ameliasasinDDG commited on
Commit
c8c6c9a
·
verified ·
1 Parent(s): 423fbd7

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +16 -8
README.md CHANGED
@@ -29,17 +29,25 @@ These are controlnet weights trained on stabilityai/stable-diffusion-2-1-base wi
29
 
30
 
31
  ## Intended uses & limitations
32
-
33
- #### How to use
34
-
35
- ```python
36
- # TODO: add an example code snippet for running this diffusion pipeline
37
- ```
38
 
39
  #### Limitations and bias
40
 
41
- [TODO: provide examples of latent issues and potential remediations]
42
 
43
  ## Training details
44
 
45
- [TODO: describe the data used to train the model]
 
 
 
 
 
 
 
 
 
 
 
 
 
 
29
 
30
 
31
  ## Intended uses & limitations
32
+ Run only with prompt Van Gogh Painting of ... since dinetuned on his paintings
 
 
 
 
 
33
 
34
  #### Limitations and bias
35
 
36
+ it it finetuned on only 3 epoch of 500 images due to computational limitations
37
 
38
  ## Training details
39
 
40
+ --pretrained_model_name_or_path="runwayml/stable-diffusion-v1-5" \
41
+ --controlnet_model_name_or_path="lllyasviel/sd-controlnet-canny" \
42
+ --output_dir="model_out" \
43
+ --dataset_name=ameliasasinDDG/vanGogh \
44
+ --conditioning_image_column=target \
45
+ --image_column=source \
46
+ --caption_column=prompt \
47
+ --resolution=512 \
48
+ --learning_rate=1e-5 \
49
+ --train_batch_size=8 \
50
+ --num_train_epochs=3 \
51
+ --tracker_project_name="controlnet" \
52
+ --checkpointing_steps=5000 \
53
+ --push_to_hub