Add checkbox for variable training dims

4 files changed, 8 insertions, 5 deletions

diff --git a/modules/hypernetworks/hypernetwork.py b/modules/hypernetworks/hypernetwork.py
index b0cfbe71..dba52841 100644
--- a/modules/hypernetworks/hypernetwork.py
+++ b/modules/hypernetworks/hypernetwork.py
@@ -403,7 +403,7 @@ def create_hypernetwork(name, enable_sizes, overwrite_old, layer_structure=None,
     shared.reload_hypernetworks()

 

 

-def train_hypernetwork(hypernetwork_name, learn_rate, batch_size, gradient_step, data_root, log_directory, training_width, training_height, steps, clip_grad_mode, clip_grad_value, shuffle_tags, tag_drop_out, latent_sampling_method, create_image_every, save_hypernetwork_every, template_file, preview_from_txt2img, preview_prompt, preview_negative_prompt, preview_steps, preview_sampler_index, preview_cfg_scale, preview_seed, preview_width, preview_height):

+def train_hypernetwork(hypernetwork_name, learn_rate, batch_size, gradient_step, data_root, log_directory, training_width, training_height, varsize, steps, clip_grad_mode, clip_grad_value, shuffle_tags, tag_drop_out, latent_sampling_method, create_image_every, save_hypernetwork_every, template_file, preview_from_txt2img, preview_prompt, preview_negative_prompt, preview_steps, preview_sampler_index, preview_cfg_scale, preview_seed, preview_width, preview_height):

     # images allows training previews to have infotext. Importing it at the top causes a circular import problem.

     from modules import images

 

diff --git a/modules/textual_inversion/dataset.py b/modules/textual_inversion/dataset.py
index 375178ed..7f8a314f 100644
--- a/modules/textual_inversion/dataset.py
+++ b/modules/textual_inversion/dataset.py
@@ -29,7 +29,7 @@ class DatasetEntry:
 

 

 class PersonalizedBase(Dataset):

-    def __init__(self, data_root, width, height, repeats, flip_p=0.5, placeholder_token="*", model=None, cond_model=None, device=None, template_file=None, include_cond=False, batch_size=1, gradient_step=1, shuffle_tags=False, tag_drop_out=0, latent_sampling_method='once'):

+    def __init__(self, data_root, width, height, repeats, flip_p=0.5, placeholder_token="*", model=None, cond_model=None, device=None, template_file=None, include_cond=False, batch_size=1, gradient_step=1, shuffle_tags=False, tag_drop_out=0, latent_sampling_method='once', varsize=False):

         re_word = re.compile(shared.opts.dataset_filename_word_regex) if len(shared.opts.dataset_filename_word_regex) > 0 else None

 

         self.placeholder_token = placeholder_token

@@ -59,7 +59,7 @@ class PersonalizedBase(Dataset):
                 raise Exception("interrupted")

             try:

                 image = Image.open(path).convert('RGB')

-                if width < 2000:

+                if not varsize:

                     image = image.resize((width, height), PIL.Image.BICUBIC)

                 else:

                     assert batch_size == 1, 'variable img size must have batch size 1'

diff --git a/modules/textual_inversion/textual_inversion.py b/modules/textual_inversion/textual_inversion.py
index 9f96d0fd..110efd19 100644
--- a/modules/textual_inversion/textual_inversion.py
+++ b/modules/textual_inversion/textual_inversion.py
@@ -255,7 +255,7 @@ def validate_train_inputs(model_name, learn_rate, batch_size, gradient_step, dat
     if save_model_every or create_image_every:

         assert log_directory, "Log directory is empty"

 

-def train_embedding(embedding_name, learn_rate, batch_size, gradient_step, data_root, log_directory, training_width, training_height, steps, clip_grad_mode, clip_grad_value, shuffle_tags, tag_drop_out, latent_sampling_method, create_image_every, save_embedding_every, template_file, save_image_with_stored_embedding, preview_from_txt2img, preview_prompt, preview_negative_prompt, preview_steps, preview_sampler_index, preview_cfg_scale, preview_seed, preview_width, preview_height):

+def train_embedding(embedding_name, learn_rate, batch_size, gradient_step, data_root, log_directory, training_width, training_height, varsize, steps, clip_grad_mode, clip_grad_value, shuffle_tags, tag_drop_out, latent_sampling_method, create_image_every, save_embedding_every, template_file, save_image_with_stored_embedding, preview_from_txt2img, preview_prompt, preview_negative_prompt, preview_steps, preview_sampler_index, preview_cfg_scale, preview_seed, preview_width, preview_height):

     save_embedding_every = save_embedding_every or 0

     create_image_every = create_image_every or 0

     validate_train_inputs(embedding_name, learn_rate, batch_size, gradient_step, data_root, template_file, steps, save_embedding_every, create_image_every, log_directory, name="embedding")

@@ -309,7 +309,7 @@ def train_embedding(embedding_name, learn_rate, batch_size, gradient_step, data_
 

     pin_memory = shared.opts.pin_memory

 

-    ds = modules.textual_inversion.dataset.PersonalizedBase(data_root=data_root, width=training_width, height=training_height, repeats=shared.opts.training_image_repeats_per_epoch, placeholder_token=embedding_name, model=shared.sd_model, cond_model=shared.sd_model.cond_stage_model, device=devices.device, template_file=template_file, batch_size=batch_size, gradient_step=gradient_step, shuffle_tags=shuffle_tags, tag_drop_out=tag_drop_out, latent_sampling_method=latent_sampling_method)

+    ds = modules.textual_inversion.dataset.PersonalizedBase(data_root=data_root, width=training_width, height=training_height, repeats=shared.opts.training_image_repeats_per_epoch, placeholder_token=embedding_name, model=shared.sd_model, cond_model=shared.sd_model.cond_stage_model, device=devices.device, template_file=template_file, batch_size=batch_size, gradient_step=gradient_step, shuffle_tags=shuffle_tags, tag_drop_out=tag_drop_out, latent_sampling_method=latent_sampling_method, varsize=varsize)

 

     if shared.opts.save_training_settings_to_txt:

         save_settings_to_file(log_directory, {**dict(model_name=checkpoint.model_name, model_hash=checkpoint.hash, num_of_dataset_images=len(ds), num_vectors_per_token=len(embedding.vec)), **locals()})

diff --git a/modules/ui.py b/modules/ui.py
index 99483130..4e709a71 100644
--- a/modules/ui.py
+++ b/modules/ui.py
@@ -1343,6 +1343,7 @@ def create_ui():
                     template_file = gr.Textbox(label='Prompt template file', value=os.path.join(script_path, "textual_inversion_templates", "style_filewords.txt"), elem_id="train_template_file")

                     training_width = gr.Slider(minimum=64, maximum=2048, step=8, label="Width", value=512, elem_id="train_training_width")

                     training_height = gr.Slider(minimum=64, maximum=2048, step=8, label="Height", value=512, elem_id="train_training_height")

+                    varsize = gr.Checkbox(label="Ignore dimension settings and do not resize images", value=False, elem_id="train_varsize")

                     steps = gr.Number(label='Max steps', value=100000, precision=0, elem_id="train_steps")

 

                     with FormRow():

@@ -1449,6 +1450,7 @@ def create_ui():
                 log_directory,

                 training_width,

                 training_height,

+                varsize,

                 steps,

                 clip_grad_mode,

                 clip_grad_value,

@@ -1480,6 +1482,7 @@ def create_ui():
                 log_directory,

                 training_width,

                 training_height,

+                varsize,

                 steps,

                 clip_grad_mode,

                 clip_grad_value,