Raincloud/SequenceCompressor
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

arguments to force 16 or 8 bit color

Browse Source
This commit is contained in:
Nathan
2025-12-11 14:56:14 -07:00
parent 0b3a1b4d1a
commit 8d7750a78f
2 changed files with 624 additions and 47 deletions
Download Patch File Download Diff File Expand all files Collapse all files

504
.specstory/history/2025-12-11_18-21Z-compress-png-sequences-with-multithreading.md
View File

@@ -2508,3 +2508,507 @@ This format is used for elapsed time, ETA, and total time in the summary.
---
_**User (2025-12-11 21:39Z)**_
let's add options to force 8bit or 16bit color: --16bit --8bit; shorthand -16, -8
---
_**Agent (model default, mode Agent)**_
---
Adding command-line options to force 8-bit or 16-bit color depth:
---
<tool-use data-tool-type="read" data-tool-name="read_file">
<details><summary>Tool use: **read_file** • Read file: compress_pngs.py</summary>
</details>
</tool-use>
---
<tool-use data-tool-type="read" data-tool-name="read_file">
<details><summary>Tool use: **read_file** • Read file: compress_pngs.py</summary>
</details>
</tool-use>
---
---
---
<tool-use data-tool-type="write" data-tool-name="search_replace">
<details><summary>Tool use: **search_replace** • Edit file: compress_pngs.py</summary>
**Chunk 1**
Lines added: 1, lines removed: undefined
```diff
@@ -7,4 +7,5 @@
import os
import sys
+ import argparse
from pathlib import Path
from concurrent.futures import ProcessPoolExecutor, as_completed
```
</details>
</tool-use>
---
<tool-use data-tool-type="write" data-tool-name="search_replace">
<details><summary>Tool use: **search_replace** • Edit file: compress_pngs.py</summary>
**Chunk 1**
Lines added: 8, lines removed: 2
```diff
@@ -14,6 +14,12 @@
import time
- def compress_png(input_path, output_path):
- """Compress a single PNG file."""
+ def compress_png(input_path, output_path, force_bitdepth=None):
+ """Compress a single PNG file.
+
+ Args:
+ input_path: Path to input image
+ output_path: Path to output image
+ force_bitdepth: None (auto-detect), '8' (force 8-bit), or '16' (force 16-bit)
+ """
try:
input_path = Path(input_path)
```
**Chunk 2**
Lines added: 30, lines removed: 26
```diff
@@ -34,31 +40,35 @@
img = Image.open(input_path)
- # Check if image is 16-bit
- # PIL represents 16-bit grayscale as 'I' mode (32-bit integer)
- # For color images, check pixel values to determine bit depth
- is_16bit = False
- original_mode = img.mode
-
- if img.mode == 'I':
- # 'I' mode typically represents 16-bit grayscale
- is_16bit = True
- elif img.mode in ('RGB', 'RGBA', 'LA'):
- # Check if max pixel value exceeds 8-bit range
- try:
- # Get a sample of pixels to check
- pixels = list(img.getdata())
- if pixels:
- # Flatten if needed (for multi-channel modes)
- if isinstance(pixels[0], (tuple, list)):
- max_val = max(max(p) for p in pixels[:1000]) # Sample first 1000 pixels
- else:
- max_val = max(pixels[:1000])
- if max_val &gt; 255:
- is_16bit = True
- except:
- # If we can't determine, assume 8-bit to be safe
- pass
+ # Determine target bit depth
+ if force_bitdepth == '8':
+ is_16bit = False
+ elif force_bitdepth == '16':
+ is_16bit = True
+ else:
+ # Auto-detect bit depth
+ is_16bit = False
+ original_mode = img.mode
+
+ if img.mode == 'I':
+ # 'I' mode typically represents 16-bit grayscale
+ is_16bit = True
+ elif img.mode in ('RGB', 'RGBA', 'LA'):
+ # Check if max pixel value exceeds 8-bit range
+ try:
+ # Get a sample of pixels to check
+ pixels = list(img.getdata())
+ if pixels:
+ # Flatten if needed (for multi-channel modes)
+ if isinstance(pixels[0], (tuple, list)):
+ max_val = max(max(p) for p in pixels[:1000]) # Sample first 1000 pixels
+ else:
+ max_val = max(pixels[:1000])
+ if max_val &gt; 255:
+ is_16bit = True
+ except:
+ # If we can't determine, assume 8-bit to be safe
+ pass
- # Preserve 16-bit depth if present, otherwise convert as needed
+ # Handle bit depth conversion based on target
if is_16bit:
# For 16-bit images, preserve the mode
```
</details>
</tool-use>
---
<tool-use data-tool-type="read" data-tool-name="read_file">
<details><summary>Tool use: **read_file** • Read file: compress_pngs.py</summary>
</details>
</tool-use>
---
---
Updating the conversion logic for forced bit depths and adding argument parsing:
---
<tool-use data-tool-type="write" data-tool-name="search_replace">
<details><summary>Tool use: **search_replace** • Edit file: compress_pngs.py</summary>
**Chunk 1**
Lines added: 52, lines removed: 22
```diff
@@ -72,26 +72,56 @@
# Handle bit depth conversion based on target
if is_16bit:
- # For 16-bit images, preserve the mode
- # PIL will save 16-bit when mode is 'I' (grayscale) or when using specific modes
- if img.mode == 'I':
- # Keep 16-bit grayscale
- pass
- elif img.mode in ('RGB', 'RGBA'):
- # Keep color mode - PIL may preserve 16-bit depending on how it was loaded
- # Note: PIL's PNG save may convert 16-bit RGB to 8-bit, but we preserve the mode
- pass
- else:
- # Convert other modes while trying to preserve bit depth
- if 'A' in img.mode:
- img = img.convert('RGBA')
- else:
- img = img.convert('RGB')
- else:
- # 8-bit images: convert as needed
- if img.mode == 'RGBA':
- # Keep RGBA for transparency support
- img = img.convert('RGBA')
- elif img.mode != 'RGB':
- img = img.convert('RGB')
+ # Force or preserve 16-bit
+ if force_bitdepth == '16':
+ # Force 16-bit: convert to appropriate 16-bit mode
+ if img.mode == 'I':
+ # Already 16-bit grayscale
+ pass
+ elif 'A' in img.mode or img.mode == 'LA':
+ # Convert to 16-bit RGBA (PIL limitation: may not fully preserve 16-bit color)
+ img = img.convert('RGBA')
+ else:
+ # Convert to 16-bit RGB
+ img = img.convert('RGB')
+ else:
+ # Preserve existing 16-bit
+ if img.mode == 'I':
+ # Keep 16-bit grayscale
+ pass
+ elif img.mode in ('RGB', 'RGBA'):
+ # Keep color mode - PIL may preserve 16-bit depending on how it was loaded
+ pass
+ else:
+ # Convert other modes while trying to preserve bit depth
+ if 'A' in img.mode:
+ img = img.convert('RGBA')
+ else:
+ img = img.convert('RGB')
+ else:
+ # Force or use 8-bit
+ if force_bitdepth == '8':
+ # Force 8-bit: ensure we're in 8-bit mode
+ if img.mode == 'I':
+ # Convert 16-bit grayscale to 8-bit
+ img = img.convert('L')
+ elif img.mode == 'RGBA':
+ # Keep RGBA for transparency support (8-bit)
+ img = img.convert('RGBA')
+ elif img.mode == 'RGB':
+ # Already 8-bit RGB
+ pass
+ else:
+ # Convert to 8-bit RGB
+ if 'A' in img.mode:
+ img = img.convert('RGBA')
+ else:
+ img = img.convert('RGB')
+ else:
+ # 8-bit images: convert as needed
+ if img.mode == 'RGBA':
+ # Keep RGBA for transparency support
+ img = img.convert('RGBA')
+ elif img.mode != 'RGB':
+ img = img.convert('RGB')
# Save with maximum compression
```
</details>
</tool-use>
---
<tool-use data-tool-type="read" data-tool-name="read_file">
<details><summary>Tool use: **read_file** • Read file: compress_pngs.py</summary>
</details>
</tool-use>
---
---
Updating the main function to parse arguments and pass the bitdepth option:
---
<tool-use data-tool-type="read" data-tool-name="read_file">
<details><summary>Tool use: **read_file** • Read file: compress_pngs.py</summary>
</details>
</tool-use>
---
---
---
<tool-use data-tool-type="write" data-tool-name="search_replace">
<details><summary>Tool use: **search_replace** • Edit file: compress_pngs.py</summary>
**Chunk 1**
Lines added: 32, lines removed: undefined
```diff
@@ -181,4 +181,36 @@
def main():
+ # Parse command-line arguments
+ parser = argparse.ArgumentParser(
+ description='Multithreaded PNG compression script with maximum parallelism.'
+ )
+ parser.add_argument(
+ '--8bit', '-8',
+ action='store_true',
+ dest='force_8bit',
+ help='Force 8-bit color depth for all images'
+ )
+ parser.add_argument(
+ '--16bit', '-16',
+ action='store_true',
+ dest='force_16bit',
+ help='Force 16-bit color depth for all images'
+ )
+ args = parser.parse_args()
+
+ # Determine bit depth setting
+ if args.force_8bit and args.force_16bit:
+ print("Error: Cannot specify both --8bit and --16bit. Choose one.")
+ return
+ elif args.force_8bit:
+ force_bitdepth = '8'
+ print("Mode: Forcing 8-bit color depth")
+ elif args.force_16bit:
+ force_bitdepth = '16'
+ print("Mode: Forcing 16-bit color depth")
+ else:
+ force_bitdepth = None
+ print("Mode: Auto-detect bit depth (preserve 16-bit if present)")
+
input_dir = Path('input')
output_dir = Path('output')
```
</details>
</tool-use>
---
<tool-use data-tool-type="read" data-tool-name="read_file">
<details><summary>Tool use: **read_file** • Read file: compress_pngs.py</summary>
</details>
</tool-use>
---
---
---
<tool-use data-tool-type="read" data-tool-name="read_file">
<details><summary>Tool use: **read_file** • Read file: compress_pngs.py</summary>
</details>
</tool-use>
---
---
---
<tool-use data-tool-type="write" data-tool-name="search_replace">
<details><summary>Tool use: **search_replace** • Edit file: compress_pngs.py</summary>
**Chunk 1**
Lines added: 1, lines removed: 1
```diff
@@ -255,5 +255,5 @@
# Submit all tasks
future_to_file = {
- executor.submit(compress_png, str(f), str(get_output_path(f, input_dir, output_dir))): f
+ executor.submit(compress_png, str(f), str(get_output_path(f, input_dir, output_dir)), force_bitdepth): f
for f in png_files
}
```
</details>
</tool-use>
---
<tool-use data-tool-type="generic" data-tool-name="read_lints">
<details>
<summary>Tool use: **read_lints** • Read lints for 1 file</summary>
Lint paths:
- `compress_pngs.py`
Lint results
**No lint errors found**
</details>
</tool-use>
---
---
Added command-line options to force 8-bit or 16-bit color depth. You can use:
- `--8bit` or `-8` to force 8-bit color depth
- `--16bit` or `-16` to force 16-bit color depth
If neither is specified, it auto-detects and preserves 16-bit when present.
Examples:
- `python compress_pngs.py` - Auto-detect (preserves 16-bit if present)
- `python compress_pngs.py --8bit` or `python compress_pngs.py -8` - Force all images to 8-bit
- `python compress_pngs.py --16bit` or `python compress_pngs.py -16` - Force all images to 16-bit
The script displays the selected mode at startup. The batch file will work with these options too.
---
_**User (2025-12-11 21:39Z)**_
Will this script work faster on a Threadripper 3970X than on an i9-13900kf?
---
_**Agent (model default, mode Agent)**_
---
Yes, it should run faster on the Threadripper 3970X, but not proportionally.
**Threadripper 3970X:**
- 32 physical cores, 64 threads
- The script uses `multiprocessing.cpu_count()`, which typically returns 64
- 64 worker processes can run in parallel
**i9-13900KF:**
- 8 P-cores + 8 E-cores = 16 physical cores, 24 threads
- The script would use 24 worker processes
**Expected performance:**
- Roughly 2–2.5x faster on the Threadripper, not 2.67x (64/24), because:
1. I/O bottlenecks: reading/writing files can limit scaling
2. Process overhead: more processes add overhead
3. PIL compression efficiency: may not scale linearly
4. Memory bandwidth: Threadripper’s higher bandwidth helps, but may not be the main factor
**To optimize further:**
- Use an NVMe SSD for input/output
- Ensure sufficient RAM (the script loads images into memory)
- Consider adjusting worker count if I/O becomes a bottleneck
The Threadripper’s higher core count should provide a clear speedup for this CPU-bound PNG compression workload.
---

167
compress_pngs.py
View File

@@ -6,14 +6,21 @@ Compresses all PNG files in subdirectories with maximum parallelism.
import os
import sys
import argparse
from pathlib import Path
from concurrent.futures import ProcessPoolExecutor, as_completed
from PIL import Image
import multiprocessing
import time
def compress_png(input_path, output_path):
"""Compress a single PNG file."""
def compress_png(input_path, output_path, force_bitdepth=None):
"""Compress a single PNG file.
Args:
input_path: Path to input image
output_path: Path to output image
force_bitdepth: None (auto-detect), '8' (force 8-bit), or '16' (force 16-bit)
"""
try:
input_path = Path(input_path)
output_path = Path(output_path)
@@ -32,56 +39,90 @@ def compress_png(input_path, output_path):
original_size = os.path.getsize(input_path)
img = Image.open(input_path)
# Check if image is 16-bit
# PIL represents 16-bit grayscale as 'I' mode (32-bit integer)
# For color images, check pixel values to determine bit depth
is_16bit = False
original_mode = img.mode
if img.mode == 'I':
# 'I' mode typically represents 16-bit grayscale
# Determine target bit depth
if force_bitdepth == '8':
is_16bit = False
elif force_bitdepth == '16':
is_16bit = True
elif img.mode in ('RGB', 'RGBA', 'LA'):
# Check if max pixel value exceeds 8-bit range
try:
# Get a sample of pixels to check
pixels = list(img.getdata())
if pixels:
# Flatten if needed (for multi-channel modes)
if isinstance(pixels[0], (tuple, list)):
max_val = max(max(p) for p in pixels[:1000]) # Sample first 1000 pixels
else:
max_val = max(pixels[:1000])
if max_val > 255:
is_16bit = True
except:
# If we can't determine, assume 8-bit to be safe
pass
# Preserve 16-bit depth if present, otherwise convert as needed
if is_16bit:
# For 16-bit images, preserve the mode
# PIL will save 16-bit when mode is 'I' (grayscale) or when using specific modes
else:
# Auto-detect bit depth
is_16bit = False
original_mode = img.mode
if img.mode == 'I':
# Keep 16-bit grayscale
pass
elif img.mode in ('RGB', 'RGBA'):
# Keep color mode - PIL may preserve 16-bit depending on how it was loaded
# Note: PIL's PNG save may convert 16-bit RGB to 8-bit, but we preserve the mode
pass
else:
# Convert other modes while trying to preserve bit depth
if 'A' in img.mode:
# 'I' mode typically represents 16-bit grayscale
is_16bit = True
elif img.mode in ('RGB', 'RGBA', 'LA'):
# Check if max pixel value exceeds 8-bit range
try:
# Get a sample of pixels to check
pixels = list(img.getdata())
if pixels:
# Flatten if needed (for multi-channel modes)
if isinstance(pixels[0], (tuple, list)):
max_val = max(max(p) for p in pixels[:1000]) # Sample first 1000 pixels
else:
max_val = max(pixels[:1000])
if max_val > 255:
is_16bit = True
except:
# If we can't determine, assume 8-bit to be safe
pass
# Handle bit depth conversion based on target
if is_16bit:
# Force or preserve 16-bit
if force_bitdepth == '16':
# Force 16-bit: convert to appropriate 16-bit mode
if img.mode == 'I':
# Already 16-bit grayscale
pass
elif 'A' in img.mode or img.mode == 'LA':
# Convert to 16-bit RGBA (PIL limitation: may not fully preserve 16-bit color)
img = img.convert('RGBA')
else:
# Convert to 16-bit RGB
img = img.convert('RGB')
else:
# Preserve existing 16-bit
if img.mode == 'I':
# Keep 16-bit grayscale
pass
elif img.mode in ('RGB', 'RGBA'):
# Keep color mode - PIL may preserve 16-bit depending on how it was loaded
pass
else:
# Convert other modes while trying to preserve bit depth
if 'A' in img.mode:
img = img.convert('RGBA')
else:
img = img.convert('RGB')
else:
# 8-bit images: convert as needed
if img.mode == 'RGBA':
# Keep RGBA for transparency support
img = img.convert('RGBA')
elif img.mode != 'RGB':
img = img.convert('RGB')
# Force or use 8-bit
if force_bitdepth == '8':
# Force 8-bit: ensure we're in 8-bit mode
if img.mode == 'I':
# Convert 16-bit grayscale to 8-bit
img = img.convert('L')
elif img.mode == 'RGBA':
# Keep RGBA for transparency support (8-bit)
img = img.convert('RGBA')
elif img.mode == 'RGB':
# Already 8-bit RGB
pass
else:
# Convert to 8-bit RGB
if 'A' in img.mode:
img = img.convert('RGBA')
else:
img = img.convert('RGB')
else:
# 8-bit images: convert as needed
if img.mode == 'RGBA':
# Keep RGBA for transparency support
img = img.convert('RGBA')
elif img.mode != 'RGB':
img = img.convert('RGB')
# Save with maximum compression
# PIL will preserve 16-bit for 'I' mode automatically
@@ -139,6 +180,38 @@ def format_time(seconds):
return f"{hours:02d}:{minutes:02d}:{secs:02d}:{centiseconds:02d}"
def main():
# Parse command-line arguments
parser = argparse.ArgumentParser(
description='Multithreaded PNG compression script with maximum parallelism.'
)
parser.add_argument(
'--8bit', '-8',
action='store_true',
dest='force_8bit',
help='Force 8-bit color depth for all images'
)
parser.add_argument(
'--16bit', '-16',
action='store_true',
dest='force_16bit',
help='Force 16-bit color depth for all images'
)
args = parser.parse_args()
# Determine bit depth setting
if args.force_8bit and args.force_16bit:
print("Error: Cannot specify both --8bit and --16bit. Choose one.")
return
elif args.force_8bit:
force_bitdepth = '8'
print("Mode: Forcing 8-bit color depth")
elif args.force_16bit:
force_bitdepth = '16'
print("Mode: Forcing 16-bit color depth")
else:
force_bitdepth = None
print("Mode: Auto-detect bit depth (preserve 16-bit if present)")
input_dir = Path('input')
output_dir = Path('output')
@@ -181,7 +254,7 @@ def main():
with ProcessPoolExecutor(max_workers=max_workers) as executor:
# Submit all tasks
future_to_file = {
executor.submit(compress_png, str(f), str(get_output_path(f, input_dir, output_dir))): f
executor.submit(compress_png, str(f), str(get_output_path(f, input_dir, output_dir)), force_bitdepth): f
for f in png_files
}