awoo

Signed-off-by: Balazs Horvath <[email protected]>

README.md

@@ -32,13 +32,16 @@ The Yiff Toolkit is a comprehensive set of tools designed to enhance your creati
       - [Sample Prompt File](#sample-prompt-file)
       - [`--lowram`](#--lowram)
       - [`--pretrained_model_name_or_path`](#--pretrained_model_name_or_path)
+      - [`--output_dir`](#--output_dir)
       - [`--train_data_dir`](#--train_data_dir)
       - [`--resolution`](#--resolution)
+      - [`--enable_bucket`](#--enable_bucket)
+      - [`--min_bucket_reso` `--max_bucket_reso`](#--min_bucket_reso---max_bucket_reso)
       - [`--optimizer_type`](#--optimizer_type)
       - [`--dataset_repeats`](#--dataset_repeats)
       - [`--max_train_steps`](#--max_train_steps)
       - [`--shuffle_caption`](#--shuffle_caption)
-      - [`--sdpa`](#--sdpa)
+      - [`--sdpa` or `--xformers` or `--mem_eff_attn`](#--sdpa-or---xformers-or---mem_eff_attn)
       - [`--sample_prompts --sample_sampler --sample_every_n_steps`](#--sample_prompts---sample_sampler---sample_every_n_steps)
     - [CosXL Training](#cosxl-training)
   - [Embeddings for 1.5 and SDXL](#embeddings-for-15-and-sdxl)
@@ -157,6 +160,14 @@ The directory containing the checkpoint you just downloaded. I recommend closing
     --pretrained_model_name_or_path="/ponydiffusers/" \
 ```
 
+#### `--output_dir`
+
+This is where all the saved epochs or steps will be saved, including the last one. If y
+
+```py
+    --output_dir="/output_dir" \
+```
+
 #### `--train_data_dir`
 
 The directory containing the dataset. We prepared this earlier together.
@@ -170,7 +181,24 @@ The directory containing the dataset. We prepared this earlier together.
 Always set this to match the model's resolution, which in Pony's case it is 1024x1024. If you can't fit into the VRAM, you can decrease it to `512,512` as a last resort.
 
 ```py
-    --resolution="512,512" \
+    --resolution="1024,1024" \
+```
+
+#### `--enable_bucket`
+
+⚠️
+
+```py
+    --enable_bucket \
+```
+
+#### `--min_bucket_reso` `--max_bucket_reso`
+
+⚠️
+
+```py
+    --min_bucket_reso=256 \
+    --max_bucket_reso=1024 \
 ```
 
 #### `--optimizer_type`
@@ -201,13 +229,13 @@ Specify the number of steps or epochs to train. If both `--max_train_steps` and
 
 Shuffles the captions set by `--caption_separator`, it is a comma `,` by default which will work perfectly for our case since our captions look like this:
 
-> rating_questionable, 5 fingers, anthro, bent over, big breasts, blue eyes, blue hair, breasts, butt, claws, curved horn, female, finger claws, fingers, fur, hair, huge breasts, looking at viewer, looking back, looking back at viewer, nipples, nude, pink body, pink hair, pink nipples, rear view, solo, tail, tail tuft, tuft, by lunarii, by x-leon-x, mythology, krystal \(darkmaster781\), dragon, scalie, wickerbeast, The image showcases a pink-scaled wickerbeast a furred dragon creature with blue eyes., She has large breasts and a thick tail., Her blue and pink horns are curved and pointy and she has a slight smiling expression on her face., Her scales are shiny and she has a blue and pink pattern on her body., Her hair is a mix of pink and blue., She is looking back at the viewer with a curious expression., She has a slight blush., 
+> rating_questionable, 5 fingers, anthro, bent over, big breasts, blue eyes, blue hair, breasts, butt, claws, curved horn, female, finger claws, fingers, fur, hair, huge breasts, looking at viewer, looking back, looking back at viewer, nipples, nude, pink body, pink hair, pink nipples, rear view, solo, tail, tail tuft, tuft, by lunarii, by x-leon-x, mythology, krystal \(darkmaster781\), dragon, scalie, wickerbeast, The image showcases a pink-scaled wickerbeast a furred dragon creature with blue eyes., She has large breasts and a thick tail., Her blue and pink horns are curved and pointy and she has a slight smiling expression on her face., Her scales are shiny and she has a blue and pink pattern on her body., Her hair is a mix of pink and blue., She is looking back at the viewer with a curious expression., She has a slight blush.,
 
 As you can tell, I have separated the caption part not just the tags with a `,` to make sure everything gets shuffled. I'm at this point pretty certain this is beneficial especially when your caption file contains more than 77 tokens.
 
-#### `--sdpa`
+#### `--sdpa` or `--xformers` or `--mem_eff_attn`
 
-The choice between `--xformers` and `--spda` will depend on your GPU. You can benchmark it by repeating a training with both!
+The choice between `--xformers` or `--mem_eff_attn` and `--spda` will depend on your GPU. You can benchmark it by repeating a training with them!
 
 #### `--sample_prompts --sample_sampler --sample_every_n_steps`