Update README.md

README.md

@@ -26,19 +26,19 @@ This is a custom-trained **ControlNet** model designed to perform **automatic co
 
 The model takes in a **black-and-white anime styled pictures** (converted to RGB) as conditioning input and generates a **colorized version** using Stable Diffusion.
 
-It is trained to act as a ControlNet module and requires a compatible SD base model — such as `nsfw-anime-xl-v1-sdxl` or other anime/manga-focused SD models.
+It is trained to act as a ControlNet module and requires a compatible SDXL base model — such as `nsfw-anime-xl-v1-sdxl` or other anime/manga-focused SDXL models.
 
 ---
 
 ## Training details
 
 - **Base model:** `John6666/nsfw-anime-xl-v1-sdxl`
-- **Dataset:** Custom dataset of ~6,000 image pairs from **Danbooru-based manga scans**, manually cleaned and resized to `512x512`
+- **Dataset:** Custom dataset of ~6,000 image pairs from **Danbooru-based manga scans**, manually cleaned and resized to `768x768`
 - **Inputs:**
   - `conditioning_image`: black-and-white manga scan (RGB)
-  - `text prompt`: optional (e.g. "colorized version of this panel")
-- **Loss:** MSE with FP16, trained on 1×RTX3090, 4 epochs
-- **Resolution:** 512x512
+  - `text prompt`: optional (e.g. "1girl, blue_eyes, blue_hair etc.")
+- **Loss:** MSE with FP16, trained on 1×RTX3090, 12 epochs
+- **Resolution:** 768x768  
 - **Scheduler:** default diffusers setup
 - **Optimizer:** LR: `1.4e-4`
 
@@ -76,7 +76,7 @@ image.save("colorized.png")
 - Place `diffusion_pytorch_model.safetensors` into your `ComfyUI/models/controlnet/` folder
 - Make sure to also include the `config.json`
 - Select this ControlNet in your workflow
-- Use grayscale images (512x512) as conditioning inputs
+- Use grayscale images as conditioning inputs
 
 ---
 
@@ -85,25 +85,25 @@ image.save("colorized.png")
 This version was trained using the SDXL-compatible ControlNet pipeline with the following CLI command:
 
 ```bash
-accelerate launch train_controlnet_sdxl.py \
-  --pretrained_model_name_or_path John6666/nsfw-anime-xl-v1-sdxl \
-  --dataset_name SubMaroon/danbooru-colored \
-  --image_column image \
-  --conditioning_image_column conditioning_image \
-  --caption_column prompt \
-  --output_dir ./controlnet-colorization \
-  --resolution 512 \
-  --train_batch_size 8 \
-  --gradient_accumulation_steps 2 \
-  --learning_rate 1.4e-4 \
-  --num_train_epochs 4 \
-  --mixed_precision fp16 \
+accelerate launch train_controlnet.py \
+  --pretrained_model_name_or_path="John6666/nsfw-anime-xl-v1-sdxl" \
+  --dataset_name="SubMaroon/danbooru-colored" \
+  --image_column="image" \
+  --conditioning_image_column="conditioning_image" \
+  --caption_column="prompt" \
+  --output_dir="./controlnet-colorization" \
+  --resolution=768 \
+  --train_batch_size=4 \
+  --gradient_accumulation_steps=4 \
+  --learning_rate=1.4e-4 \
+  --num_train_epochs=12 \
+  --mixed_precision="fp16" \
   --gradient_checkpointing \
-  --checkpointing_steps 1000 \
-  --validation_steps 1000 \
-  --report_to tensorboard \
-  --tracker_project_name controlnet-colorization \
-  --seed 42
+  --checkpointing_steps=1000 \
+  --validation_steps=1000 \
+  --report_to="tensorboard" \
+  --tracker_project_name="controlnet-colorization" \
+  --seed=42
 ```
 
 ---