Update README.md

README.md

@@ -15,17 +15,25 @@ tags:
   - safetensors
 ---
 
-# Ref2FontV1 — Contextual LoRA for FLUX.2 Klein 9B
+# Ref2Font V2 — 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.
+**Ref2Font V2** 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".
 
-> Disclaimer: it works **well**, but **not perfectly**. Expect occasional artifacts and minor alignment issues.
+**Changes in V2:**
+- Fixed alignment issues (letters no longer "dance" or jump).
+- Increased resolution to **1280x1280**.
+- Improved vectorization scripts.
+
+> Disclaimer: it works **well**, but **not perfectly**. Expect occasional artifacts.
 
 ## Examples
 
-![Example1_C](https://cdn-uploads.huggingface.co/production/uploads/658814fd586088fd274d8cc1/tV7JpfCWUOWOOwqAGY9WH.png)
-![Example2_C](https://cdn-uploads.huggingface.co/production/uploads/658814fd586088fd274d8cc1/S7ae0GOFxIvaUiS9dD4YU.png)
-![Example3_C](https://cdn-uploads.huggingface.co/production/uploads/658814fd586088fd274d8cc1/I0IKwF8iI4yJOGCEyzeUV.png)
+
+![Example_1_C](https://cdn-uploads.huggingface.co/production/uploads/658814fd586088fd274d8cc1/0r_Q2q9sNvNXKzAgUamG-.png)
+
+![Example_2_C](https://cdn-uploads.huggingface.co/production/uploads/658814fd586088fd274d8cc1/GQbdv0phQdc8a-lZMdnI1.png)
+
+![Example_3_C](https://cdn-uploads.huggingface.co/production/uploads/658814fd586088fd274d8cc1/njE7tHGxaJps7KyDmnKqY.png)
 
 ## Guide
 The full usage, installation guide and detailed workflow live in the [GitHub repo](https://github.com/SnJake/Ref2Font):
@@ -34,7 +42,7 @@ https://github.com/SnJake/Ref2Font
 ```
 
 ## What’s included
-- `Ref2FontV1.safetensors` (LoRA weights)
+- `Ref2FontV2.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`)
@@ -46,7 +54,7 @@ MIT
 ### Required models
 1) Base model:
 ```
-https://huggingface.co/black-forest-labs/FLUX.2-klein-9B/blob/main/flux-2-klein-9b.safetensors
+https://huggingface.co/black-forest-labs/FLUX.2-klein-base-9B/blob/main/flux-2-klein-base-9b.safetensors
 ```
 Place in: `ComfyUI/models/diffusion_models`
 
@@ -65,14 +73,17 @@ Place in: `ComfyUI/models/vae`
 ### LoRA
 Download:
 ```
-https://huggingface.co/SnJake/Ref2Font/blob/main/Ref2FontV1.safetensors
+https://huggingface.co/SnJake/Ref2Font/blob/main/Ref2FontV2.safetensors
 ```
-
 Place in: `ComfyUI/models/loras`
 
+### ⚠️ IMPORTANT: Required Prompt
+To get the correct grid layout and character sequence, you **must** use this exact prompt:
+> Generate letters and symbols "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789!?.,;:-" in the style of the letters given to you as a reference.
+
 ### Input image rules
 - **Strict black & white only** (no gray, no shadows, no volume)
-- **1024×1024** exactly
+- **1280×1280** (recommended)
 - Follow the examples in `Example/`
 
 ## Post-processing: Atlas → TTF
@@ -85,31 +96,21 @@ python "Flux 2 Klein 9B\flux_pipeline.py" ^
   --output-dir "G:\Flux 2 Klein 9B\test" ^
   --no-upscale ^
   --use-grid ^
-  --vectorize contours ^
   --simplify 0.5 ^
-  --canvas 1024 ^
+  --canvas 1280 ^
   --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 ^
+  --keep-components 3 ^
+  --min-component-area 10 ^
+  --component-center-bias 0.35 ^
+  --cell-bleed 0.12 ^
+  --cell-bleed-max 32 ^
   --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`.
+- `flux_upscale.py` is optional; you can skip it with `--no-upscale`.
+- If the atlas looks inverted, try removing `--no-auto-invert` or add `--invert`.