mirror of
https://github.com/Comfy-Org/ComfyUI.git
synced 2026-08-25 02:20:18 +08:00
Extract image dimensions into asset metadata (#13991)
Amp-Thread-ID: https://ampcode.com/threads/T-019e4ca5-b71a-7168-8f56-58b2325f34c3 Co-authored-by: Amp <amp@ampcode.com>
This commit is contained in:
@@ -33,6 +33,7 @@ from app.assets.services.file_utils import (
|
||||
verify_file_unchanged,
|
||||
)
|
||||
from app.assets.services.hashing import HashCheckpoint, compute_blake3_hash
|
||||
from app.assets.services.image_dimensions import extract_image_dimensions
|
||||
from app.assets.services.metadata_extract import extract_file_metadata
|
||||
from app.assets.services.path_utils import (
|
||||
compute_relative_filename,
|
||||
@@ -506,6 +507,10 @@ def enrich_asset(
|
||||
|
||||
if extract_metadata and metadata:
|
||||
system_metadata = metadata.to_user_metadata()
|
||||
if mime_type and mime_type.startswith("image/"):
|
||||
dims = extract_image_dimensions(file_path, mime_type=mime_type)
|
||||
if dims:
|
||||
system_metadata.update(dims)
|
||||
set_reference_system_metadata(session, reference_id, system_metadata)
|
||||
|
||||
if full_hash:
|
||||
|
||||
63
app/assets/services/image_dimensions.py
Normal file
63
app/assets/services/image_dimensions.py
Normal file
@@ -0,0 +1,63 @@
|
||||
"""Image dimension extraction for asset ingest.
|
||||
|
||||
Reads only the image header via Pillow to capture width/height cheaply,
|
||||
without a full pixel decode. Returns a metadata dict suitable for merging
|
||||
into ``AssetReference.system_metadata``.
|
||||
"""
|
||||
from __future__ import annotations
|
||||
|
||||
import logging
|
||||
from typing import Any
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
def extract_image_dimensions(
|
||||
file_path: str, mime_type: str | None = None
|
||||
) -> dict[str, Any] | None:
|
||||
"""Extract image dimensions for the file at ``file_path``.
|
||||
|
||||
Args:
|
||||
file_path: Absolute path to a file on disk.
|
||||
mime_type: Optional MIME type hint. When provided and not prefixed
|
||||
with ``image/``, extraction is skipped without touching the file.
|
||||
|
||||
Returns:
|
||||
``{"kind": "image", "width": W, "height": H}`` when the file is a
|
||||
recognizable image with positive dimensions, otherwise ``None``.
|
||||
|
||||
The dict shape is intended to be merged into ``system_metadata`` so the
|
||||
asset response surfaces ``metadata.kind`` plus dimension fields for image
|
||||
assets. Forward-compatible: future media kinds (e.g. ``"video"`` with
|
||||
duration/fps) can extend this shape without schema changes.
|
||||
"""
|
||||
if mime_type is not None and not mime_type.startswith("image/"):
|
||||
return None
|
||||
|
||||
try:
|
||||
from PIL import Image, UnidentifiedImageError
|
||||
except ImportError:
|
||||
logger.debug(
|
||||
"Pillow not available; skipping image dimension extraction for %s",
|
||||
file_path,
|
||||
)
|
||||
return None
|
||||
|
||||
try:
|
||||
with Image.open(file_path) as img:
|
||||
width, height = img.size
|
||||
except (OSError, UnidentifiedImageError, ValueError) as exc:
|
||||
logger.debug(
|
||||
"Failed to read image dimensions from %s: %s", file_path, exc
|
||||
)
|
||||
return None
|
||||
|
||||
if (
|
||||
not isinstance(width, int)
|
||||
or not isinstance(height, int)
|
||||
or width <= 0
|
||||
or height <= 0
|
||||
):
|
||||
return None
|
||||
|
||||
return {"kind": "image", "width": width, "height": height}
|
||||
@@ -17,9 +17,11 @@ from app.assets.database.queries import (
|
||||
get_reference_by_file_path,
|
||||
get_reference_tags,
|
||||
get_or_create_reference,
|
||||
list_references_by_asset_id,
|
||||
reference_exists,
|
||||
remove_missing_tag_for_asset_id,
|
||||
set_reference_metadata,
|
||||
set_reference_system_metadata,
|
||||
set_reference_tags,
|
||||
update_asset_hash_and_mime,
|
||||
upsert_asset,
|
||||
@@ -29,6 +31,7 @@ from app.assets.database.queries import (
|
||||
from app.assets.helpers import get_utc_now, normalize_tags
|
||||
from app.assets.services.bulk_ingest import batch_insert_seed_assets
|
||||
from app.assets.services.file_utils import get_size_and_mtime_ns
|
||||
from app.assets.services.image_dimensions import extract_image_dimensions
|
||||
from app.assets.services.path_utils import (
|
||||
compute_relative_filename,
|
||||
get_name_and_tags_from_asset_path,
|
||||
@@ -118,6 +121,14 @@ def _ingest_file_from_path(
|
||||
user_metadata=user_metadata,
|
||||
)
|
||||
|
||||
_maybe_store_image_dimensions(
|
||||
session,
|
||||
reference_id=reference_id,
|
||||
file_path=locator,
|
||||
mime_type=mime_type,
|
||||
current_system_metadata=ref.system_metadata,
|
||||
)
|
||||
|
||||
try:
|
||||
remove_missing_tag_for_asset_id(session, asset_id=asset.id)
|
||||
except Exception:
|
||||
@@ -288,6 +299,13 @@ def _register_existing_asset(
|
||||
user_metadata=new_meta,
|
||||
)
|
||||
|
||||
_backfill_image_dimensions_from_siblings(
|
||||
session,
|
||||
asset_id=asset.id,
|
||||
new_reference_id=ref.id,
|
||||
current_system_metadata=ref.system_metadata,
|
||||
)
|
||||
|
||||
if tags is not None:
|
||||
set_reference_tags(
|
||||
session,
|
||||
@@ -334,6 +352,87 @@ def _update_metadata_with_filename(
|
||||
)
|
||||
|
||||
|
||||
_IMAGE_DIMENSION_KEYS = ("kind", "width", "height")
|
||||
|
||||
|
||||
def _maybe_store_image_dimensions(
|
||||
session: Session,
|
||||
reference_id: str,
|
||||
file_path: str,
|
||||
mime_type: str | None,
|
||||
current_system_metadata: dict | None,
|
||||
) -> None:
|
||||
"""Populate ``kind``/``width``/``height`` on system_metadata for image refs.
|
||||
|
||||
Non-image MIME types are a no-op. Pre-existing keys (e.g. enricher-written
|
||||
safetensors metadata, download provenance) are preserved by merge.
|
||||
"""
|
||||
if not mime_type or not mime_type.startswith("image/"):
|
||||
return
|
||||
|
||||
dims = extract_image_dimensions(file_path, mime_type=mime_type)
|
||||
if not dims:
|
||||
return
|
||||
|
||||
current = current_system_metadata or {}
|
||||
merged = dict(current)
|
||||
merged.update(dims)
|
||||
if merged != current:
|
||||
set_reference_system_metadata(
|
||||
session,
|
||||
reference_id=reference_id,
|
||||
system_metadata=merged,
|
||||
)
|
||||
|
||||
|
||||
def _backfill_image_dimensions_from_siblings(
|
||||
session: Session,
|
||||
asset_id: str,
|
||||
new_reference_id: str,
|
||||
current_system_metadata: dict | None,
|
||||
) -> None:
|
||||
"""Copy image dimension keys from any sibling reference of the same asset.
|
||||
|
||||
The from-hash path doesn't read the file bytes, so dimensions can't be
|
||||
extracted there directly. When another reference of the same asset already
|
||||
carries image dimensions, copy them onto the new reference so consumers
|
||||
see consistent metadata regardless of how the asset was registered.
|
||||
|
||||
Best-effort: missing siblings, non-image siblings, or absent dimension
|
||||
keys leave the target reference unchanged.
|
||||
"""
|
||||
current = current_system_metadata or {}
|
||||
if current.get("kind") == "image" and "width" in current and "height" in current:
|
||||
return
|
||||
|
||||
for sibling in list_references_by_asset_id(session, asset_id):
|
||||
if sibling.id == new_reference_id:
|
||||
continue
|
||||
meta = sibling.system_metadata or {}
|
||||
if meta.get("kind") != "image":
|
||||
continue
|
||||
width = meta.get("width")
|
||||
height = meta.get("height")
|
||||
if (
|
||||
type(width) is not int
|
||||
or type(height) is not int
|
||||
or width <= 0
|
||||
or height <= 0
|
||||
):
|
||||
continue
|
||||
merged = dict(current)
|
||||
merged["kind"] = "image"
|
||||
merged["width"] = width
|
||||
merged["height"] = height
|
||||
if merged != current:
|
||||
set_reference_system_metadata(
|
||||
session,
|
||||
reference_id=new_reference_id,
|
||||
system_metadata=merged,
|
||||
)
|
||||
return
|
||||
|
||||
|
||||
def _sanitize_filename(name: str | None, fallback: str) -> str:
|
||||
n = os.path.basename((name or "").strip() or fallback)
|
||||
return n if n else fallback
|
||||
|
||||
Reference in New Issue
Block a user