Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Add a button to prune unused hash #16700

Closed
wants to merge 1 commit into from
+51 −0
Closed

Add a button to prune unused hash #16700

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
47 changes: 47 additions & 0 deletions modules/cache.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -121,3 +121,50 @@ def cached_data_for_file(subsection, title, filename, func):
dump_cache()

return entry['value']


def prune_unused_hash():
import glob

from modules.paths_internal import extensions_dir

existing_cache = cache('extensions-git')
total_count = len(existing_cache)
with tqdm.tqdm(total=total_count, desc='pruning extensions') as progress:
for name in existing_cache:
if not os.path.isdir(os.path.join(extensions_dir, name)):
existing_cache.pop(name)
progress.update(1)

def file_exists(parent_dir, filename):
matches = glob.glob(os.path.join(parent_dir, '**', f'{filename}*'), recursive=True)
return len(matches) > 0

from modules.paths_internal import models_path
from modules.shared import cmd_opts

for db in ('hashes', 'hashes-addnet', 'safetensors-metadata'):
existing_cache = cache(db)
total_count = len(existing_cache)
with tqdm.tqdm(total=total_count, desc=f'pruning {db}') as progress:
for name in existing_cache:
if '/' not in name:
progress.update(1)
continue

category, filename = name.split('/', 1)
if category.lower() == 'lora':
exists = file_exists(os.path.join(models_path, 'Lora'), filename)
elif category.lower() == 'checkpoint':
exists = file_exists(os.path.join(models_path, 'Stable-diffusion'), filename)
elif category.lower() == 'textual_inversion':
exists = file_exists(cmd_opts.embeddings_dir, filename)
else:
progress.update(1)
continue

if not exists:
del existing_cache[name]
progress.update(1)
Comment on lines +146 to +168
Copy link
Collaborator

@w-e-w w-e-w Dec 17, 2024 •
edited
Loading

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

this is wrong

  • completely forgot about hypernet

  • you are assuming that the user is using the default directories which may not be the case, that the path of each model directory is a complicated mess, some models such as Lora can come from multiple directories

  • extensions could also add own cache entries, I don't think there's a way that you can avoid not accidentally removing those entries

as you said

which can reduce file size by a tiny amount, and improve load time by an even tinier amount...

so personally I wouldn't bother makeing it work, not worth the effort


print('Finish pruning hash')
4 changes: 4 additions & 0 deletions modules/ui_settings.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,6 +1,7 @@
import gradio as gr

from modules import ui_common, shared, script_callbacks, scripts, sd_models, sysinfo, timer, shared_items
from modules.cache import prune_unused_hash
from modules.call_queue import wrap_gradio_call_no_job
from modules.options import options_section
from modules.shared import opts
Expand Down Expand Up @@ -190,6 +191,7 @@ def create_ui(self, loadsave, dummy_component):
with gr.Row():
calculate_all_checkpoint_hash = gr.Button(value='Calculate hash for all checkpoint', elem_id="calculate_all_checkpoint_hash")
calculate_all_checkpoint_hash_threads = gr.Number(value=1, label="Number of parallel calculations", elem_id="calculate_all_checkpoint_hash_threads", precision=0, minimum=1)
prune_all_unused_hash = gr.Button(value='Prune all unused hash', elem_id="prune_all_unused_hash")

with gr.TabItem("Licenses", id="licenses", elem_id="settings_tab_licenses"):
gr.HTML(shared.html("licenses.html"), elem_id="licenses")
Expand Down Expand Up @@ -285,6 +287,8 @@ def calculate_all_checkpoint_hash_fn(max_thread):
inputs=[calculate_all_checkpoint_hash_threads],
)

prune_all_unused_hash.click(fn=prune_unused_hash)

self.interface = settings_interface

def add_quicksettings(self):
Expand Down
Loading