Update README.md

README.md

@@ -2,41 +2,56 @@
 license: apache-2.0
 ---
 
-## Converted LoRAs
-- [Flux.1 Kontext Deblur](https://civitaiarchive.com/models/1737381)
-- [Flux.1 Kontext Face Detailer](https://civitaiarchive.com/models/1752776)
+## ✅ Converted LoRAs
 
-## Conversion Scripts
-https://github.com/mit-han-lab/ComfyUI-nunchaku/issues/340
+| Converted LoRAs | Original LoRAs |
+|-----------------|----------------|
+| [flux_kontext_deblur_comfyui.safetensors](https://huggingface.co/lym00/comfyui_nunchaku_lora_conversion/blob/main/flux_kontext_deblur_comfyui.safetensors) | [Flux.1 Kontext Deblur](https://civitaiarchive.com/models/1737381) |
+| [flux_kontext_face_detailer_comfyui.safetensors](https://huggingface.co/lym00/comfyui_nunchaku_lora_conversion/blob/main/flux_kontext_face_detailer_comfyui.safetensors) | [Flux.1 Kontext Face Detailer](https://civitaiarchive.com/models/1752776) |
 
-https://gist.github.com/akedia/e0a132b587e30413665d299ad893a60e
 
-```Running convert_to_comfyui_lora.py
+## 🛠️ Conversion References
+**Script:** [convert_to_comfyui_lora.py](https://huggingface.co/lym00/comfyui_nunchaku_lora_conversion/blob/main/convert_to_comfyui_lora.py)
+
+Based on
+- **Nunchaku Issue:** [ComfyUI-nunchaku #340](https://github.com/mit-han-lab/ComfyUI-nunchaku/issues/340)  
+- **Example Gist:** [akedia/e0a132b5...](https://gist.github.com/akedia/e0a132b587e30413665d299ad893a60e)  
+
+---
+
+## 🔄 Example Conversion Log
+
+```bash
+Running convert_to_comfyui_lora.py
+
 🔄 Universal final_layer.adaLN LoRA patcher (.safetensors)
+
 Enter path to input LoRA .safetensors file: Flux_kontext_deblur.safetensors
 Enter path to save patched LoRA .safetensors file: flux_kontext_deblur_comfyui.safetensors
 
 ✅ Loaded 610 tensors from: Flux_kontext_deblur.safetensors
 
-🔑 Found these final_layer-related keys:
-   lora_unet_final_layer_linear.lora_down.weight
-   lora_unet_final_layer_linear.lora_up.weight
+🔑 Found final_layer-related keys:
+  - lora_unet_final_layer_linear.lora_down.weight
+  - lora_unet_final_layer_linear.lora_up.weight
+
+🔍 Checking for final_layer keys with prefix 'lora_unet_final_layer'
+  Linear down: lora_unet_final_layer_linear.lora_down.weight
+  Linear up:   lora_unet_final_layer_linear.lora_up.weight
+  ✅ Has final_layer.linear: True
+  ✅ Has final_layer.adaLN_modulation_1: False
 
-🔍 Checking for final_layer keys with prefix: 'lora_unet_final_layer'
-   Linear down: lora_unet_final_layer_linear.lora_down.weight
-   Linear up:   lora_unet_final_layer_linear.lora_up.weight
-   ✅ Has final_layer.linear: True
-   ✅ Has final_layer.adaLN_modulation_1: False
 ✅ Added dummy adaLN weights:
-   lora_unet_final_layer_adaLN_modulation_1.lora_down.weight (shape: torch.Size([16, 3072]))
-   lora_unet_final_layer_adaLN_modulation_1.lora_up.weight (shape: torch.Size([64, 16]))
+  - lora_unet_final_layer_adaLN_modulation_1.lora_down.weight (shape: torch.Size([16, 3072]))
+  - lora_unet_final_layer_adaLN_modulation_1.lora_up.weight   (shape: torch.Size([64, 16]))
 
 ✅ Patched file saved to: flux_kontext_deblur_comfyui.safetensors
    Total tensors now: 612
 
 🔍 Verifying patched keys:
-   lora_unet_final_layer_adaLN_modulation_1.lora_down.weight
-   lora_unet_final_layer_adaLN_modulation_1.lora_up.weight
-   lora_unet_final_layer_linear.lora_down.weight
-   lora_unet_final_layer_linear.lora_up.weight
-✅ Contains adaLN after patch: True```
+  - lora_unet_final_layer_adaLN_modulation_1.lora_down.weight
+  - lora_unet_final_layer_adaLN_modulation_1.lora_up.weight
+  - lora_unet_final_layer_linear.lora_down.weight
+  - lora_unet_final_layer_linear.lora_up.weight
+
+✅ Contains adaLN after patch: True