, flux_upscale.py)

License

MIT

ComfyUI setup

Required models

1. Base model:

https://huggingface.co/black-forest-labs/FLUX.2-klein-9B/blob/main/flux-2-klein-9b.safetensors

Place in: ComfyUI/models/diffusion_models

2. Text encoder (Qwen):

https://huggingface.co/Comfy-Org/vae-text-encorder-for-flux-klein-9b/blob/main/split_files/text_encoders/qwen_3_8b.safetensors

Place in: ComfyUI/models/text_encoders

3. VAE:

https://huggingface.co/Comfy-Org/vae-text-encorder-for-flux-klein-9b/blob/main/split_files/vae/flux2-vae.safetensors

Place in: ComfyUI/models/vae

LoRA

Download:

https://huggingface.co/SnJake/Ref2Font/blob/main/Ref2FontV1.safetensors

Place in: ComfyUI/models/loras

Input image rules

• Strict black & white only (no gray, no shadows, no volume)
• 1024×1024 exactly
• Follow the examples in Example/

Post-processing: Atlas → TTF

Use the included pipeline script to convert the atlas into a TTF.

Example command (Windows)

python "Flux 2 Klein 9B\flux_pipeline.py" ^
  --input "D:\ComfyUI_temp_nckhb_00003_.png" ^
  --output-dir "G:\Flux 2 Klein 9B\test" ^
  --no-upscale ^
  --use-grid ^
  --vectorize contours ^
  --simplify 0.5 ^
  --canvas 1024 ^
  --contour-level 0.5 ^
  --trace-scale 4 ^
  --trace-blur 1.0 ^
  --smooth-iters 2 ^
  --baseline-mode auto ^
  --baseline-quantile 0.9 ^
  --baseline-min-pixels 20 ^
  --cols 8 ^
  --rows 9 ^
  --no-auto-invert

Upscaler is optional. If you want to use flux_upscale.py, install PyTorch separately:

pip install torch torchvision --index-url https://download.pytorch.org/whl/cu121

Notes

• The upscaler is optional; you can skip it with --no-upscale.
• The optional upscaler is also hosted in this HF repo:

https://huggingface.co/SnJake/Ref2Font

• If the atlas looks inverted, try removing --no-auto-invert or add --invert.
• If letters look vertically misaligned, use --baseline-mode auto.