diff --git a/modules/segment.py b/modules/segment.py
index 7f1405dc1..261ecf56e 100644
--- a/modules/segment.py
+++ b/modules/segment.py
@@ -21,6 +21,7 @@ MODELS = {
'Facebook SAM ViT Huge': 'facebook/sam-vit-huge',
'SlimSAM Uniform': 'Zigeng/SlimSAM-uniform-50',
}
+COLORMAP = ['autumn', 'bone', 'jet', 'winter', 'rainbow', 'ocean', 'summer', 'spring', 'cool', 'hsv', 'pink', 'hot', 'parula', 'magma', 'inferno', 'plasma', 'viridis', 'cividis', 'twilight', 'shifted', 'turbo', 'deepgreen']
cache_dir = 'models/control/segment'
loaded_model = None
model: SamModel = None
@@ -49,43 +50,75 @@ def init(selected_model: str, input_image: gr.Image):
# run as auto-mask with all possible masks
-def run_segment(selected_model: str, input_image: gr.Image):
+def run_segment(selected_model: str, input_image: gr.Image, points_per_batch=64, pred_iou_thresh=0.75, stability_score_thresh=0.85, crops_nms_thresh=0.5, crop_overlap_ratio=0.3, topK=25, colormap='jet', erode=0, dilate=0):
if not init(selected_model, input_image):
- return input_image
+ return gr.update(), None
input_mask = input_image.get('mask', None) or Image.new('L', input_image.get('image', None).size, 255)
+ input_mask = input_mask.convert('L')
input_image = input_image.get('image', None)
generator: MaskGenerationPipeline = MaskGenerationPipeline(model=model, image_processor=processor, device=devices.device)
with devices.inference_context():
outputs = generator(
input_image,
- points_per_batch=64,
- pred_iou_thresh=0.75,
- stability_score_thresh=0.95,
- crops_nms_thresh=0.7,
- crop_overlap_ratio=0.3,
+ points_per_batch=points_per_batch,
+ pred_iou_thresh=pred_iou_thresh,
+ stability_score_thresh=stability_score_thresh,
+ crops_nms_thresh=crops_nms_thresh,
+ crop_overlap_ratio=crop_overlap_ratio,
)
combined_mask = np.zeros(input_mask.size, dtype='uint8')
- for i, mask in enumerate(outputs['masks']):
- mask = mask.astype('uint8') * i * 10
+ input_mask = np.array(input_mask) // 255
+ input_mask_size = np.count_nonzero(input_mask)
+ print('HERE', input_mask.shape, input_mask_size)
+ i = 1
+ for mask in outputs['masks']:
+ mask = mask.astype('uint8')
+ mask_size = np.count_nonzero(mask)
+ if mask_size == 0:
+ continue
+ overlap = 0
+ if input_mask_size > 0:
+ overlap = cv2.bitwise_and(mask, input_mask)
+ overlap = np.count_nonzero(overlap)
+ if overlap == 0:
+ continue
+ # TODO erode,dilate
+ if erode > 0:
+ mask = cv2.erode(mask, np.ones((erode, erode), np.uint8), iterations=2) # remove noise
+ if dilate > 0:
+ mask = cv2.dilate(mask, np.ones((dilate, dilate), np.uint8), iterations=2) # expand area
+ mask = (topK + 1 - i) * mask * (255 // topK) # set grayscale intensity so we can recolor
combined_mask = combined_mask + mask
- total_size = np.prod(mask.shape)
- area_size = np.count_nonzero(mask)
- shared.log.debug(f'Segment mask: i={i} area={area_size/total_size:.2f} score={outputs["scores"][i].item():.2f}')
- if i > 25:
+ i += 1
+ if i > topK:
break
- combined_mask = cv2.applyColorMap(combined_mask, cv2.COLORMAP_JET)
- combined_image = cv2.addWeighted(np.array(input_image), 0.6, combined_mask, 0.4, 0)
+ mask_size = np.count_nonzero(combined_mask)
+ total_size = np.prod(combined_mask.shape)
+ area_size = np.count_nonzero(combined_mask)
+ shared.log.debug(f'Segment mask: size={input_image.width}x{input_image.height} input={input_mask_size}px masked={mask_size}px area={area_size/total_size:.2f}')
+ colored_mask = cv2.applyColorMap(combined_mask, COLORMAP.index(colormap)) # recolor mask
+ combined_image = cv2.addWeighted(np.array(input_image), 0.6, colored_mask, 0.4, 0)
+ _thres, binary_mask = cv2.threshold(combined_mask, 1, 255, cv2.THRESH_BINARY_INV) # create mask
+ binary_mask = np.invert(binary_mask)
+
+ binary_mask = Image.fromarray(binary_mask)
combined_mask = Image.fromarray(combined_mask)
- combined_image = Image.fromarray(combined_image)
+ colored_mask = Image.fromarray(colored_mask)
+ overlay_image = Image.fromarray(combined_image)
+
+ # TODO return type
+ binary_mask.save('/tmp/mask-binary.png')
combined_mask.save('/tmp/mask-combined.png')
- combined_image.save('/tmp/mask-combined-image.png')
+ combined_mask.save('/tmp/mask-colored.png')
+ overlay_image.save('/tmp/mask-overlay.png')
+ return input_image, overlay_image
# run with sam model directly needing set of points
def run_segment_points(selected_model: str, input_image: gr.Image):
if not init(selected_model, input_image):
return input_image
- input_mask = input_image.get('mask', None) or Image.new('L', input_image.get('image', None).size, 0)
+ # input_mask = input_image.get('mask', None) or Image.new('L', input_image.get('image', None).size, 0)
input_image = input_image.get('image', None)
with devices.inference_context():
inputs = processor(
@@ -118,7 +151,7 @@ def run_segment_points(selected_model: str, input_image: gr.Image):
output_masks.append(mask)
-def create_segment_ui(input_image: gr.Image):
+def create_segment_ui(input_image: gr.Image, preview_image: gr.Image):
selected = gr.Dropdown(label="Segment", choices=MODELS.keys(), value='None')
- selected.change(fn=run_segment, inputs=[selected, input_image], outputs=[])
+ selected.change(fn=run_segment, inputs=[selected, input_image], outputs=[input_image, preview_image])
return selected
diff --git a/modules/timer.py b/modules/timer.py
index 4f1e6a744..da3996f59 100644
--- a/modules/timer.py
+++ b/modules/timer.py
@@ -22,11 +22,11 @@ class Timer:
self.total += e + extra_time
def summary(self, min_time=0.05):
- res = f"{self.total:.2f}"
+ res = f"{self.total:.2f} "
additions = [x for x in self.records.items() if x[1] >= min_time]
if not additions:
return res
- res += " { " + " ".join([f"{category}={time_taken:.2f}" for category, time_taken in additions]) + " }"
+ res += " ".join([f"{category}={time_taken:.2f}" for category, time_taken in additions])
return res
def reset(self):
diff --git a/modules/ui.py b/modules/ui.py
index 8cd2eeeea..7be951525 100644
--- a/modules/ui.py
+++ b/modules/ui.py
@@ -141,10 +141,9 @@ def create_ui(startup_timer = None):
timer.startup.record("ui-extras")
with gr.Blocks(analytics_enabled=False) as train_interface:
- if shared.backend == shared.Backend.ORIGINAL:
- from modules import ui_train
- ui_train.create_ui()
- timer.startup.record("ui-train")
+ from modules import ui_train
+ ui_train.create_ui()
+ timer.startup.record("ui-train")
with gr.Blocks(analytics_enabled=False) as models_interface:
from modules import ui_models
diff --git a/modules/ui_control.py b/modules/ui_control.py
index a39e323d4..50d3c2817 100644
--- a/modules/ui_control.py
+++ b/modules/ui_control.py
@@ -353,7 +353,7 @@ def create_ui(_blocks: gr.Blocks=None):
with gr.Row(variant='compact', elem_id="control_extra_networks", visible=False) as extra_networks_ui:
from modules import timer, ui_extra_networks
extra_networks_ui = ui_extra_networks.create_ui(extra_networks_ui, btn_extra, 'control', skip_indexing=shared.opts.extra_network_skip_indexing)
- timer.startup.record('ui-extra-networks')
+ timer.startup.record('ui-en')
with gr.Row(elem_id='control_status'):
result_txt = gr.HTML(elem_classes=['control-result'], elem_id='control-result')
@@ -368,8 +368,6 @@ def create_ui(_blocks: gr.Blocks=None):
input_resize = gr.Image(label="Input", show_label=False, type="pil", source="upload", interactive=True, tool="select", height=gr_height, visible=False, image_mode='RGB', elem_id='control_input_resize')
input_inpaint = gr.Image(label="Input", show_label=False, type="pil", source="upload", interactive=True, tool="sketch", height=gr_height, visible=False, image_mode='RGB', elem_id='control_input_inpaint', brush_radius=64, mask_opacity=0.6)
interrogate_clip, interrogate_booru = ui_sections.create_interrogate_buttons('control')
- # with gr.Row():
- # segment_ui = segment.create_segment_ui(input_inpaint)
with gr.Row():
input_buttons = [gr.Button('Select', visible=True, interactive=False), gr.Button('Inpaint', visible=True, interactive=True), gr.Button('Outpaint', visible=True, interactive=True)]
with gr.Tab('Video', id='in-video') as tab_video:
@@ -404,6 +402,10 @@ def create_ui(_blocks: gr.Blocks=None):
with gr.Tab('Preview', id='preview-image') as tab_image:
preview_process = gr.Image(label="Input", show_label=False, type="pil", source="upload", interactive=False, height=gr_height, visible=True)
+ # TODO segment as accordian
+ # with gr.Row():
+ # segment_ui = segment.create_segment_ui(input_inpaint, preview_process)
+
with gr.Tabs(elem_id='control-tabs') as _tabs_control_type:
with gr.Tab('ControlNet') as _tab_controlnet:
diff --git a/modules/ui_img2img.py b/modules/ui_img2img.py
index e1a3c4b62..708b35769 100644
--- a/modules/ui_img2img.py
+++ b/modules/ui_img2img.py
@@ -3,7 +3,7 @@ from PIL import Image
import gradio as gr
import numpy as np
from modules.call_queue import wrap_gradio_gpu_call, wrap_queued_call
-from modules import shared, ui_common, ui_sections, generation_parameters_copypaste
+from modules import timer, shared, ui_common, ui_sections, generation_parameters_copypaste
from modules.ui_components import FormRow, FormGroup
@@ -45,6 +45,7 @@ def create_ui():
with FormRow(variant='compact', elem_id="img2img_extra_networks", visible=False) as extra_networks_ui:
from modules import ui_extra_networks
extra_networks_ui_img2img = ui_extra_networks.create_ui(extra_networks_ui, img2img_extra_networks_button, 'img2img', skip_indexing=shared.opts.extra_network_skip_indexing)
+ timer.startup.record('ui-en')
with FormRow(elem_id="img2img_interface", equal_height=False):
with gr.Column(variant='compact', elem_id="img2img_settings"):
diff --git a/modules/ui_train.py b/modules/ui_train.py
index ae07b5d16..17358f395 100644
--- a/modules/ui_train.py
+++ b/modules/ui_train.py
@@ -1,6 +1,6 @@
import os
import gradio as gr
-from modules import sd_hijack, script_callbacks, shared
+from modules import script_callbacks, shared
from modules.ui_components import FormRow
from modules.ui_common import create_refresh_button
from modules.ui_sections import create_sampler_inputs
@@ -150,227 +150,231 @@ def create_ui():
)
### train embedding tab
- with gr.Tab(label="Train embedding", id="train_embedding_tab") as tab_ti:
- tab_ti.select(fn=lambda: train_tab_change('ti'), inputs=[], outputs=[action_pp, action_ti, action_hn])
- def get_textual_inversion_template_names():
- return sorted(textual_inversion.textual_inversion_templates)
+ if shared.backend == shared.Backend.ORIGINAL:
+ from modules import sd_hijack
+ with gr.Tab(label="Train embedding", id="train_embedding_tab") as tab_ti:
+ tab_ti.select(fn=lambda: train_tab_change('ti'), inputs=[], outputs=[action_pp, action_ti, action_hn])
+ def get_textual_inversion_template_names():
+ return sorted(textual_inversion.textual_inversion_templates)
- gr.HTML('Select existing embedding to continue training or create a new one
')
- with FormRow():
- with gr.Column():
- with gr.Row():
- ti_name = gr.Dropdown(label='Select embedding', choices=sorted(sd_hijack.model_hijack.embedding_db.word_embeddings.keys()))
- create_refresh_button(ti_name, sd_hijack.model_hijack.embedding_db.load_textual_inversion_embeddings, lambda: {"choices": sorted(sd_hijack.model_hijack.embedding_db.word_embeddings.keys())}, "refresh_train_embedding_name")
- with gr.Column():
- ti_new_name = gr.Textbox(label="Create emebedding")
- ti_init_text = gr.Textbox(label="Initialization text", value="*")
- ti_vectors = gr.Slider(label="Number of vectors per token", minimum=1, maximum=75, step=1, value=1)
- ti_overwrite = gr.Checkbox(value=False, label="Overwrite Old Embedding")
- with gr.Row():
- ti_create = gr.Button(value="Create embedding", variant='secondary')
-
- with gr.Box():
- gr.HTML('Training parameters
')
- ti_learn_rate = gr.Textbox(label='Embedding Learning rate', placeholder="Embedding Learning rate", value="0.005")
+ gr.HTML('Select existing embedding to continue training or create a new one
')
with FormRow():
- ti_clip_grad_mode = gr.Dropdown(value="disabled", label="Gradient Clipping", choices=["disabled", "value", "norm"])
- ti_clip_grad_value = gr.Number(label="Gradient clip value", value=0.1)
- ti_batch_size = gr.Number(label='Batch size', value=1, precision=0)
- ti_gradient_step = gr.Number(label='Gradient accumulation steps', value=1, precision=0)
- ti_steps = gr.Number(label='Max steps', value=1000, precision=0)
+ with gr.Column():
+ with gr.Row():
+ ti_name = gr.Dropdown(label='Select embedding', choices=sorted(sd_hijack.model_hijack.embedding_db.word_embeddings.keys()))
+ create_refresh_button(ti_name, sd_hijack.model_hijack.embedding_db.load_textual_inversion_embeddings, lambda: {"choices": sorted(sd_hijack.model_hijack.embedding_db.word_embeddings.keys())}, "refresh_train_embedding_name")
+ with gr.Column():
+ ti_new_name = gr.Textbox(label="Create emebedding")
+ ti_init_text = gr.Textbox(label="Initialization text", value="*")
+ ti_vectors = gr.Slider(label="Number of vectors per token", minimum=1, maximum=75, step=1, value=1)
+ ti_overwrite = gr.Checkbox(value=False, label="Overwrite Old Embedding")
+ with gr.Row():
+ ti_create = gr.Button(value="Create embedding", variant='secondary')
- with gr.Box():
- gr.HTML('Training images
')
- ti_dataset_directory = gr.Textbox(label='Dataset directory', placeholder="Path to directory with input images")
- with FormRow():
- ti_varsize = gr.Checkbox(label="Do not resize images", value=False)
- ti_width = gr.Slider(minimum=64, maximum=2048, step=8, label="Width", value=512)
- ti_height = gr.Slider(minimum=64, maximum=2048, step=8, label="Height", value=512)
- ti_use_weight = gr.Checkbox(label="Use PNG alpha channel as loss weight", value=False)
+ with gr.Box():
+ gr.HTML('Training parameters
')
+ ti_learn_rate = gr.Textbox(label='Embedding Learning rate', placeholder="Embedding Learning rate", value="0.005")
+ with FormRow():
+ ti_clip_grad_mode = gr.Dropdown(value="disabled", label="Gradient Clipping", choices=["disabled", "value", "norm"])
+ ti_clip_grad_value = gr.Number(label="Gradient clip value", value=0.1)
+ ti_batch_size = gr.Number(label='Batch size', value=1, precision=0)
+ ti_gradient_step = gr.Number(label='Gradient accumulation steps', value=1, precision=0)
+ ti_steps = gr.Number(label='Max steps', value=1000, precision=0)
- with gr.Box():
- gr.HTML('Dataset processing
')
- with FormRow():
- ti_template = gr.Dropdown(label='Prompt template', value="style_filewords.txt", choices=get_textual_inversion_template_names())
- create_refresh_button(ti_template, textual_inversion.list_textual_inversion_templates, lambda: {"choices": get_textual_inversion_template_names()}, "refrsh_train_template_file")
- ti_shuffle = gr.Checkbox(label="Shuffle tags", value=False)
- ti_tag_drop_out = gr.Slider(minimum=0, maximum=1, step=0.1, label="Drop out tags when creating prompts", value=0)
- ti_latent_sampling_method = gr.Radio(label='Choose latent sampling method', value="once", choices=['once', 'deterministic', 'random'])
+ with gr.Box():
+ gr.HTML('Training images
')
+ ti_dataset_directory = gr.Textbox(label='Dataset directory', placeholder="Path to directory with input images")
+ with FormRow():
+ ti_varsize = gr.Checkbox(label="Do not resize images", value=False)
+ ti_width = gr.Slider(minimum=64, maximum=2048, step=8, label="Width", value=512)
+ ti_height = gr.Slider(minimum=64, maximum=2048, step=8, label="Height", value=512)
+ ti_use_weight = gr.Checkbox(label="Use PNG alpha channel as loss weight", value=False)
- with gr.Box():
- gr.HTML('Training outputs
')
- with FormRow():
- ti_create_every = gr.Number(label='Create interim images', value=500, precision=0)
- ti_save_every = gr.Number(label='Create interim embeddings', value=500, precision=0)
- ti_save_image_with_stored_embedding = gr.Checkbox(label='Save images with embedding in PNG chunks', value=True)
- ti_preview_from_txt2img = gr.Checkbox(label='Use current settings for previews', value=False)
- ti_log_directory = gr.Textbox(label='Log directory', placeholder="Defaults to train/log/embedding", value="")
+ with gr.Box():
+ gr.HTML('Dataset processing
')
+ with FormRow():
+ ti_template = gr.Dropdown(label='Prompt template', value="style_filewords.txt", choices=get_textual_inversion_template_names())
+ create_refresh_button(ti_template, textual_inversion.list_textual_inversion_templates, lambda: {"choices": get_textual_inversion_template_names()}, "refrsh_train_template_file")
+ ti_shuffle = gr.Checkbox(label="Shuffle tags", value=False)
+ ti_tag_drop_out = gr.Slider(minimum=0, maximum=1, step=0.1, label="Drop out tags when creating prompts", value=0)
+ ti_latent_sampling_method = gr.Radio(label='Choose latent sampling method', value="once", choices=['once', 'deterministic', 'random'])
- ti_stop.click(fn=lambda: shared.state.interrupt(), inputs=[], outputs=[])
+ with gr.Box():
+ gr.HTML('Training outputs
')
+ with FormRow():
+ ti_create_every = gr.Number(label='Create interim images', value=500, precision=0)
+ ti_save_every = gr.Number(label='Create interim embeddings', value=500, precision=0)
+ ti_save_image_with_stored_embedding = gr.Checkbox(label='Save images with embedding in PNG chunks', value=True)
+ ti_preview_from_txt2img = gr.Checkbox(label='Use current settings for previews', value=False)
+ ti_log_directory = gr.Textbox(label='Log directory', placeholder="Defaults to train/log/embedding", value="")
- ti_create.click(
- fn=modules.textual_inversion.ui.create_embedding,
- inputs=[
- ti_new_name,
- ti_init_text,
- ti_vectors,
- ti_overwrite,
- ],
- outputs=[
- ti_name,
- train_output,
- train_outcome,
- ]
- )
+ ti_stop.click(fn=lambda: shared.state.interrupt(), inputs=[], outputs=[])
- ti_train.click(
- fn=wrap_gradio_gpu_call(modules.textual_inversion.ui.train_embedding, extra_outputs=[gr.update()]),
- _js="startTrainMonitor",
- inputs=[
- dummy_component,
- ti_name,
- ti_learn_rate,
- ti_batch_size,
- ti_gradient_step,
- ti_dataset_directory,
- ti_log_directory,
- ti_width,
- ti_height,
- ti_varsize,
- ti_steps,
- ti_clip_grad_mode,
- ti_clip_grad_value,
- ti_shuffle,
- ti_tag_drop_out,
- ti_latent_sampling_method,
- ti_use_weight,
- ti_create_every,
- ti_save_every,
- ti_template,
- ti_save_image_with_stored_embedding,
- ti_preview_from_txt2img,
- *txt2img_preview_params,
- ],
- outputs=[
- train_output,
- train_outcome,
- ]
- )
+ ti_create.click(
+ fn=modules.textual_inversion.ui.create_embedding,
+ inputs=[
+ ti_new_name,
+ ti_init_text,
+ ti_vectors,
+ ti_overwrite,
+ ],
+ outputs=[
+ ti_name,
+ train_output,
+ train_outcome,
+ ]
+ )
+
+ ti_train.click(
+ fn=wrap_gradio_gpu_call(modules.textual_inversion.ui.train_embedding, extra_outputs=[gr.update()]),
+ _js="startTrainMonitor",
+ inputs=[
+ dummy_component,
+ ti_name,
+ ti_learn_rate,
+ ti_batch_size,
+ ti_gradient_step,
+ ti_dataset_directory,
+ ti_log_directory,
+ ti_width,
+ ti_height,
+ ti_varsize,
+ ti_steps,
+ ti_clip_grad_mode,
+ ti_clip_grad_value,
+ ti_shuffle,
+ ti_tag_drop_out,
+ ti_latent_sampling_method,
+ ti_use_weight,
+ ti_create_every,
+ ti_save_every,
+ ti_template,
+ ti_save_image_with_stored_embedding,
+ ti_preview_from_txt2img,
+ *txt2img_preview_params,
+ ],
+ outputs=[
+ train_output,
+ train_outcome,
+ ]
+ )
### train hypernetwork tab
- with gr.Tab(label="Train hypernetwork", id="train_hypernetwork_tab") as tab_hn:
- tab_hn.select(fn=lambda: train_tab_change('hn'), inputs=[], outputs=[action_pp, action_ti, action_hn])
- gr.HTML('Select existing hypernetwork to continue training or create a new one
')
- with FormRow():
- with gr.Column():
+ if shared.backend == shared.Backend.ORIGINAL:
+ from modules import sd_hijack
+ with gr.Tab(label="Train hypernetwork", id="train_hypernetwork_tab") as tab_hn:
+ tab_hn.select(fn=lambda: train_tab_change('hn'), inputs=[], outputs=[action_pp, action_ti, action_hn])
+ gr.HTML('Select existing hypernetwork to continue training or create a new one
')
+ with FormRow():
+ with gr.Column():
+ with FormRow():
+ hn_name = gr.Dropdown(label='Hypernetwork', choices=sorted(shared.hypernetworks))
+ create_refresh_button(hn_name, shared.reload_hypernetworks, lambda: {"choices": sorted(shared.hypernetworks)}, "refresh_train_hypernetwork_name")
+ with gr.Column():
+ hn_new_name = gr.Textbox(label="Name")
+ hn_new_sizes = gr.CheckboxGroup(label="Modules", value=["768", "320", "640", "1280"], choices=["768", "1024", "320", "640", "1280"])
+ hn_new_layer_structure = gr.Textbox("1, 2, 1", label="Enter hypernetwork layer structure", placeholder="1st and last digit must be 1. ex:'1, 2, 1'")
+ with gr.Row():
+ hn_new_activation_func = gr.Dropdown(value="linear", label="Select activation function of hypernetwork", choices=modules.hypernetworks.ui.keys)
+ hn_new_initialization_option = gr.Dropdown(value = "Normal", label="Select Layer weights initialization", choices=["Normal", "KaimingUniform", "KaimingNormal", "XavierUniform", "XavierNormal"])
+ hn_new_add_layer_norm = gr.Checkbox(label="Add layer normalization")
+ hn_new_use_dropout = gr.Checkbox(label="Use dropout")
+ hn_new_dropout_structure = gr.Textbox("0, 0, 0", label="Enter hypernetwork Dropout structure", placeholder="1st and last digit must be 0 and values should be between 0 and 1. ex:'0, 0.01, 0'")
+ hn_overwrite = gr.Checkbox(value=False, label="Overwrite Old Hypernetwork")
+ with gr.Row():
+ hn_create = gr.Button(value="Create hypernetwork", variant='secondary')
+
+ with gr.Box():
+ gr.HTML('Training parameters
')
+ hn_learn_rate = gr.Textbox(label='Hypernetwork Learning rate', placeholder="Hypernetwork Learning rate", value="0.00001")
with FormRow():
- hn_name = gr.Dropdown(label='Hypernetwork', choices=sorted(shared.hypernetworks))
- create_refresh_button(hn_name, shared.reload_hypernetworks, lambda: {"choices": sorted(shared.hypernetworks)}, "refresh_train_hypernetwork_name")
- with gr.Column():
- hn_new_name = gr.Textbox(label="Name")
- hn_new_sizes = gr.CheckboxGroup(label="Modules", value=["768", "320", "640", "1280"], choices=["768", "1024", "320", "640", "1280"])
- hn_new_layer_structure = gr.Textbox("1, 2, 1", label="Enter hypernetwork layer structure", placeholder="1st and last digit must be 1. ex:'1, 2, 1'")
- with gr.Row():
- hn_new_activation_func = gr.Dropdown(value="linear", label="Select activation function of hypernetwork", choices=modules.hypernetworks.ui.keys)
- hn_new_initialization_option = gr.Dropdown(value = "Normal", label="Select Layer weights initialization", choices=["Normal", "KaimingUniform", "KaimingNormal", "XavierUniform", "XavierNormal"])
- hn_new_add_layer_norm = gr.Checkbox(label="Add layer normalization")
- hn_new_use_dropout = gr.Checkbox(label="Use dropout")
- hn_new_dropout_structure = gr.Textbox("0, 0, 0", label="Enter hypernetwork Dropout structure", placeholder="1st and last digit must be 0 and values should be between 0 and 1. ex:'0, 0.01, 0'")
- hn_overwrite = gr.Checkbox(value=False, label="Overwrite Old Hypernetwork")
- with gr.Row():
- hn_create = gr.Button(value="Create hypernetwork", variant='secondary')
+ hn_clip_grad_mode = gr.Dropdown(value="disabled", label="Gradient Clipping", choices=["disabled", "value", "norm"])
+ hn_clip_grad_value = gr.Number(label="Gradient clip value", value=0.1)
+ hn_batch_size = gr.Number(label='Batch size', value=1, precision=0)
+ hn_gradient_step = gr.Number(label='Gradient accumulation steps', value=1, precision=0)
+ hn_steps = gr.Number(label='Max steps', value=1000, precision=0)
- with gr.Box():
- gr.HTML('Training parameters
')
- hn_learn_rate = gr.Textbox(label='Hypernetwork Learning rate', placeholder="Hypernetwork Learning rate", value="0.00001")
- with FormRow():
- hn_clip_grad_mode = gr.Dropdown(value="disabled", label="Gradient Clipping", choices=["disabled", "value", "norm"])
- hn_clip_grad_value = gr.Number(label="Gradient clip value", value=0.1)
- hn_batch_size = gr.Number(label='Batch size', value=1, precision=0)
- hn_gradient_step = gr.Number(label='Gradient accumulation steps', value=1, precision=0)
- hn_steps = gr.Number(label='Max steps', value=1000, precision=0)
+ with gr.Box():
+ gr.HTML('Training images
')
+ hn_dataset_directory = gr.Textbox(label='Dataset directory', placeholder="Path to directory with input images")
+ with FormRow():
+ hn_varsize = gr.Checkbox(label="Do not resize images", value=False)
+ hn_width = gr.Slider(minimum=64, maximum=2048, step=8, label="Width", value=512)
+ hn_height = gr.Slider(minimum=64, maximum=2048, step=8, label="Height", value=512)
+ hn_use_weight = gr.Checkbox(label="Use PNG alpha channel as loss weight", value=False)
- with gr.Box():
- gr.HTML('Training images
')
- hn_dataset_directory = gr.Textbox(label='Dataset directory', placeholder="Path to directory with input images")
- with FormRow():
- hn_varsize = gr.Checkbox(label="Do not resize images", value=False)
- hn_width = gr.Slider(minimum=64, maximum=2048, step=8, label="Width", value=512)
- hn_height = gr.Slider(minimum=64, maximum=2048, step=8, label="Height", value=512)
- hn_use_weight = gr.Checkbox(label="Use PNG alpha channel as loss weight", value=False)
+ with gr.Box():
+ gr.HTML('Dataset processing
')
+ with FormRow():
+ hn_template = gr.Dropdown(label='Prompt template', value="style_filewords.txt", choices=get_textual_inversion_template_names())
+ create_refresh_button(hn_template, textual_inversion.list_textual_inversion_templates, lambda: {"choices": get_textual_inversion_template_names()}, "refrsh_train_template_file")
+ hn_shuffle_tags = gr.Checkbox(label="Shuffle tags by ',' when creating prompts.", value=False)
+ hn_tag_drop_out = gr.Slider(minimum=0, maximum=1, step=0.1, label="Drop out tags when creating prompts", value=0)
+ hn_latent_sampling_method = gr.Radio(label='Choose latent sampling method', value="once", choices=['once', 'deterministic', 'random'])
- with gr.Box():
- gr.HTML('Dataset processing
')
- with FormRow():
- hn_template = gr.Dropdown(label='Prompt template', value="style_filewords.txt", choices=get_textual_inversion_template_names())
- create_refresh_button(hn_template, textual_inversion.list_textual_inversion_templates, lambda: {"choices": get_textual_inversion_template_names()}, "refrsh_train_template_file")
- hn_shuffle_tags = gr.Checkbox(label="Shuffle tags by ',' when creating prompts.", value=False)
- hn_tag_drop_out = gr.Slider(minimum=0, maximum=1, step=0.1, label="Drop out tags when creating prompts", value=0)
- hn_latent_sampling_method = gr.Radio(label='Choose latent sampling method', value="once", choices=['once', 'deterministic', 'random'])
+ with gr.Box():
+ gr.HTML('Training outputs
')
+ with FormRow():
+ hn_create_every = gr.Number(label='Create interim images', value=500, precision=0)
+ hn_save_every = gr.Number(label='Create interim hypernetworks', value=500, precision=0)
+ hn_preview_from_txt2img = gr.Checkbox(label='Use current settings for previews', value=False)
+ hn_log_directory = gr.Textbox(label='Log directory', placeholder="Path to directory where to write outputs", value=f"{os.path.join('cmd_opts.data_dir', 'train/log/embeddings')}")
- with gr.Box():
- gr.HTML('Training outputs
')
- with FormRow():
- hn_create_every = gr.Number(label='Create interim images', value=500, precision=0)
- hn_save_every = gr.Number(label='Create interim hypernetworks', value=500, precision=0)
- hn_preview_from_txt2img = gr.Checkbox(label='Use current settings for previews', value=False)
- hn_log_directory = gr.Textbox(label='Log directory', placeholder="Path to directory where to write outputs", value=f"{os.path.join('cmd_opts.data_dir', 'train/log/embeddings')}")
+ hn_stop.click(fn=lambda: shared.state.interrupt(), inputs=[], outputs=[])
- hn_stop.click(fn=lambda: shared.state.interrupt(), inputs=[], outputs=[])
+ hn_create.click(
+ fn=modules.hypernetworks.ui.create_hypernetwork,
+ inputs=[
+ hn_new_name,
+ hn_new_sizes,
+ hn_overwrite,
+ hn_new_layer_structure,
+ hn_new_activation_func,
+ hn_new_initialization_option,
+ hn_new_add_layer_norm,
+ hn_new_use_dropout,
+ hn_new_dropout_structure
+ ],
+ outputs=[
+ hn_name,
+ train_output,
+ train_outcome,
+ ]
+ )
- hn_create.click(
- fn=modules.hypernetworks.ui.create_hypernetwork,
- inputs=[
- hn_new_name,
- hn_new_sizes,
- hn_overwrite,
- hn_new_layer_structure,
- hn_new_activation_func,
- hn_new_initialization_option,
- hn_new_add_layer_norm,
- hn_new_use_dropout,
- hn_new_dropout_structure
- ],
- outputs=[
- hn_name,
- train_output,
- train_outcome,
- ]
- )
-
- hn_train.click(
- fn=wrap_gradio_gpu_call(modules.hypernetworks.ui.train_hypernetwork, extra_outputs=[gr.update()]),
- _js="startTrainMonitor",
- inputs=[
- dummy_component,
- hn_name,
- hn_learn_rate,
- hn_batch_size,
- hn_gradient_step,
- hn_dataset_directory,
- hn_log_directory,
- hn_width,
- hn_height,
- hn_varsize,
- hn_steps,
- hn_clip_grad_mode,
- hn_clip_grad_value,
- hn_shuffle_tags,
- hn_tag_drop_out,
- hn_latent_sampling_method,
- hn_use_weight,
- hn_create_every,
- hn_save_every,
- hn_template,
- hn_preview_from_txt2img,
- *txt2img_preview_params,
- ],
- outputs=[
- train_output,
- train_outcome,
- ]
- )
+ hn_train.click(
+ fn=wrap_gradio_gpu_call(modules.hypernetworks.ui.train_hypernetwork, extra_outputs=[gr.update()]),
+ _js="startTrainMonitor",
+ inputs=[
+ dummy_component,
+ hn_name,
+ hn_learn_rate,
+ hn_batch_size,
+ hn_gradient_step,
+ hn_dataset_directory,
+ hn_log_directory,
+ hn_width,
+ hn_height,
+ hn_varsize,
+ hn_steps,
+ hn_clip_grad_mode,
+ hn_clip_grad_value,
+ hn_shuffle_tags,
+ hn_tag_drop_out,
+ hn_latent_sampling_method,
+ hn_use_weight,
+ hn_create_every,
+ hn_save_every,
+ hn_template,
+ hn_preview_from_txt2img,
+ *txt2img_preview_params,
+ ],
+ outputs=[
+ train_output,
+ train_outcome,
+ ]
+ )
params = script_callbacks.UiTrainTabParams(txt2img_preview_params)
script_callbacks.ui_train_tabs_callback(params)
diff --git a/modules/ui_txt2img.py b/modules/ui_txt2img.py
index d03010fcf..e2d3e3a66 100644
--- a/modules/ui_txt2img.py
+++ b/modules/ui_txt2img.py
@@ -29,7 +29,7 @@ def create_ui():
with FormRow(variant='compact', elem_id="txt2img_extra_networks", visible=False) as extra_networks_ui:
from modules import ui_extra_networks
extra_networks_ui = ui_extra_networks.create_ui(extra_networks_ui, txt2img_extra_networks_button, 'txt2img', skip_indexing=shared.opts.extra_network_skip_indexing)
- timer.startup.record('ui-extra-networks')
+ timer.startup.record('ui-en')
with gr.Row(elem_id="txt2img_interface", equal_height=False):
with gr.Column(variant='compact', elem_id="txt2img_settings"):
diff --git a/webui.py b/webui.py
index 8bf274e4a..efd0d6038 100644
--- a/webui.py
+++ b/webui.py
@@ -122,7 +122,7 @@ def initialize():
ui_extra_networks.register_pages()
extra_networks.initialize()
extra_networks.register_default_extra_networks()
- timer.startup.record("extra-networks")
+ timer.startup.record("networks")
if cmd_opts.tls_keyfile is not None and cmd_opts.tls_certfile is not None:
try:
@@ -311,7 +311,6 @@ def webui(restart=False):
if cmd_opts.profile:
for k, v in modules.script_callbacks.callback_map.items():
shared.log.debug(f'Registered callbacks: {k}={len(v)} {[c.script for c in v]}')
- log.info(f"Startup time: {timer.startup.summary()}")
debug = log.trace if os.environ.get('SD_SCRIPT_DEBUG', None) is not None else lambda *args, **kwargs: None
debug('Trace: SCRIPTS')
for m in modules.scripts.scripts_data:
@@ -319,8 +318,9 @@ def webui(restart=False):
debug('Loaded postprocessing scripts:')
for m in modules.scripts.postprocessing_scripts_data:
debug(f' {m}')
- timer.startup.reset()
modules.script_callbacks.print_timers()
+ log.info(f"Startup time: {timer.startup.summary()}")
+ timer.startup.reset()
if not restart:
# override all loggers to use the same handlers as the main logger