metadata

license: cc-by-nc-sa-4.0
datasets:
  - ChristophSchuhmann/improved_aesthetics_6.5plus
language:
  - en
tags:
  - controlnet

Controls image generation by edge maps generated with Edge Drawing. Note that Edge Drawing comes in different flavors: original (ed), parameter free (edpf), color (edcolor).

Based on my monologs at github.com - Edge Drawing
For usage see the model page on civitai.com - Model.
To generate edpf maps you can use this space or this script gitlab.com.
For evaluation see the corresponding .zip with images at the files.
To run your own evaluations you can use this script at gitlab.com.

Edge Drawing Parameter Free

Clear and pristine! Wooow!

Example

sampler=UniPC steps=20 cfg=7.5 seed=0 batch=9 model: v1-5-pruned-emaonly.safetensors cherry-picked: 1/9

prompt: a detailed high-quality professional photo of swedish woman standing in front of a mirror, dark brown hair, white hat with purple feather

Canndy Edge for comparison (default in Automatic1111)

Noise, artifacts and missing edges. Yuck! Ugh!

Image dataset

laion2B-en aesthetics>=6.5 dataset
--min_image_size 512 --max_aspect_ratio 2 --resize_mode="center_crop" --image_size 512
resulting in 180k images

Training

accelerate launch train_controlnet.py ^
  --pretrained_model_name_or_path="runwayml/stable-diffusion-v1-5" ^
  --output_dir="control-edgedrawing-[version]-fp16/" ^
  --dataset_name="mydataset" ^
  --mixed_precision="fp16" ^
  --resolution=512 ^
  --learning_rate=1e-5 ^
  --train_batch_size=1 ^
  --gradient_accumulation_steps=4 ^
  --gradient_checkpointing ^
  --use_8bit_adam ^
  --enable_xformers_memory_efficient_attention ^
  --set_grads_to_none ^
  --seed=0

Evaluation

To evaluate the model it makes sense to compare it with the original Canny model. Original evaluations and comparisons are available at ControlNet 1.0 repo, ControlNet 1.1 repo, ControlNet paper v1, ControlNet paper v2 and Diffusers implementation. Some points we have to keep in mind when comparing canny with edpf in order not to compare apples with oranges:

canny 1.0 model was trained on 3M images with fp32, canny 1.1 model on even more, while edpf model so far is only trained on a 180k-360k with fp16.
canny edge-detector requires parameter tuning while edpf is parameter free.
Should we manually fine-tune canny to find the perfect input image or do we leave it at default? We could argue that "no fine-tuning required" is the usp of edpf and we want to compare in the default setting, whereas canny fine-tuning is subjective.
Would the canny model actually benefit from a edpf pre-processor and we might not even require a specialized edpf model? (2023-09-25: see eval_canny_edpf.zip but it seems as if it doesn't work and the edpf model may be justified)
When evaluating human images we need to be aware of Stable Diffusion's inherent limits, like disformed faces and hands, and don't attribute them to the control net.
When evaluating style we need to be aware of the bias from the image dataset (laion2b-en-aesthetics65), which might tend to generating "aesthetic" images, and not actually work "intrisicly better".

Versions

Experiment 1 - 2023-09-19 - control-edgedrawing-default-drop50-fp16-checkpoint-40000

Images converted with https://github.com/shaojunluo/EDLinePython (based on original (non-parameter free) edge drawing). Default settings are:

smoothed=False

{ 'ksize'            :  5
, 'sigma'            :  1.0
, 'gradientThreshold': 36
, 'anchorThreshold'  :  8
, 'scanIntervals'    :  1
}

additional arguments: --proportion_empty_prompts=0.5.

Trained for 40000 steps with default settings => results are not good. empty prompts were probably too excessive. retry with no drops and different algorithm parameters.

Update 2023-09-22: bug in algorithm produces too sparse images on default, see https://github.com/shaojunluo/EDLinePython/issues/4

Experiment 2 - 2023-09-20 - control-edgedrawing-default-noisy-drop0-fp16-checkpoint-40000

Same as experiment 1 with smoothed=True and --proportion_empty_prompts=0.

Trained for 40000 steps with default settings => results are not good. conditioning images look too noisy. investigate algorithm.

Experiment 3.0 - 2023-09-22 - control-edgedrawing-cv480edpf-drop0-fp16-checkpoint-45000

Conditioning images generated with edpf.py using opencv-contrib-python::ximgproc::EdgeDrawing.

ed     = cv2.ximgproc.createEdgeDrawing()
params = cv2.ximgproc.EdgeDrawing.Params()
params.PFmode = True
ed.setParams(params)
edges    = ed.detectEdges(image)
edge_map = ed.getEdgeImage(edges)

45000 steps => looks good. resuming with left-right flipped images. released as version 0.1 on civitai.

Experiment 3.1 - 2023-09-24 - control-edgedrawing-cv480edpf-drop0-fp16-checkpoint-90000

90000 steps (45000 steps on original, 45000 steps with left-right flipped images) => quality became better, might release as 0.2 on civitai.

Experiment 3.2 - 2023-09-24 -control-edgedrawing-cv480edpf-drop0+50-fp16-checkpoint-118000

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 intermediate checkpoint-104000). restarting with 50% drop.

Experiment 4.0 - 2023-09-25 - control-edgedrawing-cv480edpf-drop50-fp16-checkpoint-45000

see experiment 3.0. restarted from 0 with --proportion_empty_prompts=0.5 => results are not good, 50% is probably too much for 45k steps. guessmode still doesn't work and tends to produces humans. resuming until 90k with right-left flipped in the hope it will get better with more images.

Experiment 4.1 - 2023-09-26 - control-edgedrawing-cv480edpf-drop50-fp16-checkpoint-90000

resumed from 45000 steps with left-right flipped images until 90000 steps => results are still not good, 50% is probably also too much for 90k steps. guessmode still doesn't work and tends to produces humans. aborting.

** Experiment 5.0 - 2023-09-28 - control-edgedrawing-cv480edpf-fastdup-fp16-checkpoint-45000 **

see experiment 3. cleaned original images following the fastdup introduction resulting in:

180210 images in total
 67854 duplicates
   644 outliers
    26 too dark
   321 too bright
    57 blurry
 68621 unique removed (that's 38%!)

restarted from 0 with left-right flipped images and --mixed-precision="no" to create a master release and converted to fp16 afterwards.

** Experiment 6.0 - control-edgedrawing-cv480edpf-rect-fp16-checkpoint-XXXXX **

see experiment 5.0.

included images with aspect ratio > 2
resized images with shortside to 512 which gives us rectangular images instead of 512x512 squares
center-cropped images to 512x(n)*64 (to make them SD compatible) and max longside 1024
sorted duplicates by similarity value from laion2b-en-aesthetics65 to get the best text of all duplicates

183410 images in total
 75686 duplicates
   381 outliers
    50 too dark
   436 too bright
    31 blurry
 76288 unique removed (that's 42%!)

restarted from 0 and --mixed-precision="fp16".

Ideas

make conceptual captions for laion
integrate edcolor
try to fine-tune from canny
image dataset with better captions (cc3m)
remove images by semantic (use only photos, paintings etc. for edge detection)
re-train with fp32

Question and answers

Q: What's the point of another edge control net anyway?

A: 🤷