From 12c4d5c6b5bf9dd50d0601c36af4f99b65316d58 Mon Sep 17 00:00:00 2001
From: AUTOMATIC <16777216c@gmail.com>
Date: Fri, 7 Oct 2022 23:22:22 +0300
Subject: hypernetwork training mk1
---
modules/ui.py | 58 +++++++++++++++++++++++++++++++++++++++++++++++++++-------
1 file changed, 51 insertions(+), 7 deletions(-)
(limited to 'modules/ui.py')
diff --git a/modules/ui.py b/modules/ui.py
index 4f18126f..051908c1 100644
--- a/modules/ui.py
+++ b/modules/ui.py
@@ -37,6 +37,7 @@ import modules.generation_parameters_copypaste
from modules import prompt_parser
from modules.images import save_image
import modules.textual_inversion.ui
+import modules.hypernetwork.ui
# this is a fix for Windows users. Without it, javascript files will be served with text/html content-type and the bowser will not show any UI
mimetypes.init()
@@ -965,6 +966,18 @@ def create_ui(wrap_gradio_gpu_call):
with gr.Column():
create_embedding = gr.Button(value="Create", variant='primary')
+ with gr.Group():
+ gr.HTML(value="Create a new hypernetwork
")
+
+ new_hypernetwork_name = gr.Textbox(label="Name")
+
+ with gr.Row():
+ with gr.Column(scale=3):
+ gr.HTML(value="")
+
+ with gr.Column():
+ create_hypernetwork = gr.Button(value="Create", variant='primary')
+
with gr.Group():
gr.HTML(value="Preprocess images
")
@@ -986,6 +999,7 @@ def create_ui(wrap_gradio_gpu_call):
with gr.Group():
gr.HTML(value="Train an embedding; must specify a directory with a set of 512x512 images
")
train_embedding_name = gr.Dropdown(label='Embedding', choices=sorted(sd_hijack.model_hijack.embedding_db.word_embeddings.keys()))
+ train_hypernetwork_name = gr.Dropdown(label='Hypernetwork', choices=[x for x in shared.hypernetworks.keys()])
learn_rate = gr.Number(label='Learning rate', value=5.0e-03)
dataset_directory = gr.Textbox(label='Dataset directory', placeholder="Path to directory with input images")
log_directory = gr.Textbox(label='Log directory', placeholder="Path to directory where to write outputs", value="textual_inversion")
@@ -993,15 +1007,12 @@ def create_ui(wrap_gradio_gpu_call):
steps = gr.Number(label='Max steps', value=100000, precision=0)
create_image_every = gr.Number(label='Save an image to log directory every N steps, 0 to disable', value=500, precision=0)
save_embedding_every = gr.Number(label='Save a copy of embedding to log directory every N steps, 0 to disable', value=500, precision=0)
+ preview_image_prompt = gr.Textbox(label='Preview prompt', value="")
with gr.Row():
- with gr.Column(scale=2):
- gr.HTML(value="")
-
- with gr.Column():
- with gr.Row():
- interrupt_training = gr.Button(value="Interrupt")
- train_embedding = gr.Button(value="Train", variant='primary')
+ interrupt_training = gr.Button(value="Interrupt")
+ train_hypernetwork = gr.Button(value="Train Hypernetwork", variant='primary')
+ train_embedding = gr.Button(value="Train Embedding", variant='primary')
with gr.Column():
progressbar = gr.HTML(elem_id="ti_progressbar")
@@ -1027,6 +1038,18 @@ def create_ui(wrap_gradio_gpu_call):
]
)
+ create_hypernetwork.click(
+ fn=modules.hypernetwork.ui.create_hypernetwork,
+ inputs=[
+ new_hypernetwork_name,
+ ],
+ outputs=[
+ train_hypernetwork_name,
+ ti_output,
+ ti_outcome,
+ ]
+ )
+
run_preprocess.click(
fn=wrap_gradio_gpu_call(modules.textual_inversion.ui.preprocess, extra_outputs=[gr.update()]),
_js="start_training_textual_inversion",
@@ -1062,12 +1085,33 @@ def create_ui(wrap_gradio_gpu_call):
]
)
+ train_hypernetwork.click(
+ fn=wrap_gradio_gpu_call(modules.hypernetwork.ui.train_hypernetwork, extra_outputs=[gr.update()]),
+ _js="start_training_textual_inversion",
+ inputs=[
+ train_hypernetwork_name,
+ learn_rate,
+ dataset_directory,
+ log_directory,
+ steps,
+ create_image_every,
+ save_embedding_every,
+ template_file,
+ preview_image_prompt,
+ ],
+ outputs=[
+ ti_output,
+ ti_outcome,
+ ]
+ )
+
interrupt_training.click(
fn=lambda: shared.state.interrupt(),
inputs=[],
outputs=[],
)
+
def create_setting_component(key):
def fun():
return opts.data[key] if key in opts.data else opts.data_labels[key].default
--
cgit v1.2.3
From ea00c1624bbb0dcb5be07f59c9509061baddf5b1 Mon Sep 17 00:00:00 2001
From: alg-wiki
Date: Mon, 10 Oct 2022 17:07:46 +0900
Subject: Textual Inversion: Added custom training image size and number of
repeats per input image in a single epoch
---
modules/textual_inversion/dataset.py | 6 +++---
modules/textual_inversion/preprocess.py | 4 ++--
modules/textual_inversion/textual_inversion.py | 15 ++++++++++++---
modules/ui.py | 8 +++++++-
4 files changed, 24 insertions(+), 9 deletions(-)
(limited to 'modules/ui.py')
diff --git a/modules/textual_inversion/dataset.py b/modules/textual_inversion/dataset.py
index 7c44ea5b..acc4ce59 100644
--- a/modules/textual_inversion/dataset.py
+++ b/modules/textual_inversion/dataset.py
@@ -15,13 +15,13 @@ re_tag = re.compile(r"[a-zA-Z][_\w\d()]+")
class PersonalizedBase(Dataset):
- def __init__(self, data_root, size=None, repeats=100, flip_p=0.5, placeholder_token="*", width=512, height=512, model=None, device=None, template_file=None):
+ def __init__(self, data_root, size, repeats, flip_p=0.5, placeholder_token="*", model=None, device=None, template_file=None):
self.placeholder_token = placeholder_token
self.size = size
- self.width = width
- self.height = height
+ self.width = size
+ self.height = size
self.flip = transforms.RandomHorizontalFlip(p=flip_p)
self.dataset = []
diff --git a/modules/textual_inversion/preprocess.py b/modules/textual_inversion/preprocess.py
index f1c002a2..b3de6fd7 100644
--- a/modules/textual_inversion/preprocess.py
+++ b/modules/textual_inversion/preprocess.py
@@ -7,8 +7,8 @@ import tqdm
from modules import shared, images
-def preprocess(process_src, process_dst, process_flip, process_split, process_caption):
- size = 512
+def preprocess(process_src, process_dst, process_size, process_flip, process_split, process_caption):
+ size = process_size
src = os.path.abspath(process_src)
dst = os.path.abspath(process_dst)
diff --git a/modules/textual_inversion/textual_inversion.py b/modules/textual_inversion/textual_inversion.py
index cd9f3498..e34dc2e8 100644
--- a/modules/textual_inversion/textual_inversion.py
+++ b/modules/textual_inversion/textual_inversion.py
@@ -6,6 +6,7 @@ import torch
import tqdm
import html
import datetime
+import math
from modules import shared, devices, sd_hijack, processing, sd_models
@@ -156,7 +157,7 @@ def create_embedding(name, num_vectors_per_token, init_text='*'):
return fn
-def train_embedding(embedding_name, learn_rate, data_root, log_directory, steps, create_image_every, save_embedding_every, template_file):
+def train_embedding(embedding_name, learn_rate, data_root, log_directory, training_size, steps, num_repeats, create_image_every, save_embedding_every, template_file):
assert embedding_name, 'embedding not selected'
shared.state.textinfo = "Initializing textual inversion training..."
@@ -182,7 +183,7 @@ def train_embedding(embedding_name, learn_rate, data_root, log_directory, steps,
shared.state.textinfo = f"Preparing dataset from {html.escape(data_root)}..."
with torch.autocast("cuda"):
- ds = modules.textual_inversion.dataset.PersonalizedBase(data_root=data_root, size=512, placeholder_token=embedding_name, model=shared.sd_model, device=devices.device, template_file=template_file)
+ ds = modules.textual_inversion.dataset.PersonalizedBase(data_root=data_root, size=training_size, repeats=num_repeats, placeholder_token=embedding_name, model=shared.sd_model, device=devices.device, template_file=template_file)
hijack = sd_hijack.model_hijack
@@ -200,6 +201,9 @@ def train_embedding(embedding_name, learn_rate, data_root, log_directory, steps,
if ititial_step > steps:
return embedding, filename
+ tr_img_len = len([os.path.join(data_root, file_path) for file_path in os.listdir(data_root)])
+ epoch_len = (tr_img_len * num_repeats) + tr_img_len
+
pbar = tqdm.tqdm(enumerate(ds), total=steps-ititial_step)
for i, (x, text) in pbar:
embedding.step = i + ititial_step
@@ -223,7 +227,10 @@ def train_embedding(embedding_name, learn_rate, data_root, log_directory, steps,
loss.backward()
optimizer.step()
- pbar.set_description(f"loss: {losses.mean():.7f}")
+ epoch_num = math.floor(embedding.step / epoch_len)
+ epoch_step = embedding.step - (epoch_num * epoch_len)
+
+ pbar.set_description(f"[Epoch {epoch_num}: {epoch_step}/{epoch_len}]loss: {losses.mean():.7f}")
if embedding.step > 0 and embedding_dir is not None and embedding.step % save_embedding_every == 0:
last_saved_file = os.path.join(embedding_dir, f'{embedding_name}-{embedding.step}.pt')
@@ -236,6 +243,8 @@ def train_embedding(embedding_name, learn_rate, data_root, log_directory, steps,
sd_model=shared.sd_model,
prompt=text,
steps=20,
+ height=training_size,
+ width=training_size,
do_not_save_grid=True,
do_not_save_samples=True,
)
diff --git a/modules/ui.py b/modules/ui.py
index 2231a8ed..f821fd8d 100644
--- a/modules/ui.py
+++ b/modules/ui.py
@@ -1029,6 +1029,7 @@ def create_ui(wrap_gradio_gpu_call):
process_src = gr.Textbox(label='Source directory')
process_dst = gr.Textbox(label='Destination directory')
+ process_size = gr.Slider(minimum=64, maximum=2048, step=64, label="Size (width and height)", value=512)
with gr.Row():
process_flip = gr.Checkbox(label='Create flipped copies')
@@ -1043,13 +1044,15 @@ def create_ui(wrap_gradio_gpu_call):
run_preprocess = gr.Button(value="Preprocess", variant='primary')
with gr.Group():
- gr.HTML(value="Train an embedding; must specify a directory with a set of 512x512 images
")
+ gr.HTML(value="Train an embedding; must specify a directory with a set of 1:1 ratio images
")
train_embedding_name = gr.Dropdown(label='Embedding', choices=sorted(sd_hijack.model_hijack.embedding_db.word_embeddings.keys()))
learn_rate = gr.Number(label='Learning rate', value=5.0e-03)
dataset_directory = gr.Textbox(label='Dataset directory', placeholder="Path to directory with input images")
log_directory = gr.Textbox(label='Log directory', placeholder="Path to directory where to write outputs", value="textual_inversion")
template_file = gr.Textbox(label='Prompt template file', value=os.path.join(script_path, "textual_inversion_templates", "style_filewords.txt"))
+ training_size = gr.Slider(minimum=64, maximum=2048, step=64, label="Size (width and height)", value=512)
steps = gr.Number(label='Max steps', value=100000, precision=0)
+ num_repeats = gr.Number(label='Number of repeats for a single input image per epoch', value=100, precision=0)
create_image_every = gr.Number(label='Save an image to log directory every N steps, 0 to disable', value=500, precision=0)
save_embedding_every = gr.Number(label='Save a copy of embedding to log directory every N steps, 0 to disable', value=500, precision=0)
@@ -1092,6 +1095,7 @@ def create_ui(wrap_gradio_gpu_call):
inputs=[
process_src,
process_dst,
+ process_size,
process_flip,
process_split,
process_caption,
@@ -1110,7 +1114,9 @@ def create_ui(wrap_gradio_gpu_call):
learn_rate,
dataset_directory,
log_directory,
+ training_size,
steps,
+ num_repeats,
create_image_every,
save_embedding_every,
template_file,
--
cgit v1.2.3
From 7a20f914eddfdf09c0ccced157ec108205bc3d0f Mon Sep 17 00:00:00 2001
From: alg-wiki
Date: Mon, 10 Oct 2022 22:35:35 +0900
Subject: Custom Width and Height
---
modules/textual_inversion/dataset.py | 7 +++----
modules/textual_inversion/preprocess.py | 19 ++++++++++---------
modules/textual_inversion/textual_inversion.py | 11 +++++------
modules/ui.py | 12 ++++++++----
4 files changed, 26 insertions(+), 23 deletions(-)
(limited to 'modules/ui.py')
diff --git a/modules/textual_inversion/dataset.py b/modules/textual_inversion/dataset.py
index acc4ce59..bcf772d2 100644
--- a/modules/textual_inversion/dataset.py
+++ b/modules/textual_inversion/dataset.py
@@ -15,13 +15,12 @@ re_tag = re.compile(r"[a-zA-Z][_\w\d()]+")
class PersonalizedBase(Dataset):
- def __init__(self, data_root, size, repeats, flip_p=0.5, placeholder_token="*", model=None, device=None, template_file=None):
+ def __init__(self, data_root, width, height, repeats, flip_p=0.5, placeholder_token="*", model=None, device=None, template_file=None):
self.placeholder_token = placeholder_token
- self.size = size
- self.width = size
- self.height = size
+ self.width = width
+ self.height = height
self.flip = transforms.RandomHorizontalFlip(p=flip_p)
self.dataset = []
diff --git a/modules/textual_inversion/preprocess.py b/modules/textual_inversion/preprocess.py
index b3de6fd7..d7efdef2 100644
--- a/modules/textual_inversion/preprocess.py
+++ b/modules/textual_inversion/preprocess.py
@@ -7,8 +7,9 @@ import tqdm
from modules import shared, images
-def preprocess(process_src, process_dst, process_size, process_flip, process_split, process_caption):
- size = process_size
+def preprocess(process_src, process_dst, process_width, process_height, process_flip, process_split, process_caption):
+ width = process_width
+ height = process_height
src = os.path.abspath(process_src)
dst = os.path.abspath(process_dst)
@@ -55,23 +56,23 @@ def preprocess(process_src, process_dst, process_size, process_flip, process_spl
is_wide = ratio < 1 / 1.35
if process_split and is_tall:
- img = img.resize((size, size * img.height // img.width))
+ img = img.resize((width, height * img.height // img.width))
- top = img.crop((0, 0, size, size))
+ top = img.crop((0, 0, width, height))
save_pic(top, index)
- bot = img.crop((0, img.height - size, size, img.height))
+ bot = img.crop((0, img.height - height, width, img.height))
save_pic(bot, index)
elif process_split and is_wide:
- img = img.resize((size * img.width // img.height, size))
+ img = img.resize((width * img.width // img.height, height))
- left = img.crop((0, 0, size, size))
+ left = img.crop((0, 0, width, height))
save_pic(left, index)
- right = img.crop((img.width - size, 0, img.width, size))
+ right = img.crop((img.width - width, 0, img.width, height))
save_pic(right, index)
else:
- img = images.resize_image(1, img, size, size)
+ img = images.resize_image(1, img, width, height)
save_pic(img, index)
shared.state.nextjob()
diff --git a/modules/textual_inversion/textual_inversion.py b/modules/textual_inversion/textual_inversion.py
index 769682ea..5965c5a0 100644
--- a/modules/textual_inversion/textual_inversion.py
+++ b/modules/textual_inversion/textual_inversion.py
@@ -6,7 +6,6 @@ import torch
import tqdm
import html
import datetime
-import math
from modules import shared, devices, sd_hijack, processing, sd_models
@@ -157,7 +156,7 @@ def create_embedding(name, num_vectors_per_token, init_text='*'):
return fn
-def train_embedding(embedding_name, learn_rate, data_root, log_directory, training_size, steps, num_repeats, create_image_every, save_embedding_every, template_file):
+def train_embedding(embedding_name, learn_rate, data_root, log_directory, training_width, training_height, steps, num_repeats, create_image_every, save_embedding_every, template_file):
assert embedding_name, 'embedding not selected'
shared.state.textinfo = "Initializing textual inversion training..."
@@ -183,7 +182,7 @@ def train_embedding(embedding_name, learn_rate, data_root, log_directory, traini
shared.state.textinfo = f"Preparing dataset from {html.escape(data_root)}..."
with torch.autocast("cuda"):
- ds = modules.textual_inversion.dataset.PersonalizedBase(data_root=data_root, size=training_size, repeats=num_repeats, placeholder_token=embedding_name, model=shared.sd_model, device=devices.device, template_file=template_file)
+ ds = modules.textual_inversion.dataset.PersonalizedBase(data_root=data_root, width=training_width, height=training_height, repeats=num_repeats, placeholder_token=embedding_name, model=shared.sd_model, device=devices.device, template_file=template_file)
hijack = sd_hijack.model_hijack
@@ -227,7 +226,7 @@ def train_embedding(embedding_name, learn_rate, data_root, log_directory, traini
loss.backward()
optimizer.step()
- epoch_num = math.floor(embedding.step / epoch_len)
+ epoch_num = embedding.step // epoch_len
epoch_step = embedding.step - (epoch_num * epoch_len) + 1
pbar.set_description(f"[Epoch {epoch_num}: {epoch_step}/{epoch_len}]loss: {losses.mean():.7f}")
@@ -243,8 +242,8 @@ def train_embedding(embedding_name, learn_rate, data_root, log_directory, traini
sd_model=shared.sd_model,
prompt=text,
steps=20,
- height=training_size,
- width=training_size,
+ height=training_height,
+ width=training_width,
do_not_save_grid=True,
do_not_save_samples=True,
)
diff --git a/modules/ui.py b/modules/ui.py
index f821fd8d..8c06ad7c 100644
--- a/modules/ui.py
+++ b/modules/ui.py
@@ -1029,7 +1029,8 @@ def create_ui(wrap_gradio_gpu_call):
process_src = gr.Textbox(label='Source directory')
process_dst = gr.Textbox(label='Destination directory')
- process_size = gr.Slider(minimum=64, maximum=2048, step=64, label="Size (width and height)", value=512)
+ process_width = gr.Slider(minimum=64, maximum=2048, step=64, label="Width", value=512)
+ process_height = gr.Slider(minimum=64, maximum=2048, step=64, label="Height", value=512)
with gr.Row():
process_flip = gr.Checkbox(label='Create flipped copies')
@@ -1050,7 +1051,8 @@ def create_ui(wrap_gradio_gpu_call):
dataset_directory = gr.Textbox(label='Dataset directory', placeholder="Path to directory with input images")
log_directory = gr.Textbox(label='Log directory', placeholder="Path to directory where to write outputs", value="textual_inversion")
template_file = gr.Textbox(label='Prompt template file', value=os.path.join(script_path, "textual_inversion_templates", "style_filewords.txt"))
- training_size = gr.Slider(minimum=64, maximum=2048, step=64, label="Size (width and height)", value=512)
+ training_width = gr.Slider(minimum=64, maximum=2048, step=64, label="Width", value=512)
+ training_height = gr.Slider(minimum=64, maximum=2048, step=64, label="Height", value=512)
steps = gr.Number(label='Max steps', value=100000, precision=0)
num_repeats = gr.Number(label='Number of repeats for a single input image per epoch', value=100, precision=0)
create_image_every = gr.Number(label='Save an image to log directory every N steps, 0 to disable', value=500, precision=0)
@@ -1095,7 +1097,8 @@ def create_ui(wrap_gradio_gpu_call):
inputs=[
process_src,
process_dst,
- process_size,
+ process_width,
+ process_height,
process_flip,
process_split,
process_caption,
@@ -1114,7 +1117,8 @@ def create_ui(wrap_gradio_gpu_call):
learn_rate,
dataset_directory,
log_directory,
- training_size,
+ training_width,
+ training_height,
steps,
num_repeats,
create_image_every,
--
cgit v1.2.3
From f347ddfd808c56bb1bacdec0c4bedf826ff85cd8 Mon Sep 17 00:00:00 2001
From: RW21
Date: Mon, 10 Oct 2022 10:44:11 +0900
Subject: Remove max_batch_count from ui.py
---
modules/ui.py | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
(limited to 'modules/ui.py')
diff --git a/modules/ui.py b/modules/ui.py
index 8c06ad7c..8ba84911 100644
--- a/modules/ui.py
+++ b/modules/ui.py
@@ -524,7 +524,7 @@ def create_ui(wrap_gradio_gpu_call):
denoising_strength = gr.Slider(minimum=0.0, maximum=1.0, step=0.01, label='Denoising strength', value=0.7)
with gr.Row():
- batch_count = gr.Slider(minimum=1, maximum=cmd_opts.max_batch_count, step=1, label='Batch count', value=1)
+ batch_count = gr.Slider(minimum=1, step=1, label='Batch count', value=1)
batch_size = gr.Slider(minimum=1, maximum=8, step=1, label='Batch size', value=1)
cfg_scale = gr.Slider(minimum=1.0, maximum=30.0, step=0.5, label='CFG Scale', value=7.0)
@@ -710,7 +710,7 @@ def create_ui(wrap_gradio_gpu_call):
tiling = gr.Checkbox(label='Tiling', value=False)
with gr.Row():
- batch_count = gr.Slider(minimum=1, maximum=cmd_opts.max_batch_count, step=1, label='Batch count', value=1)
+ batch_count = gr.Slider(minimum=1, step=1, label='Batch count', value=1)
batch_size = gr.Slider(minimum=1, maximum=8, step=1, label='Batch size', value=1)
with gr.Group():
--
cgit v1.2.3
From 9d33baba587637815d818e5e641d8f8b74c4900d Mon Sep 17 00:00:00 2001
From: Vladimir Repin <32306715+mezotaken@users.noreply.github.com>
Date: Mon, 10 Oct 2022 18:46:48 +0300
Subject: Always show previous mask and fix extras_send dest
---
modules/ui.py | 2 +-
style.css | 7 +++++++
2 files changed, 8 insertions(+), 1 deletion(-)
(limited to 'modules/ui.py')
diff --git a/modules/ui.py b/modules/ui.py
index 8ba84911..e8039d76 100644
--- a/modules/ui.py
+++ b/modules/ui.py
@@ -961,7 +961,7 @@ def create_ui(wrap_gradio_gpu_call):
extras_send_to_inpaint.click(
fn=lambda x: image_from_url_text(x),
- _js="extract_image_from_gallery_img2img",
+ _js="extract_image_from_gallery_inpaint",
inputs=[result_images],
outputs=[init_img_with_mask],
)
diff --git a/style.css b/style.css
index 04bb9576..00a3d07f 100644
--- a/style.css
+++ b/style.css
@@ -467,3 +467,10 @@ input[type="range"]{
max-width: 32em;
padding: 0;
}
+
+canvas[key="mask"] {
+ z-index: 12 !important;
+ filter: invert();
+ mix-blend-mode: multiply;
+ pointer-events: none;
+}
--
cgit v1.2.3
From 8b7d3f1bef47bbe048f644ed0d8dd3ad46554045 Mon Sep 17 00:00:00 2001
From: Jairo Correa
Date: Tue, 11 Oct 2022 02:22:46 -0300
Subject: Make the ctrl+enter shortcut use the generate button on the current
tab
---
modules/ui.py | 2 +-
script.js | 11 +++++++++--
2 files changed, 10 insertions(+), 3 deletions(-)
(limited to 'modules/ui.py')
diff --git a/modules/ui.py b/modules/ui.py
index e8039d76..cafda884 100644
--- a/modules/ui.py
+++ b/modules/ui.py
@@ -1331,7 +1331,7 @@ Requested path was: {f}
with gr.Tabs() as tabs:
for interface, label, ifid in interfaces:
- with gr.TabItem(label, id=ifid):
+ with gr.TabItem(label, id=ifid, elem_id='tab_' + ifid):
interface.render()
if os.path.exists(os.path.join(script_path, "notification.mp3")):
diff --git a/script.js b/script.js
index a92c0f77..9543cbe6 100644
--- a/script.js
+++ b/script.js
@@ -6,6 +6,10 @@ function get_uiCurrentTab() {
return gradioApp().querySelector('.tabs button:not(.border-transparent)')
}
+function get_uiCurrentTabContent() {
+ return gradioApp().querySelector('.tabitem[id^=tab_]:not([style*="display: none"])')
+}
+
uiUpdateCallbacks = []
uiTabChangeCallbacks = []
let uiCurrentTab = null
@@ -50,8 +54,11 @@ document.addEventListener("DOMContentLoaded", function() {
} else if (e.keyCode !== undefined) {
if((e.keyCode == 13 && (e.metaKey || e.ctrlKey))) handled = true;
}
- if (handled) {
- gradioApp().querySelector("#txt2img_generate").click();
+ if (handled) {
+ button = get_uiCurrentTabContent().querySelector('button[id$=_generate]');
+ if (button) {
+ button.click();
+ }
e.preventDefault();
}
})
--
cgit v1.2.3
From 8617396c6df71074c7fd3d39419802026874712a Mon Sep 17 00:00:00 2001
From: Kenneth
Date: Mon, 10 Oct 2022 17:23:07 -0600
Subject: Added slider for deepbooru score threshold in settings
---
modules/shared.py | 1 +
modules/ui.py | 2 +-
2 files changed, 2 insertions(+), 1 deletion(-)
(limited to 'modules/ui.py')
diff --git a/modules/shared.py b/modules/shared.py
index ecd15ef5..e0830e28 100644
--- a/modules/shared.py
+++ b/modules/shared.py
@@ -239,6 +239,7 @@ options_templates.update(options_section(('interrogate', "Interrogate Options"),
"interrogate_clip_min_length": OptionInfo(24, "Interrogate: minimum description length (excluding artists, etc..)", gr.Slider, {"minimum": 1, "maximum": 128, "step": 1}),
"interrogate_clip_max_length": OptionInfo(48, "Interrogate: maximum description length", gr.Slider, {"minimum": 1, "maximum": 256, "step": 1}),
"interrogate_clip_dict_limit": OptionInfo(1500, "Interrogate: maximum number of lines in text file (0 = No limit)"),
+ "interrogate_deepbooru_score_threshold": OptionInfo(0.5, "Interrogate: deepbooru score threshold", gr.Slider, {"minimum": 0, "maximum": 1, "step": 0.01}),
}))
options_templates.update(options_section(('ui', "User interface"), {
diff --git a/modules/ui.py b/modules/ui.py
index cafda884..ca3151c4 100644
--- a/modules/ui.py
+++ b/modules/ui.py
@@ -311,7 +311,7 @@ def interrogate(image):
def interrogate_deepbooru(image):
- prompt = get_deepbooru_tags(image)
+ prompt = get_deepbooru_tags(image, opts.interrogate_deepbooru_score_threshold)
return gr_show(True) if prompt is None else prompt
--
cgit v1.2.3
From 530103b586109c11fd068eb70ef09503ec6a4caf Mon Sep 17 00:00:00 2001
From: AUTOMATIC <16777216c@gmail.com>
Date: Tue, 11 Oct 2022 14:53:02 +0300
Subject: fixes related to merge
---
modules/hypernetwork.py | 103 -------------------------
modules/hypernetwork/hypernetwork.py | 74 +++++++++++-------
modules/hypernetwork/ui.py | 10 +--
modules/sd_hijack_optimizations.py | 3 +-
modules/shared.py | 13 +++-
modules/textual_inversion/textual_inversion.py | 12 +--
modules/ui.py | 5 +-
scripts/xy_grid.py | 3 +-
webui.py | 15 +---
9 files changed, 78 insertions(+), 160 deletions(-)
delete mode 100644 modules/hypernetwork.py
(limited to 'modules/ui.py')
diff --git a/modules/hypernetwork.py b/modules/hypernetwork.py
deleted file mode 100644
index 7bbc443e..00000000
--- a/modules/hypernetwork.py
+++ /dev/null
@@ -1,103 +0,0 @@
-import glob
-import os
-import sys
-import traceback
-
-import torch
-
-from ldm.util import default
-from modules import devices, shared
-import torch
-from torch import einsum
-from einops import rearrange, repeat
-
-
-class HypernetworkModule(torch.nn.Module):
- def __init__(self, dim, state_dict):
- super().__init__()
-
- self.linear1 = torch.nn.Linear(dim, dim * 2)
- self.linear2 = torch.nn.Linear(dim * 2, dim)
-
- self.load_state_dict(state_dict, strict=True)
- self.to(devices.device)
-
- def forward(self, x):
- return x + (self.linear2(self.linear1(x)))
-
-
-class Hypernetwork:
- filename = None
- name = None
-
- def __init__(self, filename):
- self.filename = filename
- self.name = os.path.splitext(os.path.basename(filename))[0]
- self.layers = {}
-
- state_dict = torch.load(filename, map_location='cpu')
- for size, sd in state_dict.items():
- self.layers[size] = (HypernetworkModule(size, sd[0]), HypernetworkModule(size, sd[1]))
-
-
-def list_hypernetworks(path):
- res = {}
- for filename in glob.iglob(os.path.join(path, '**/*.pt'), recursive=True):
- name = os.path.splitext(os.path.basename(filename))[0]
- res[name] = filename
- return res
-
-
-def load_hypernetwork(filename):
- path = shared.hypernetworks.get(filename, None)
- if path is not None:
- print(f"Loading hypernetwork {filename}")
- try:
- shared.loaded_hypernetwork = Hypernetwork(path)
- except Exception:
- print(f"Error loading hypernetwork {path}", file=sys.stderr)
- print(traceback.format_exc(), file=sys.stderr)
- else:
- if shared.loaded_hypernetwork is not None:
- print(f"Unloading hypernetwork")
-
- shared.loaded_hypernetwork = None
-
-
-def apply_hypernetwork(hypernetwork, context):
- hypernetwork_layers = (hypernetwork.layers if hypernetwork is not None else {}).get(context.shape[2], None)
-
- if hypernetwork_layers is None:
- return context, context
-
- context_k = hypernetwork_layers[0](context)
- context_v = hypernetwork_layers[1](context)
- return context_k, context_v
-
-
-def attention_CrossAttention_forward(self, x, context=None, mask=None):
- h = self.heads
-
- q = self.to_q(x)
- context = default(context, x)
-
- context_k, context_v = apply_hypernetwork(shared.loaded_hypernetwork, context)
- k = self.to_k(context_k)
- v = self.to_v(context_v)
-
- q, k, v = map(lambda t: rearrange(t, 'b n (h d) -> (b h) n d', h=h), (q, k, v))
-
- sim = einsum('b i d, b j d -> b i j', q, k) * self.scale
-
- if mask is not None:
- mask = rearrange(mask, 'b ... -> b (...)')
- max_neg_value = -torch.finfo(sim.dtype).max
- mask = repeat(mask, 'b j -> (b h) () j', h=h)
- sim.masked_fill_(~mask, max_neg_value)
-
- # attention, what we cannot get enough of
- attn = sim.softmax(dim=-1)
-
- out = einsum('b i j, b j d -> b i d', attn, v)
- out = rearrange(out, '(b h) n d -> b n (h d)', h=h)
- return self.to_out(out)
diff --git a/modules/hypernetwork/hypernetwork.py b/modules/hypernetwork/hypernetwork.py
index a3d6a47e..aa701bda 100644
--- a/modules/hypernetwork/hypernetwork.py
+++ b/modules/hypernetwork/hypernetwork.py
@@ -26,10 +26,11 @@ class HypernetworkModule(torch.nn.Module):
if state_dict is not None:
self.load_state_dict(state_dict, strict=True)
else:
- self.linear1.weight.data.fill_(0.0001)
- self.linear1.bias.data.fill_(0.0001)
- self.linear2.weight.data.fill_(0.0001)
- self.linear2.bias.data.fill_(0.0001)
+
+ self.linear1.weight.data.normal_(mean=0.0, std=0.01)
+ self.linear1.bias.data.zero_()
+ self.linear2.weight.data.normal_(mean=0.0, std=0.01)
+ self.linear2.bias.data.zero_()
self.to(devices.device)
@@ -92,41 +93,54 @@ class Hypernetwork:
self.sd_checkpoint_name = state_dict.get('sd_checkpoint_name', None)
-def load_hypernetworks(path):
+def list_hypernetworks(path):
res = {}
+ for filename in glob.iglob(os.path.join(path, '**/*.pt'), recursive=True):
+ name = os.path.splitext(os.path.basename(filename))[0]
+ res[name] = filename
+ return res
- for filename in glob.iglob(path + '**/*.pt', recursive=True):
+
+def load_hypernetwork(filename):
+ path = shared.hypernetworks.get(filename, None)
+ if path is not None:
+ print(f"Loading hypernetwork {filename}")
try:
- hn = Hypernetwork()
- hn.load(filename)
- res[hn.name] = hn
+ shared.loaded_hypernetwork = Hypernetwork()
+ shared.loaded_hypernetwork.load(path)
+
except Exception:
- print(f"Error loading hypernetwork {filename}", file=sys.stderr)
+ print(f"Error loading hypernetwork {path}", file=sys.stderr)
print(traceback.format_exc(), file=sys.stderr)
+ else:
+ if shared.loaded_hypernetwork is not None:
+ print(f"Unloading hypernetwork")
- return res
+ shared.loaded_hypernetwork = None
-def attention_CrossAttention_forward(self, x, context=None, mask=None):
- h = self.heads
+def apply_hypernetwork(hypernetwork, context, layer=None):
+ hypernetwork_layers = (hypernetwork.layers if hypernetwork is not None else {}).get(context.shape[2], None)
- q = self.to_q(x)
- context = default(context, x)
+ if hypernetwork_layers is None:
+ return context, context
- hypernetwork_layers = (shared.hypernetwork.layers if shared.hypernetwork is not None else {}).get(context.shape[2], None)
+ if layer is not None:
+ layer.hyper_k = hypernetwork_layers[0]
+ layer.hyper_v = hypernetwork_layers[1]
- if hypernetwork_layers is not None:
- hypernetwork_k, hypernetwork_v = hypernetwork_layers
+ context_k = hypernetwork_layers[0](context)
+ context_v = hypernetwork_layers[1](context)
+ return context_k, context_v
- self.hypernetwork_k = hypernetwork_k
- self.hypernetwork_v = hypernetwork_v
- context_k = hypernetwork_k(context)
- context_v = hypernetwork_v(context)
- else:
- context_k = context
- context_v = context
+def attention_CrossAttention_forward(self, x, context=None, mask=None):
+ h = self.heads
+
+ q = self.to_q(x)
+ context = default(context, x)
+ context_k, context_v = apply_hypernetwork(shared.loaded_hypernetwork, context, self)
k = self.to_k(context_k)
v = self.to_v(context_v)
@@ -151,7 +165,9 @@ def attention_CrossAttention_forward(self, x, context=None, mask=None):
def train_hypernetwork(hypernetwork_name, learn_rate, data_root, log_directory, steps, create_image_every, save_hypernetwork_every, template_file, preview_image_prompt):
assert hypernetwork_name, 'embedding not selected'
- shared.hypernetwork = shared.hypernetworks[hypernetwork_name]
+ path = shared.hypernetworks.get(hypernetwork_name, None)
+ shared.loaded_hypernetwork = Hypernetwork()
+ shared.loaded_hypernetwork.load(path)
shared.state.textinfo = "Initializing hypernetwork training..."
shared.state.job_count = steps
@@ -176,9 +192,9 @@ def train_hypernetwork(hypernetwork_name, learn_rate, data_root, log_directory,
shared.state.textinfo = f"Preparing dataset from {html.escape(data_root)}..."
with torch.autocast("cuda"):
- ds = modules.textual_inversion.dataset.PersonalizedBase(data_root=data_root, size=512, placeholder_token=hypernetwork_name, model=shared.sd_model, device=devices.device, template_file=template_file)
+ ds = modules.textual_inversion.dataset.PersonalizedBase(data_root=data_root, width=512, height=512, repeats=1, placeholder_token=hypernetwork_name, model=shared.sd_model, device=devices.device, template_file=template_file)
- hypernetwork = shared.hypernetworks[hypernetwork_name]
+ hypernetwork = shared.loaded_hypernetwork
weights = hypernetwork.weights()
for weight in weights:
weight.requires_grad = True
@@ -194,7 +210,7 @@ def train_hypernetwork(hypernetwork_name, learn_rate, data_root, log_directory,
if ititial_step > steps:
return hypernetwork, filename
- pbar = tqdm.tqdm(enumerate(ds), total=steps-ititial_step)
+ pbar = tqdm.tqdm(enumerate(ds), total=steps - ititial_step)
for i, (x, text) in pbar:
hypernetwork.step = i + ititial_step
diff --git a/modules/hypernetwork/ui.py b/modules/hypernetwork/ui.py
index 525f978c..f6d1d0a3 100644
--- a/modules/hypernetwork/ui.py
+++ b/modules/hypernetwork/ui.py
@@ -6,24 +6,24 @@ import gradio as gr
import modules.textual_inversion.textual_inversion
import modules.textual_inversion.preprocess
from modules import sd_hijack, shared
+from modules.hypernetwork import hypernetwork
def create_hypernetwork(name):
fn = os.path.join(shared.cmd_opts.hypernetwork_dir, f"{name}.pt")
assert not os.path.exists(fn), f"file {fn} already exists"
- hypernetwork = modules.hypernetwork.hypernetwork.Hypernetwork(name=name)
- hypernetwork.save(fn)
+ hypernet = modules.hypernetwork.hypernetwork.Hypernetwork(name=name)
+ hypernet.save(fn)
shared.reload_hypernetworks()
- shared.hypernetwork = shared.hypernetworks.get(shared.opts.sd_hypernetwork, None)
return gr.Dropdown.update(choices=sorted([x for x in shared.hypernetworks.keys()])), f"Created: {fn}", ""
def train_hypernetwork(*args):
- initial_hypernetwork = shared.hypernetwork
+ initial_hypernetwork = shared.loaded_hypernetwork
try:
sd_hijack.undo_optimizations()
@@ -38,6 +38,6 @@ Hypernetwork saved to {html.escape(filename)}
except Exception:
raise
finally:
- shared.hypernetwork = initial_hypernetwork
+ shared.loaded_hypernetwork = initial_hypernetwork
sd_hijack.apply_optimizations()
diff --git a/modules/sd_hijack_optimizations.py b/modules/sd_hijack_optimizations.py
index 25cb67a4..27e571fc 100644
--- a/modules/sd_hijack_optimizations.py
+++ b/modules/sd_hijack_optimizations.py
@@ -8,7 +8,8 @@ from torch import einsum
from ldm.util import default
from einops import rearrange
-from modules import shared, hypernetwork
+from modules import shared
+from modules.hypernetwork import hypernetwork
if shared.cmd_opts.xformers or shared.cmd_opts.force_enable_xformers:
diff --git a/modules/shared.py b/modules/shared.py
index 14b40d70..8753015e 100644
--- a/modules/shared.py
+++ b/modules/shared.py
@@ -13,7 +13,8 @@ import modules.memmon
import modules.sd_models
import modules.styles
import modules.devices as devices
-from modules import sd_samplers, hypernetwork
+from modules import sd_samplers
+from modules.hypernetwork import hypernetwork
from modules.paths import models_path, script_path, sd_path
sd_model_file = os.path.join(script_path, 'model.ckpt')
@@ -29,6 +30,7 @@ parser.add_argument("--no-half-vae", action='store_true', help="do not switch th
parser.add_argument("--no-progressbar-hiding", action='store_true', help="do not hide progressbar in gradio UI (we hide it because it slows down ML if you have hardware acceleration in browser)")
parser.add_argument("--max-batch-count", type=int, default=16, help="maximum batch count value for the UI")
parser.add_argument("--embeddings-dir", type=str, default=os.path.join(script_path, 'embeddings'), help="embeddings directory for textual inversion (default: embeddings)")
+parser.add_argument("--hypernetwork-dir", type=str, default=os.path.join(models_path, 'hypernetworks'), help="hypernetwork directory")
parser.add_argument("--allow-code", action='store_true', help="allow custom script execution from webui")
parser.add_argument("--medvram", action='store_true', help="enable stable diffusion model optimizations for sacrificing a little speed for low VRM usage")
parser.add_argument("--lowvram", action='store_true', help="enable stable diffusion model optimizations for sacrificing a lot of speed for very low VRM usage")
@@ -82,10 +84,17 @@ parallel_processing_allowed = not cmd_opts.lowvram and not cmd_opts.medvram
xformers_available = False
config_filename = cmd_opts.ui_settings_file
-hypernetworks = hypernetwork.list_hypernetworks(os.path.join(models_path, 'hypernetworks'))
+hypernetworks = hypernetwork.list_hypernetworks(cmd_opts.hypernetwork_dir)
loaded_hypernetwork = None
+def reload_hypernetworks():
+ global hypernetworks
+
+ hypernetworks = hypernetwork.list_hypernetworks(cmd_opts.hypernetwork_dir)
+ hypernetwork.load_hypernetwork(opts.sd_hypernetwork)
+
+
class State:
skipped = False
interrupted = False
diff --git a/modules/textual_inversion/textual_inversion.py b/modules/textual_inversion/textual_inversion.py
index 5965c5a0..d6977950 100644
--- a/modules/textual_inversion/textual_inversion.py
+++ b/modules/textual_inversion/textual_inversion.py
@@ -156,7 +156,7 @@ def create_embedding(name, num_vectors_per_token, init_text='*'):
return fn
-def train_embedding(embedding_name, learn_rate, data_root, log_directory, training_width, training_height, steps, num_repeats, create_image_every, save_embedding_every, template_file):
+def train_embedding(embedding_name, learn_rate, data_root, log_directory, training_width, training_height, steps, num_repeats, create_image_every, save_embedding_every, template_file, preview_image_prompt):
assert embedding_name, 'embedding not selected'
shared.state.textinfo = "Initializing textual inversion training..."
@@ -238,12 +238,14 @@ def train_embedding(embedding_name, learn_rate, data_root, log_directory, traini
if embedding.step > 0 and images_dir is not None and embedding.step % create_image_every == 0:
last_saved_image = os.path.join(images_dir, f'{embedding_name}-{embedding.step}.png')
+ preview_text = text if preview_image_prompt == "" else preview_image_prompt
+
p = processing.StableDiffusionProcessingTxt2Img(
sd_model=shared.sd_model,
- prompt=text,
+ prompt=preview_text,
steps=20,
- height=training_height,
- width=training_width,
+ height=training_height,
+ width=training_width,
do_not_save_grid=True,
do_not_save_samples=True,
)
@@ -254,7 +256,7 @@ def train_embedding(embedding_name, learn_rate, data_root, log_directory, traini
shared.state.current_image = image
image.save(last_saved_image)
- last_saved_image += f", prompt: {text}"
+ last_saved_image += f", prompt: {preview_text}"
shared.state.job_no = embedding.step
diff --git a/modules/ui.py b/modules/ui.py
index 10b1ee3a..df653059 100644
--- a/modules/ui.py
+++ b/modules/ui.py
@@ -1023,7 +1023,7 @@ def create_ui(wrap_gradio_gpu_call):
gr.HTML(value="")
with gr.Column():
- create_embedding = gr.Button(value="Create", variant='primary')
+ create_embedding = gr.Button(value="Create embedding", variant='primary')
with gr.Group():
gr.HTML(value="Create a new hypernetwork
")
@@ -1035,7 +1035,7 @@ def create_ui(wrap_gradio_gpu_call):
gr.HTML(value="")
with gr.Column():
- create_hypernetwork = gr.Button(value="Create", variant='primary')
+ create_hypernetwork = gr.Button(value="Create hypernetwork", variant='primary')
with gr.Group():
gr.HTML(value="Preprocess images
")
@@ -1147,6 +1147,7 @@ def create_ui(wrap_gradio_gpu_call):
create_image_every,
save_embedding_every,
template_file,
+ preview_image_prompt,
],
outputs=[
ti_output,
diff --git a/scripts/xy_grid.py b/scripts/xy_grid.py
index 42e1489c..0af5993c 100644
--- a/scripts/xy_grid.py
+++ b/scripts/xy_grid.py
@@ -10,7 +10,8 @@ import numpy as np
import modules.scripts as scripts
import gradio as gr
-from modules import images, hypernetwork
+from modules import images
+from modules.hypernetwork import hypernetwork
from modules.processing import process_images, Processed, get_correct_sampler
from modules.shared import opts, cmd_opts, state
import modules.shared as shared
diff --git a/webui.py b/webui.py
index 7c200551..ba2156c8 100644
--- a/webui.py
+++ b/webui.py
@@ -29,6 +29,7 @@ from modules import devices
from modules import modelloader
from modules.paths import script_path
from modules.shared import cmd_opts
+import modules.hypernetwork.hypernetwork
modelloader.cleanup_models()
modules.sd_models.setup_model()
@@ -77,22 +78,12 @@ def wrap_gradio_gpu_call(func, extra_outputs=None):
return modules.ui.wrap_gradio_call(f, extra_outputs=extra_outputs)
-def set_hypernetwork():
- shared.hypernetwork = shared.hypernetworks.get(shared.opts.sd_hypernetwork, None)
-
-
-shared.reload_hypernetworks()
-shared.opts.onchange("sd_hypernetwork", set_hypernetwork)
-set_hypernetwork()
-
-
modules.scripts.load_scripts(os.path.join(script_path, "scripts"))
shared.sd_model = modules.sd_models.load_model()
shared.opts.onchange("sd_model_checkpoint", wrap_queued_call(lambda: modules.sd_models.reload_model_weights(shared.sd_model)))
-loaded_hypernetwork = modules.hypernetwork.load_hypernetwork(shared.opts.sd_hypernetwork)
-shared.opts.onchange("sd_hypernetwork", wrap_queued_call(lambda: modules.hypernetwork.load_hypernetwork(shared.opts.sd_hypernetwork)))
+shared.opts.onchange("sd_hypernetwork", wrap_queued_call(lambda: modules.hypernetwork.hypernetwork.load_hypernetwork(shared.opts.sd_hypernetwork)))
def webui():
@@ -117,7 +108,7 @@ def webui():
prevent_thread_lock=True
)
- app.add_middleware(GZipMiddleware,minimum_size=1000)
+ app.add_middleware(GZipMiddleware, minimum_size=1000)
while 1:
time.sleep(0.5)
--
cgit v1.2.3