hoelee/stable-diffusion-webui
1
0
Fork 0
mirror of https://github.com/AUTOMATIC1111/stable-diffusion-webui.git synced 2025-08-05 03:32:37 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

Merge branch 'master' into fix/train-preprocess-keep-ratio

Browse Source
This commit is contained in:
AUTOMATIC1111
2022-10-21 18:36:29 +03:00
committed by GitHub
parent 85dd62c4c7 24ce67a13b
commit 5e9afa5c8a
29 changed files with 1106 additions and 209 deletions
Download Patch File Download Diff File Expand all files Collapse all files

130
modules/ui.py
View File

@@ -25,7 +25,9 @@ import gradio.routes
from modules import sd_hijack, sd_models, localization
from modules.paths import script_path
from modules.shared import opts, cmd_opts, restricted_opts
from modules.shared import opts, cmd_opts, restricted_opts, aesthetic_embeddings
if cmd_opts.deepdanbooru:
from modules.deepbooru import get_deepbooru_tags
import modules.shared as shared
@@ -41,8 +43,11 @@ from modules import prompt_parser
from modules.images import save_image
import modules.textual_inversion.ui
import modules.hypernetworks.ui
import modules.aesthetic_clip as aesthetic_clip
import modules.images_history as img_his
# this is a fix for Windows users. Without it, javascript files will be served with text/html content-type and the browser will not show any UI
mimetypes.init()
mimetypes.add_type('application/javascript', '.js')
@@ -592,27 +597,29 @@ def apply_setting(key, value):
return value
def create_refresh_button(refresh_component, refresh_method, refreshed_args, elem_id):
def refresh():
refresh_method()
args = refreshed_args() if callable(refreshed_args) else refreshed_args
for k, v in args.items():
setattr(refresh_component, k, v)
return gr.update(**(args or {}))
refresh_button = gr.Button(value=refresh_symbol, elem_id=elem_id)
refresh_button.click(
fn=refresh,
inputs=[],
outputs=[refresh_component]
)
return refresh_button
def create_ui(wrap_gradio_gpu_call):
import modules.img2img
import modules.txt2img
def create_refresh_button(refresh_component, refresh_method, refreshed_args, elem_id):
def refresh():
refresh_method()
args = refreshed_args() if callable(refreshed_args) else refreshed_args
for k, v in args.items():
setattr(refresh_component, k, v)
return gr.update(**(args or {}))
refresh_button = gr.Button(value=refresh_symbol, elem_id=elem_id)
refresh_button.click(
fn = refresh,
inputs = [],
outputs = [refresh_component]
)
return refresh_button
with gr.Blocks(analytics_enabled=False) as txt2img_interface:
txt2img_prompt, roll, txt2img_prompt_style, txt2img_negative_prompt, txt2img_prompt_style2, submit, _, _, txt2img_prompt_style_apply, txt2img_save_style, txt2img_paste, token_counter, token_button = create_toprow(is_img2img=False)
@@ -655,6 +662,8 @@ def create_ui(wrap_gradio_gpu_call):
seed, reuse_seed, subseed, reuse_subseed, subseed_strength, seed_resize_from_h, seed_resize_from_w, seed_checkbox = create_seed_inputs()
aesthetic_weight, aesthetic_steps, aesthetic_lr, aesthetic_slerp, aesthetic_imgs, aesthetic_imgs_text, aesthetic_slerp_angle, aesthetic_text_negative = aesthetic_clip.create_ui()
with gr.Group():
custom_inputs = modules.scripts.scripts_txt2img.setup_ui(is_img2img=False)
@@ -709,7 +718,16 @@ def create_ui(wrap_gradio_gpu_call):
denoising_strength,
firstphase_width,
firstphase_height,
aesthetic_lr,
aesthetic_weight,
aesthetic_steps,
aesthetic_imgs,
aesthetic_slerp,
aesthetic_imgs_text,
aesthetic_slerp_angle,
aesthetic_text_negative
] + custom_inputs,
outputs=[
txt2img_gallery,
generation_info,
@@ -786,6 +804,14 @@ def create_ui(wrap_gradio_gpu_call):
(hr_options, lambda d: gr.Row.update(visible="Denoising strength" in d)),
(firstphase_width, "First pass size-1"),
(firstphase_height, "First pass size-2"),
(aesthetic_lr, "Aesthetic LR"),
(aesthetic_weight, "Aesthetic weight"),
(aesthetic_steps, "Aesthetic steps"),
(aesthetic_imgs, "Aesthetic embedding"),
(aesthetic_slerp, "Aesthetic slerp"),
(aesthetic_imgs_text, "Aesthetic text"),
(aesthetic_text_negative, "Aesthetic text negative"),
(aesthetic_slerp_angle, "Aesthetic slerp angle"),
]
txt2img_preview_params = [
@@ -853,8 +879,8 @@ def create_ui(wrap_gradio_gpu_call):
sampler_index = gr.Radio(label='Sampling method', choices=[x.name for x in samplers_for_img2img], value=samplers_for_img2img[0].name, type="index")
with gr.Group():
width = gr.Slider(minimum=64, maximum=2048, step=64, label="Width", value=512)
height = gr.Slider(minimum=64, maximum=2048, step=64, label="Height", value=512)
width = gr.Slider(minimum=64, maximum=2048, step=64, label="Width", value=512, elem_id="img2img_width")
height = gr.Slider(minimum=64, maximum=2048, step=64, label="Height", value=512, elem_id="img2img_height")
with gr.Row():
restore_faces = gr.Checkbox(label='Restore faces', value=False, visible=len(shared.face_restorers) > 1)
@@ -870,6 +896,8 @@ def create_ui(wrap_gradio_gpu_call):
seed, reuse_seed, subseed, reuse_subseed, subseed_strength, seed_resize_from_h, seed_resize_from_w, seed_checkbox = create_seed_inputs()
aesthetic_weight_im, aesthetic_steps_im, aesthetic_lr_im, aesthetic_slerp_im, aesthetic_imgs_im, aesthetic_imgs_text_im, aesthetic_slerp_angle_im, aesthetic_text_negative_im = aesthetic_clip.create_ui()
with gr.Group():
custom_inputs = modules.scripts.scripts_img2img.setup_ui(is_img2img=True)
@@ -960,6 +988,14 @@ def create_ui(wrap_gradio_gpu_call):
inpainting_mask_invert,
img2img_batch_input_dir,
img2img_batch_output_dir,
aesthetic_lr_im,
aesthetic_weight_im,
aesthetic_steps_im,
aesthetic_imgs_im,
aesthetic_slerp_im,
aesthetic_imgs_text_im,
aesthetic_slerp_angle_im,
aesthetic_text_negative_im,
] + custom_inputs,
outputs=[
img2img_gallery,
@@ -1051,6 +1087,14 @@ def create_ui(wrap_gradio_gpu_call):
(seed_resize_from_w, "Seed resize from-1"),
(seed_resize_from_h, "Seed resize from-2"),
(denoising_strength, "Denoising strength"),
(aesthetic_lr_im, "Aesthetic LR"),
(aesthetic_weight_im, "Aesthetic weight"),
(aesthetic_steps_im, "Aesthetic steps"),
(aesthetic_imgs_im, "Aesthetic embedding"),
(aesthetic_slerp_im, "Aesthetic slerp"),
(aesthetic_imgs_text_im, "Aesthetic text"),
(aesthetic_text_negative_im, "Aesthetic text negative"),
(aesthetic_slerp_angle_im, "Aesthetic slerp angle"),
]
token_button.click(fn=update_token_counter, inputs=[img2img_prompt, steps], outputs=[token_counter])
@@ -1211,6 +1255,7 @@ def create_ui(wrap_gradio_gpu_call):
new_embedding_name = gr.Textbox(label="Name")
initialization_text = gr.Textbox(label="Initialization text", value="*")
nvpt = gr.Slider(label="Number of vectors per token", minimum=1, maximum=75, step=1, value=1)
overwrite_old_embedding = gr.Checkbox(value=False, label="Overwrite Old Embedding")
with gr.Row():
with gr.Column(scale=3):
@@ -1219,11 +1264,25 @@ def create_ui(wrap_gradio_gpu_call):
with gr.Column():
create_embedding = gr.Button(value="Create embedding", variant='primary')
with gr.Tab(label="Create aesthetic images embedding"):
new_embedding_name_ae = gr.Textbox(label="Name")
process_src_ae = gr.Textbox(label='Source directory')
batch_ae = gr.Slider(minimum=1, maximum=1024, step=1, label="Batch size", value=256)
with gr.Row():
with gr.Column(scale=3):
gr.HTML(value="")
with gr.Column():
create_embedding_ae = gr.Button(value="Create images embedding", variant='primary')
with gr.Tab(label="Create hypernetwork"):
new_hypernetwork_name = gr.Textbox(label="Name")
new_hypernetwork_sizes = gr.CheckboxGroup(label="Modules", value=["768", "320", "640", "1280"], choices=["768", "320", "640", "1280"])
new_hypernetwork_layer_structure = gr.Textbox("1, 2, 1", label="Enter hypernetwork layer structure", placeholder="1st and last digit must be 1. ex:'1, 2, 1'")
new_hypernetwork_add_layer_norm = gr.Checkbox(label="Add layer normalization")
overwrite_old_hypernetwork = gr.Checkbox(value=False, label="Overwrite Old Hypernetwork")
new_hypernetwork_activation_func = gr.Dropdown(value="relu", label="Select activation function of hypernetwork", choices=["linear", "relu", "leakyrelu"])
with gr.Row():
with gr.Column(scale=3):
@@ -1237,6 +1296,7 @@ def create_ui(wrap_gradio_gpu_call):
process_dst = gr.Textbox(label='Destination directory')
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)
preprocess_txt_action = gr.Dropdown(label='Existing Caption txt Action', value="ignore", choices=["ignore", "copy", "prepend", "append"])
with gr.Row():
process_flip = gr.Checkbox(label='Create flipped copies')
@@ -1262,14 +1322,17 @@ def create_ui(wrap_gradio_gpu_call):
)
with gr.Tab(label="Train"):
gr.HTML(value="<p style='margin-bottom: 0.7em'>Train an embedding; must specify a directory with a set of 1:1 ratio images</p>")
gr.HTML(value="<p style='margin-bottom: 0.7em'>Train an embedding or Hypernetwork; you must specify a directory with a set of 1:1 ratio images <a href=\"https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Textual-Inversion\" style=\"font-weight:bold;\">[wiki]</a></p>")
with gr.Row():
train_embedding_name = gr.Dropdown(label='Embedding', elem_id="train_embedding", choices=sorted(sd_hijack.model_hijack.embedding_db.word_embeddings.keys()))
create_refresh_button(train_embedding_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.Row():
train_hypernetwork_name = gr.Dropdown(label='Hypernetwork', elem_id="train_hypernetwork", choices=[x for x in shared.hypernetworks.keys()])
create_refresh_button(train_hypernetwork_name, shared.reload_hypernetworks, lambda: {"choices": sorted([x for x in shared.hypernetworks.keys()])}, "refresh_train_hypernetwork_name")
learn_rate = gr.Textbox(label='Learning rate', placeholder="Learning rate", value="0.005")
with gr.Row():
embedding_learn_rate = gr.Textbox(label='Embedding Learning rate', placeholder="Embedding Learning rate", value="0.005")
hypernetwork_learn_rate = gr.Textbox(label='Hypernetwork Learning rate', placeholder="Hypernetwork Learning rate", value="0.00001")
batch_size = gr.Number(label='Batch size', value=1, precision=0)
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")
@@ -1303,6 +1366,7 @@ def create_ui(wrap_gradio_gpu_call):
new_embedding_name,
initialization_text,
nvpt,
overwrite_old_embedding,
],
outputs=[
train_embedding_name,
@@ -1311,13 +1375,30 @@ def create_ui(wrap_gradio_gpu_call):
]
)
create_embedding_ae.click(
fn=aesthetic_clip.generate_imgs_embd,
inputs=[
new_embedding_name_ae,
process_src_ae,
batch_ae
],
outputs=[
aesthetic_imgs,
aesthetic_imgs_im,
ti_output,
ti_outcome,
]
)
create_hypernetwork.click(
fn=modules.hypernetworks.ui.create_hypernetwork,
inputs=[
new_hypernetwork_name,
new_hypernetwork_sizes,
overwrite_old_hypernetwork,
new_hypernetwork_layer_structure,
new_hypernetwork_add_layer_norm,
new_hypernetwork_activation_func,
],
outputs=[
train_hypernetwork_name,
@@ -1334,6 +1415,7 @@ def create_ui(wrap_gradio_gpu_call):
process_dst,
process_width,
process_height,
preprocess_txt_action,
process_flip,
process_split,
process_caption,
@@ -1352,7 +1434,7 @@ def create_ui(wrap_gradio_gpu_call):
_js="start_training_textual_inversion",
inputs=[
train_embedding_name,
learn_rate,
embedding_learn_rate,
batch_size,
dataset_directory,
log_directory,
@@ -1377,7 +1459,7 @@ def create_ui(wrap_gradio_gpu_call):
_js="start_training_textual_inversion",
inputs=[
train_hypernetwork_name,
learn_rate,
hypernetwork_learn_rate,
batch_size,
dataset_directory,
log_directory,