Update README.md

README.md

@@ -11,10 +11,9 @@ Based on https://github.com/lllyasviel/ControlNet/discussions/318
 ```
 accelerate launch train_controlnet.py ^
   --pretrained_model_name_or_path="runwayml/stable-diffusion-v1-5" ^
-  --output_dir="control-edgedrawing-default-drop50-fp16/" ^
+  --output_dir="control-edgedrawing-[version]-fp16/" ^
   --dataset_name="mydataset" ^
   --mixed_precision="fp16" ^
-  --proportion_empty_prompts=0.5 ^
   --resolution=512 ^
   --learning_rate=1e-5 ^
   --train_batch_size=1 ^
@@ -26,7 +25,11 @@ accelerate launch train_controlnet.py ^
   --seed=0
 ```
 
-Trained for 40000 steps on images converted with https://github.com/shaojunluo/EDLinePython using `smoothed = False` and default settings:
+Images converted with https://github.com/shaojunluo/EDLinePython
+
+Default settings are:
+
+`smoothed=False`
 
 ```
 { 'ksize'            :  5
@@ -37,13 +40,14 @@ Trained for 40000 steps on images converted with https://github.com/shaojunluo/E
 }
 ```
 
-**TODO**
+**control-edgedrawing-default-drop50-fp16-checkpoint-40000**
+
+additional argument: `--proportion_empty_prompts=0.5`
+Trained for 40000 steps with default settings
+=> empty prompts were probably too excessive
 
-Results are not good so far:
+**control-edgedrawing-default-noisy-drop0-fp16-checkpoint-40000**
 
-* `--proportion_empty_prompts=0.5` me be too excessive for 40000 steps
-* Use `smoothed = True` next time, maybe control net doesn't pick up on single pixels
-* Find better parameter spread instead of default values, most images are very sparse
-* Train on more steps
-* Train on more diverse dataset
-* Train on higher-precision
+`smoothed=True`, but no empty prompts
+Trained for 40000 steps with default settings
+=> conditioning images are too noisy