control-edgedrawing-cv480edpf-drop0+50-fp16-checkpoint-118000

README.md

@@ -55,6 +55,10 @@ accelerate launch train_controlnet.py ^
 
 # Versions
 
+**Experiment 5 - control-edgedrawing-cv480edpf-drop0+50-fp16-checkpoint-118000**
+
+see experiment 4. resumed with epoch 2 from 90000 using `--proportion_empty_prompts=0.5` => results became worse, CN didn't pick up on no-prompts (I also tried checkpoint-104000). restarting with 50% drop.
+
 **Experiment 4 - control-edgedrawing-cv480edpf-drop0-fp16-checkpoint-90000**
 
 Conditioning images generated with [edpf.py](https://gitlab.com/-/snippets/3601881) using [opencv-contrib-python::ximgproc::EdgeDrawing](https://docs.opencv.org/4.8.0/d1/d1c/classcv_1_1ximgproc_1_1EdgeDrawing.html).
@@ -91,9 +95,7 @@ Default settings are:
 }
 ```
 
-`smoothed=True`, but no empty prompts
-Trained for 40000 steps with default settings
-=> conditioning images are too noisy
+`smoothed=True`, but no empty prompts. Trained for 40000 steps with default settings => conditioning images are too noisy.
 
 **Experiment 1 - control-edgedrawing-default-drop50-fp16-checkpoint-40000**
 
@@ -101,11 +103,10 @@ Same as experiment 2.
 
 Update: bug in algorithm produces too sparse images on default, see https://github.com/shaojunluo/EDLinePython/issues/4
 
-additional arguments: `--proportion_empty_prompts=0.5`
-Trained for 40000 steps with default settings
-=> empty prompts were probably too excessive
+additional arguments: `--proportion_empty_prompts=0.5`. Trained for 40000 steps with default settings => empty prompts were probably too excessive
 
 # Question and answers
 
 **Q: What's the point of another edge control net anyway?**
+
 A: 🤷

control-edgedrawing-cv480edpf-drop0+50-fp16-checkpoint-118000.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0c7fcb98e57ce7953a87813e23be56d7fc6b34d7c93890aafbf3c34738c566f
+size 722598616

control-edgedrawing-cv480edpf-drop0+50-fp16-checkpoint-118000.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e25224616598e5a2beb3c26cddef66ea07c737abe117e548140f29f969a0378f
+size 4714338