Update README.md
Browse files
README.md
CHANGED
|
@@ -15,9 +15,14 @@ tags:
|
|
| 15 |
- safetensors
|
| 16 |
---
|
| 17 |
|
| 18 |
-
# Ref2Font
|
| 19 |
|
| 20 |
-
**Ref2Font
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 21 |
|
| 22 |
**Changes in V2:**
|
| 23 |
- Fixed alignment issues (letters no longer "dance" or jump).
|
|
@@ -28,12 +33,11 @@ tags:
|
|
| 28 |
|
| 29 |
## Examples
|
| 30 |
|
|
|
|
| 31 |
|
| 32 |
-

|
| 35 |
|
| 36 |
-
:
|
|
@@ -42,7 +46,7 @@ https://github.com/SnJake/Ref2Font
|
|
| 42 |
```
|
| 43 |
|
| 44 |
## What’s included
|
| 45 |
-
- `
|
| 46 |
- `Example Workflow/` (ComfyUI workflow with notes inside nodes)
|
| 47 |
- `Example/` (input images and their atlases)
|
| 48 |
- Post-processing scripts (`flux_pipeline.py`, `flux_grid_to_ttf.py`, `flux_upscale.py`)
|
|
@@ -77,9 +81,13 @@ https://huggingface.co/SnJake/Ref2Font/blob/main/Ref2FontV2.safetensors
|
|
| 77 |
```
|
| 78 |
Place in: `ComfyUI/models/loras`
|
| 79 |
|
| 80 |
-
|
| 81 |
-
|
| 82 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
| 83 |
|
| 84 |
### Input image rules
|
| 85 |
- **Strict black & white only** (no gray, no shadows, no volume)
|
|
|
|
| 15 |
- safetensors
|
| 16 |
---
|
| 17 |
|
| 18 |
+
# Ref2Font V3 — Contextual LoRA for FLUX.2 Klein 9B
|
| 19 |
|
| 20 |
+
**Ref2Font V3** is an updated **contextual LoRA** trained for **black-forest-labs/FLUX.2-klein-9B**. It generates **1280×1280 font atlases** from a single reference image "Aa".
|
| 21 |
+
|
| 22 |
+
### Changes in V3:
|
| 23 |
+
- **Cyrillic Support:** Now generates Russian fonts using "Аа" as reference.
|
| 24 |
+
- **Extended Glyphs:** Added `"` and `&`.
|
| 25 |
+
- **Straighter Letters:** Improved alignment and reduced "jitter" in atlas generation.
|
| 26 |
|
| 27 |
**Changes in V2:**
|
| 28 |
- Fixed alignment issues (letters no longer "dance" or jump).
|
|
|
|
| 33 |
|
| 34 |
## Examples
|
| 35 |
|
| 36 |
+

|
| 37 |
|
| 38 |
+

|
|
|
|
|
|
|
| 39 |
|
| 40 |
+

|
| 41 |
|
| 42 |
## Guide
|
| 43 |
The full usage, installation guide and detailed workflow live in the [GitHub repo](https://github.com/SnJake/Ref2Font):
|
|
|
|
| 46 |
```
|
| 47 |
|
| 48 |
## What’s included
|
| 49 |
+
- `Ref2FontV3.safetensors` (LoRA weights)
|
| 50 |
- `Example Workflow/` (ComfyUI workflow with notes inside nodes)
|
| 51 |
- `Example/` (input images and their atlases)
|
| 52 |
- Post-processing scripts (`flux_pipeline.py`, `flux_grid_to_ttf.py`, `flux_upscale.py`)
|
|
|
|
| 81 |
```
|
| 82 |
Place in: `ComfyUI/models/loras`
|
| 83 |
|
| 84 |
+
## ⚠️ IMPORTANT: V3 Required Prompts
|
| 85 |
+
|
| 86 |
+
**For Latin ("Aa" reference):**
|
| 87 |
+
> A technical font atlas grid of the Latin charset: "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789!?.,;:-"&". The style is strictly derived from the reference image "Aa".
|
| 88 |
+
|
| 89 |
+
**For Cyrillic ("Аа" reference):**
|
| 90 |
+
> A technical font atlas grid of the Cyrillic charset: "АБВГДЕЁЖЗИЙКЛМНОПРСТУФХЦЧШЩЪЫЬЭЮЯабвгдеёжзийклмнопрстуфхцчшщъыьэюя0123456789!?.,;:-"&". The style is strictly derived from the reference image "Аа".
|
| 91 |
|
| 92 |
### Input image rules
|
| 93 |
- **Strict black & white only** (no gray, no shadows, no volume)
|