Files
ComfyAssets-ComfyUI_PromptM…/py/api/__init__.py
T
Vito fc3266d455 fix(thumbnails): generate thumbnails automatically and use them everywhere (#316)
* fix(thumbnails): generate thumbnails automatically and use them everywhere

New outputs never got a preview, so the workspace grid loaded full-size
originals (844 of 19,907 images on a live install, exactly the newest).

- Listings always give images and videos a thumbnail URL; a missing
  preview is made by the serve route on first view (bounded, single
  flight per file) and falls back to the original, remembering files
  that cannot be decoded.
- The image monitor queues each settled output's preview on one
  background worker that follows Worker threads.
- A scan that leaves 200 or more previews missing starts the visible
  thumbnail job; fewer go through the worker.
- Automatic previews wait for a restore, a duplicate removal, a sources
  change, the gallery's clear and exclusive jobs.
- The inspector cover uses the preview; the Overview row counts
  previews that failed.

* fix(thumbnails): keep the video fallback tested and stop the preview worker before cleanup

A video listed without a preview still renders its own element and is
released on refresh. Test teardowns and the browser reset stop the
automatic preview worker before the temp tree goes, so no preview lands
after cleanup (Windows). TESTING.md documents automatic previews.

* fix(thumbnails): admit previews on the loop and never send a video to an img

Final review fixes for automatic previews:
- A video preview that cannot be made is the placeholder frame (no-store),
  never the video; OpenCV failures fall through to ffmpeg and the
  placeholder. Cards and the inspector cover swap back to the video
  element when the preview image fails.
- View requests are admitted on the event loop (3 writers, one flight per
  file, at most 64 waiting; past that the fallback at once). Writes run on
  a small dedicated pool, never the default executor. The history route
  shares the admission, flight key and link checks.
- Drive, UNC, empty and dot segments are refused as text; the folder
  listing runs inside the admission.
- Holds are checked after the slot and again before the rename; only
  decode failures are remembered.
- Bounded, logged shutdown: ffmpeg is killed, no worker restarts after
  cleanup, and a reload stops the old worker.
- The listing says whether the preview file exists (thumbnail_ready) for
  the legacy gallery's dot; media in a nested thumbnails folder keeps its
  original; file names the server quotes match in the inspector.

* fix(thumbnails): cover the image fallback card and document the admission

An image listed without a preview (a nested thumbnails folder) still
shows its original; TESTING.md describes the view admission, the video
placeholder, the holds before the rename and the bounded shutdown.

* fix(thumbnails): let an idle preview worker leave and fit case-insensitive filesystems

The capture worker exits once its queue is empty, so no thread outlives
its work; the next output starts a fresh one. The mixed-case source test
expects no folder listing where the exact name already resolves (macOS,
Windows).

* fix(thumbnails): answer shared flights with the outcome only and restart a failed worker

The history and serve routes share a flight key, so a flight now answers
only the ensure outcome whichever route started it; the serve route
derives the preview path and, for a fallback, looks its source up again
on the view pool. A view joining a history flight no longer gets a 500
or an image answered with the video placeholder.

The capture worker clears its running state however its loop ends, and a
worker that cannot start leaves the file queued for the next enqueue.
2026-10-24 08:35:14 -07:00

1129 lines
44 KiB
Python

"""REST API module for ComfyUI PromptManager.
Split into domain-specific mixins for maintainability:
- PromptRoutesMixin: prompt CRUD, tags, categories, bulk ops, export
- ImageRoutesMixin: gallery, thumbnails, image serving and linking
- AdminRoutesMixin: duplicates, stats, settings, diagnostics, maintenance, backup, scan
- LoggingRoutesMixin: log management endpoints
- AutotagRoutesMixin: auto-tagging model management and tagging
- JobRoutesMixin: the session job registry behind Activity (py/api/jobs.py)
- ImageTagJobsMixin: bulk Add tags / Auto-tag as image-tags jobs
- ThumbnailJobsMixin: thumbnail plan, thumbnail job and the gallery stream on it
- AutoThumbnailMixin: previews made on first view, on capture and after a scan
- ReviewRoutesMixin: the Needs review queue, item detail and decisions
- ReviewRecordingMixin: Needs review recording for the scan and the monitor
- ReviewEventsMixin: the Needs review change stream an open page re-reads on
- SystemRoutesMixin: System health check, Overview and usage statistics
- MaintenanceRoutesMixin: reviewed maintenance plans (preview, apply)
- WorkflowStorageRoutesMixin: store each workflow once, then Reclaim space
- DuplicateFilesMixin: duplicate image files as find and removal jobs
"""
import asyncio
import datetime
import functools
import gzip as gzip_module
import json
import math
import ntpath
import os
import re
from pathlib import Path
from aiohttp import web
from PIL import Image
from .prompts import PromptRoutesMixin
from .pairs import PairRoutesMixin
from .library import LibraryRoutesMixin
from .vocabulary import VocabularyRoutesMixin
from .annotations import AnnotationRoutesMixin
from .review import ReviewRoutesMixin
from .review_recording import ReviewRecordingMixin
from .review_events import ReviewEventsMixin
from .saved_views import SavedViewRoutesMixin
from .history import HistoryRoutesMixin
from .images import ImageRoutesMixin
from .admin import AdminRoutesMixin
from .settings_routes import SettingsRoutesMixin
from .job_routes import JobRoutesMixin
from .image_tag_jobs import ImageTagJobsMixin
from .thumbnail_jobs import ThumbnailJobsMixin
from .thumbnail_auto import AutoThumbnailMixin
from .system import SystemRoutesMixin
from .maintenance import MaintenanceRoutesMixin
from .workflow_storage import WorkflowStorageRoutesMixin
from .duplicate_files import DuplicateFilesMixin
from .maintenance_plans import PlanStore
from .jobs import JobRegistry
from .logging_routes import LoggingRoutesMixin
from .autotag_routes import AutotagRoutesMixin
from .lora_integration import LoraIntegrationMixin
try:
from ...database.operations import PromptDatabase
from ...utils.logging_config import get_logger
from ...utils.video_metadata import is_video_path, read_video_metadata
except ImportError:
import sys
sys.path.insert(
0, os.path.dirname(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
)
from database.operations import PromptDatabase
from utils.logging_config import get_logger
from utils.video_metadata import is_video_path, read_video_metadata
def _get_project_root():
"""Get the project root directory (3 levels up from py/api/__init__.py)."""
return os.path.dirname(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
def _public_path(path) -> str:
"""Render a server path for an API response without revealing the layout.
Returns the path relative to the ComfyUI base directory (or to the parent
of an opted-in extra gallery root), as a POSIX-style string, or just the
basename when the path is not under any of those anchors.
"""
if not path:
return ""
from ..config import GalleryConfig
try:
canonical = Path(os.path.normcase(os.path.realpath(str(path))))
except (OSError, ValueError):
return os.path.basename(str(path))
for anchor in GalleryConfig.path_anchors():
if canonical.is_relative_to(Path(anchor)):
return canonical.relative_to(Path(anchor)).as_posix() or "."
return canonical.name
def _public_error(exc: BaseException) -> str:
"""Error text safe for API responses: OSError paths reduced to basenames."""
if isinstance(exc, OSError):
parts = [exc.strerror or type(exc).__name__]
if exc.filename:
parts.append(os.path.basename(str(exc.filename)))
return ": ".join(parts)
return str(exc) or type(exc).__name__
# ── Static file serving ────────────────────────────────────────────────
# Only these extensions are ever served from web/lib and web/js; the map
# doubles as the allow-list.
STATIC_MIME_TYPES = {
".js": "application/javascript",
".mjs": "application/javascript",
".css": "text/css",
".map": "application/json",
".woff": "font/woff",
".woff2": "font/woff2",
".ttf": "font/ttf",
".png": "image/png",
".svg": "image/svg+xml",
".ico": "image/x-icon",
".html": "text/html",
}
_STATIC_SEPARATORS = re.compile(r"[\\/]+")
# Served by exact request path beside the extension allow-list: the browser's
# copy of the inspection node table (local Inspect resolves with it, #249).
STATIC_EXACT_FILES = {("js", "inspection-semantics.json"): "application/json"}
def _resolve_static_file(root, filepath, allowed=STATIC_MIME_TYPES):
"""Real path of ``filepath`` under ``root``, or None when it must not be served.
The request path is untrusted. It is rejected when it is empty, carries a
``..`` segment, is absolute on any platform (a leading slash or backslash,
a drive letter such as ``C:`` or a UNC ``\\\\server\\share`` prefix all
re-anchor ``os.path.join`` on Windows), has an extension outside
``allowed`` (STATIC_MIME_TYPES), or resolves (symlinks included) outside
``root``.
"""
if not isinstance(filepath, str) or not filepath:
return None
if (
os.path.isabs(filepath)
or ntpath.isabs(filepath)
or ntpath.splitdrive(filepath)[0]
):
return None
segments = _STATIC_SEPARATORS.split(filepath)
if any(segment in ("", ".", "..") for segment in segments):
return None
if os.path.splitext(filepath)[1].lower() not in allowed:
return None
try:
root_real = Path(os.path.normcase(os.path.realpath(root)))
candidate = Path(
os.path.normcase(os.path.realpath(os.path.join(root, *segments)))
)
except (OSError, ValueError):
return None
if candidate == root_real or not candidate.is_relative_to(root_real):
return None
return str(candidate)
# ── JSON request bodies ────────────────────────────────────────────────
JSON_BODY_MAX_BYTES = 1_000_000
_JSON_READ_CHUNK = 64 * 1024
def _json_error(message, status):
return web.json_response({"success": False, "error": message}, status=status)
async def _read_json_body(request, max_bytes=JSON_BODY_MAX_BYTES):
"""Read and parse a JSON object body of at most ``max_bytes``.
The body is read in chunks so an oversized or chunked upload is refused
as soon as it crosses the cap rather than buffered whole.
Returns:
(data, None) on success, or (None, response) where ``response`` is a
413 (body too large) or 400 (invalid JSON, or not a JSON object).
"""
too_large = _json_error(f"Request body too large (max {max_bytes} bytes)", 413)
declared = request.content_length
if declared is not None and declared > max_bytes:
return None, too_large
chunks = []
size = 0
async for chunk in request.content.iter_chunked(_JSON_READ_CHUNK):
size += len(chunk)
if size > max_bytes:
return None, too_large
chunks.append(chunk)
try:
data = json.loads(b"".join(chunks).decode("utf-8"))
except (UnicodeDecodeError, ValueError):
return None, _json_error("Request body must be valid JSON", 400)
if not isinstance(data, dict):
return None, _json_error("Request body must be a JSON object", 400)
return data, None
class _LongJobGuard:
"""Async context manager handed out by ``_acquire_long_job``."""
def __init__(self, lock):
self._lock = lock
async def __aenter__(self):
# The caller checked ``locked()`` on this same loop iteration, so this
# acquire never waits.
await self._lock.acquire()
return self
async def __aexit__(self, exc_type, exc, tb):
self._lock.release()
return False
# ── Gzip compression middleware ────────────────────────────────────────
_GZIP_MIN_SIZE = 1024 # Only compress bodies larger than 1 KB
_GZIP_TYPES = frozenset(
(
"application/json",
"text/html",
"text/css",
"application/javascript",
"text/plain",
)
)
_gzip_registered = False
@web.middleware
async def _gzip_middleware(request, handler):
"""Compress PromptManager responses when the client accepts gzip."""
response = await handler(request)
if not request.path.startswith("/prompt_manager/"):
return response
# Only handle regular Response objects (not StreamResponse/WebSocket)
if not isinstance(response, web.Response):
return response
if "gzip" not in request.headers.get("Accept-Encoding", ""):
return response
if "Content-Encoding" in response.headers:
return response
body = response.body
if body is None or len(body) < _GZIP_MIN_SIZE:
return response
content_type = response.content_type or ""
if not any(ct in content_type for ct in _GZIP_TYPES):
return response
compressed = gzip_module.compress(body, compresslevel=6)
if len(compressed) >= len(body):
return response
response.body = compressed
response.headers["Content-Encoding"] = "gzip"
response.headers["Vary"] = "Accept-Encoding"
return response
class PromptManagerAPI(
PairRoutesMixin,
LibraryRoutesMixin,
VocabularyRoutesMixin,
AnnotationRoutesMixin,
ReviewRoutesMixin,
ReviewRecordingMixin,
ReviewEventsMixin,
SavedViewRoutesMixin,
HistoryRoutesMixin,
PromptRoutesMixin,
ImageRoutesMixin,
AdminRoutesMixin,
SettingsRoutesMixin,
JobRoutesMixin,
ImageTagJobsMixin,
ThumbnailJobsMixin,
AutoThumbnailMixin,
SystemRoutesMixin,
MaintenanceRoutesMixin,
WorkflowStorageRoutesMixin,
DuplicateFilesMixin,
LoggingRoutesMixin,
AutotagRoutesMixin,
LoraIntegrationMixin,
):
"""REST API handler for PromptManager operations and web interface.
This class provides comprehensive REST API endpoints for managing prompts,
images, and system operations. It handles database interactions, file
operations, image processing, and web UI serving.
The API is designed to integrate seamlessly with ComfyUI's aiohttp server
and provides both JSON API endpoints and static file serving for the
web interface.
Attributes:
logger: Configured logger instance for API operations
db (PromptDatabase): Database connection and operations handler
"""
def __init__(self, db: PromptDatabase | None = None) -> None:
"""Initialize the API, using an injected database before any cleanup."""
self.logger = get_logger("prompt_manager.api")
self.logger.info("Initializing PromptManager API")
self.db = db if db is not None else PromptDatabase()
self._history_read_fence = None
self._history_reads_closed = False
# Private media captures of the annotation routes (py/api/annotations.py),
# created on first use with their restore subscription.
self._captures = None
self._captures_unsubscribe = None
# Set by close_annotation_captures (shutdown): no store is recreated.
self._captures_closed = False
self._cached_output_dir = None # Lazy-cached by _find_comfyui_output_dir()
self._html_cache = {} # Cached HTML file contents keyed by path
self._gallery_cache = {} # dict: path_str -> (files, timestamp)
self._gallery_cache_ttl = 30 # Cache TTL in seconds
# Workspace listing values and sort orders derived from a cached scan
# (py/api/images.py _workspace_listed/_workspace_orders).
self._workspace_listed_cache = {}
self._workspace_order_cache = {}
# Card facts (dimensions, seed, positive title) per root and
# (path, mtime), kept and pruned with the per-file values
# (py/api/images.py _card_facts).
self._workspace_card_cache = {}
# Favorite keys of each root's cached scan (images._favorite_listing).
self._favorite_listing_cache = {}
# Single-flight locks for long jobs, keyed by job family; see
# _acquire_long_job(). Created lazily so no lock binds to an event
# loop before the server's loop exists.
self._long_jobs: dict = {}
# This session's jobs (py/api/jobs.py): the metadata scan, and later
# every other long operation the Activity page tracks.
self._jobs = JobRegistry(self.logger)
# The latest metadata scan job (also in self._jobs), if one was started.
self._scan_job = None
# Duplicate-file finds by job id, with the groups each one holds for
# review (py/api/duplicate_files.py); the last few only.
self._duplicate_finds = {}
# The last System health report this session and the database
# generation it describes, bumped when a restore replaces self.db
# (py/api/system.py).
self._health_report = None
self._db_generation = 0
# Reviewed maintenance plans under single-use tokens; a restart
# forgets them (py/api/maintenance.py).
self._maintenance_plans = PlanStore()
# A safety backup interrupted by a crash leaves its temp copy behind.
try:
from .maintenance import sweep_safety_temps
swept = sweep_safety_temps(self.db.model.db_path)
if swept:
self.logger.info(f"Removed {len(swept)} interrupted backup copies")
except Exception as e:
self.logger.warning(f"Could not sweep interrupted backup copies: {e}")
# Run cleanup on initialization to remove any existing duplicates
try:
removed = self.db.cleanup_duplicates()
if removed > 0:
self.logger.info(
f"Startup cleanup: removed {removed} duplicate prompts"
)
except Exception as e:
self.logger.error(f"Startup cleanup failed: {e}")
self.logger.info("PromptManager API initialization completed")
_public_path = staticmethod(_public_path)
_public_error = staticmethod(_public_error)
_read_json_body = staticmethod(_read_json_body)
def _acquire_long_job(self, name):
"""Claim the single-flight slot for a long job family, or None when busy.
Usage in a handler::
job = self._acquire_long_job("duplicates")
if job is None:
return self._long_job_busy_response("Duplicate scan")
async with job:
...
Families are free-form strings ("duplicates", "thumbnails",
"autotag", ...); the lock is released when the ``async with`` block
exits, including on exceptions. Must be called from the event loop.
"""
lock = self._long_jobs.setdefault(name, asyncio.Lock())
if lock.locked():
return None
return _LongJobGuard(lock)
@staticmethod
def _long_job_busy_response(label):
"""409 envelope for a long job that is already running."""
return _json_error(f"{label} already running", 409)
async def _run_held(self, kind, title, admission, operation):
"""Run a legacy-page operation under a registry hold (D80).
While ``operation()`` runs, the registry lists it as a running,
non-cancellable job, so workspace jobs its admission class conflicts
with are refused, naming it. When the registry refuses the hold, the
legacy 409 envelope names the running job and nothing is done. A
response of 400 or above ends the hold ``failed``.
"""
busy = self._jobs.blocker(kind, admission=admission)
if busy is not None:
return self._long_job_busy_response(busy.title)
async with self._jobs.hold(kind, title, admission=admission) as job:
response = await operation()
if getattr(response, "status", 200) >= 400:
job.finish("failed")
return response
async def _run_in_executor(self, func, *args, **kwargs):
"""Run a blocking function in the default thread pool executor.
Prevents synchronous database calls, file I/O, and PIL operations
from blocking the aiohttp event loop.
"""
loop = asyncio.get_event_loop()
if kwargs:
call = functools.partial(func, *args, **kwargs)
return await loop.run_in_executor(None, call)
return await loop.run_in_executor(None, func, *args)
def invalidate_gallery_cache(self):
"""Invalidate the cached gallery file listing.
Called by the image monitor when new files are detected. The workspace
keeps its per-file values and card facts, so the next request rebuilds
only new or changed files (see ImageRoutesMixin._workspace_listed and
_card_facts); its sort orders
are dropped, as the rescan replaces them anyway, and so is the
favorites lookup, which holds the old scan list.
"""
self._gallery_cache = {}
self._workspace_order_cache = {}
self._favorite_listing_cache = {}
def reset_gallery_roots_cache(self):
"""Drop every cached listing and derived workspace value (roots changed)."""
self.invalidate_gallery_cache()
self._workspace_listed_cache = {}
self._workspace_card_cache = {}
def add_routes(self, routes):
"""Register all API routes with the ComfyUI server.
Args:
routes: aiohttp RouteTableDef object from ComfyUI server instance.
"""
# Test route to verify registration works
@routes.get("/prompt_manager/test")
async def test_route(request):
return web.json_response(
{
"success": True,
"message": "PromptManager API is working!",
"timestamp": str(datetime.datetime.now()),
}
)
# ── Web UI serving routes ─────────────────────────────────────
@routes.get("/prompt_manager/workspace")
async def serve_workspace_ui(request: web.Request) -> web.Response:
return self._serve_html_page("workspace.html", "Workspace")
@routes.get("/prompt_manager/web")
async def serve_web_ui(request):
return self._serve_html_page("index.html", "Web UI", cache=False)
@routes.get("/prompt_manager/gallery.html")
async def serve_gallery_ui(request):
return self._serve_html_page("metadata.html", "Gallery")
@routes.get("/prompt_manager/admin")
async def serve_admin_ui(request):
return self._serve_html_page("admin.html", "Admin UI")
@routes.get("/prompt_manager/gallery")
async def serve_gallery_admin_ui(request):
return self._serve_html_page("gallery.html", "Gallery")
# ── Static file serving ───────────────────────────────────────
@routes.get("/prompt_manager/lib/{filepath:.*}")
async def serve_lib_static(request):
"""Serve static library files (JS, CSS) from web/lib directory."""
return self._serve_static_file("lib", request.match_info.get("filepath"))
@routes.get("/prompt_manager/js/{filepath:.*}")
async def serve_js_static(request):
"""Serve static JavaScript files from web/js directory."""
return self._serve_static_file("js", request.match_info.get("filepath"))
# ── Register domain-specific routes from mixins ───────────────
self._register_pair_routes(routes)
self._register_library_routes(routes)
self._register_vocabulary_routes(routes)
self._register_annotation_routes(routes)
self._register_review_routes(routes)
self._register_review_event_routes(routes)
self._register_saved_view_routes(routes)
self._register_history_routes(routes)
self._register_prompt_routes(routes)
self._register_image_routes(routes)
self._register_admin_routes(routes)
self._register_settings_routes(routes)
self._register_job_routes(routes)
self._register_system_routes(routes)
self._register_maintenance_routes(routes)
self._register_duplicate_routes(routes)
self._register_logging_routes(routes)
self._register_autotag_routes(routes)
self._register_lora_routes(routes)
# Register gzip compression middleware (once)
global _gzip_registered
if not _gzip_registered:
try:
from ..config import server_instance
server_instance.app.middlewares.append(_gzip_middleware)
_gzip_registered = True
self.logger.info("Gzip compression middleware registered")
except Exception as e:
self.logger.warning(f"Could not register gzip middleware: {e}")
self.logger.info("All routes registered with decorator pattern")
def _serve_static_file(self, subdir, filepath):
"""Serve ``web/<subdir>/<filepath>``; 403 outside it, 404 when missing."""
root = os.path.join(_get_project_root(), "web", subdir)
exact = STATIC_EXACT_FILES.get((subdir, filepath))
# An exact file passes the same containment check, its extension only.
allowed = STATIC_MIME_TYPES if exact is None else {".json"}
file_path = _resolve_static_file(root, filepath, allowed)
if file_path is None:
return web.Response(text="Forbidden", status=403)
content_type = (
exact or STATIC_MIME_TYPES[os.path.splitext(file_path)[1].lower()]
)
if not os.path.isfile(file_path):
return web.Response(text="Not Found", status=404)
with open(file_path, "rb") as f:
content = f.read()
return web.Response(body=content, content_type=content_type)
def _serve_html_page(self, filename, title, cache=True):
"""Serve ``web/<filename>``; 404 when missing, 500 when unreadable."""
html_path = os.path.join(_get_project_root(), "web", filename)
try:
if cache and html_path in self._html_cache:
content = self._html_cache[html_path]
elif os.path.exists(html_path):
with open(html_path, "r", encoding="utf-8") as f:
content = f.read()
if cache:
self._html_cache[html_path] = content
else:
return web.Response(
text=f"<h1>{title} not found</h1>"
"<p>HTML file not located at expected path.</p>",
content_type="text/html",
status=404,
)
return web.Response(text=content, content_type="text/html", charset="utf-8")
except Exception:
self.logger.exception(f"Failed to load {title}")
return web.Response(
text=f"<h1>Error</h1><p>Failed to load {title}. "
"Check server logs for details.</p>",
content_type="text/html",
status=500,
)
# ── Shared utilities used by multiple mixins ──────────────────────
def _enrich_images(self, images):
"""Add url and thumbnail_url to a flat list of image dicts."""
from urllib.parse import quote as url_quote
output_dirs = self._get_all_output_dirs()
for image in images:
image_path_str = image.get("image_path", "")
if not image_path_str:
continue
img_path = Path(image_path_str)
# Set fallback url via image ID
if image.get("id"):
image["url"] = f"/prompt_manager/images/{image['id']}/file"
# Try each root to compute relative path and thumbnail URL
for output_path in output_dirs:
try:
rel_path = img_path.resolve().relative_to(output_path.resolve())
image["relative_path"] = str(rel_path)
image["url"] = (
"/prompt_manager/images/serve/"
f"{url_quote(rel_path.as_posix(), safe='/')}"
)
# Check for thumbnail
rel_no_ext = rel_path.with_suffix("")
thumb_rel = (
f"thumbnails/{rel_no_ext.as_posix()}_thumb{rel_path.suffix}"
)
from .prompts import thumbnail_url_for
thumbnail_url = thumbnail_url_for(
thumb_rel, output_path / thumb_rel
)
if thumbnail_url:
image["thumbnail_url"] = thumbnail_url
break # Found matching root, stop searching
except (ValueError, RuntimeError):
continue # Try next root
return images
def _enrich_prompt_images(self, prompts):
"""Add url and thumbnail_url to each image in prompt results."""
for prompt in prompts:
self._enrich_images(prompt.get("images", []))
return prompts
def _clean_nan_recursive(self, obj):
"""Recursively replace NaN and Infinity in nested data with None."""
if isinstance(obj, dict):
return {key: self._clean_nan_recursive(value) for key, value in obj.items()}
elif isinstance(obj, list):
return [self._clean_nan_recursive(item) for item in obj]
elif isinstance(obj, float) and not math.isfinite(obj):
return None
else:
return obj
def _find_comfyui_output_dir(self):
"""Locate the ComfyUI output directory using multiple detection strategies.
Checks in order:
1. User-configured directory (GalleryConfig.MONITORING_DIRECTORIES)
2. Upward filesystem search for ComfyUI markers
3. Common installation path patterns
4. Common ComfyUI installation locations
Results are cached after first successful lookup. The cache is
invalidated when the user changes the configured directory via
save_settings().
Returns:
str or None: Absolute path to ComfyUI output directory, or None
if no valid directory is found
"""
if self._cached_output_dir is not None:
return self._cached_output_dir
# Method 0: Check user-configured directory first
try:
from ..config import GalleryConfig
if GalleryConfig.MONITORING_DIRECTORIES:
configured = GalleryConfig.MONITORING_DIRECTORIES[0]
# Same check as the settings endpoint: a root hand-edited
# into config.json must not open a directory outside ComfyUI
ok, reason = GalleryConfig.validate_gallery_root(configured)
if ok:
configured_dir = Path(configured).resolve()
self.logger.info(
f"Using configured monitoring directory: {configured_dir}"
)
self._cached_output_dir = str(configured_dir)
return self._cached_output_dir
self.logger.warning(f"Ignoring configured directory: {reason}")
except ImportError:
self.logger.debug(
"GalleryConfig not available, skipping configured directory check"
)
current_file = Path(__file__).resolve()
self.logger.debug(f"Starting ComfyUI output search from: {current_file}")
# Method 1: Search upward from current file location
current_dir = current_file.parent
max_depth = 10 # Prevent infinite loops
for i in range(max_depth):
# Check if current directory contains ComfyUI markers
comfyui_markers = ["main.py", "nodes.py", "server.py"]
if any((current_dir / marker).exists() for marker in comfyui_markers):
output_dir = current_dir / "output"
if output_dir.exists() and output_dir.is_dir():
self.logger.debug(
"Found ComfyUI output directory via upward search: "
f"{output_dir}"
)
self._cached_output_dir = str(output_dir)
return self._cached_output_dir
# Move up one directory
parent = current_dir.parent
if parent == current_dir: # Reached filesystem root
break
current_dir = parent
# Method 2: Try common installation patterns relative to this file
# File is at: custom_nodes/ComfyUI_PromptManager/py/api/__init__.py
base_dir = current_file.parent # .../py/api/
possible_paths = [
base_dir.parent.parent.parent.parent / "output", # ../../../../output
base_dir.parent.parent.parent / "output", # ../../../output
base_dir.parent.parent / "output", # ../../output
base_dir.parent / "output", # ../output
]
# Method 3: Add common ComfyUI installation locations
common_locations = [
Path.home() / "ComfyUI" / "output",
Path.cwd() / "output",
Path.cwd() / ".." / "output",
Path.cwd() / ".." / ".." / "output",
]
all_paths = possible_paths + common_locations
for path in all_paths:
try:
abs_path = path.resolve()
if abs_path.exists() and abs_path.is_dir():
self.logger.debug(f"Found ComfyUI output directory: {abs_path}")
self._cached_output_dir = str(abs_path)
return self._cached_output_dir
except (OSError, RuntimeError):
continue # Skip invalid paths
self.logger.warning("ComfyUI output directory not found. Searched paths:")
for path in all_paths:
try:
self.logger.warning(f" - {path.resolve()} (exists: {path.exists()})")
except (OSError, RuntimeError):
self.logger.warning(f" - {path} (invalid path)")
return None
def _get_all_output_dirs(self):
"""Get the directories images may be served from.
Configured gallery roots are filtered through
``GalleryConfig.validate_gallery_root`` so a root that was hand-edited
into config.json (or persisted before validation existed) can never
expose files outside ComfyUI's directories.
Returns:
List[Path]: Validated directory paths, possibly empty.
"""
return self._output_dirs_with_origin()[0]
def _output_dirs_with_origin(self):
"""``(dirs, auto_detected)``: the ``_get_all_output_dirs`` list, and
whether it comes from detection or ComfyUI's output rather than from
a valid configured root (False when there is no directory at all).
"""
from ..config import GalleryConfig
configured = list(GalleryConfig.MONITORING_DIRECTORIES)
output_dirs = []
seen = set()
for d in configured:
ok, reason = GalleryConfig.validate_gallery_root(d)
if not ok:
self.logger.warning(f"Ignoring configured gallery root: {reason}")
continue
real = os.path.realpath(d)
key = os.path.normcase(real) # one entry per directory, however spelled
if key in seen:
continue
seen.add(key)
output_dirs.append(Path(real))
if output_dirs:
return output_dirs, False
if configured:
# Every configured root was rejected: never let auto-detection
# resurrect it, serve ComfyUI's own output directory instead.
fallback_dirs = self._comfyui_output_dir_list()
else:
fallback = self._find_comfyui_output_dir()
fallback_dirs = [Path(fallback)] if fallback else []
return fallback_dirs, bool(fallback_dirs)
def _comfyui_output_dir_list(self):
"""ComfyUI's output directory as a one-element list, or [] if unknown."""
try:
import folder_paths
output_dir = folder_paths.get_output_directory()
except (ImportError, AttributeError, OSError):
return []
if isinstance(output_dir, str) and os.path.isdir(output_dir):
return [Path(os.path.realpath(output_dir))]
return []
def _extract_comfyui_metadata(self, image_path):
"""Embedded ComfyUI metadata of an image (PNG text chunks) or a video.
Videos go through ffprobe (see utils/video_metadata). Unreadable files
are a warning, not an error: a scan over a large output tree meets
truncated and foreign files, and it carries on past them.
"""
if is_video_path(image_path):
return read_video_metadata(image_path)
try:
with Image.open(image_path) as img:
return dict(getattr(img, "text", None) or {})
except Exception as e:
self.logger.warning(
f"Unreadable image {os.path.basename(str(image_path))}: {e}"
)
return {}
def _parse_comfyui_prompt(self, metadata):
"""Parse ComfyUI and A1111 prompt data from metadata."""
result = {
"prompt": None,
"workflow": None,
"parameters": {},
"positive_prompt": None,
"negative_prompt": None,
}
# Check for A1111/Forge style parameters first.
# The chunk is one block: a possibly multi-line positive prompt, then a
# "Negative prompt:" section, then a trailing "Steps: ..." settings line.
# Taking lines[0] as the positive prompt truncates any multi-line prompt
# to one line, so split on the settings line instead.
if "parameters" in metadata:
import re as _re
params = metadata["parameters"]
body = params
settings = ""
_sm = _re.search(r"\nSteps:\s", body)
if _sm:
settings = body[_sm.start() + 1 :].strip()
body = body[: _sm.start()]
negative = None
_nm = _re.search(r"(?im)^\s*negative prompt:\s*", body)
if _nm:
negative = body[_nm.end() :].strip()
body = body[: _nm.start()]
elif body.lower().lstrip().startswith("negative prompt:"):
negative = body.lower().lstrip()[len("negative prompt:") :].strip()
body = ""
result["positive_prompt"] = body.strip() or None
if negative:
result["negative_prompt"] = negative
# Store raw parameters too
result["parameters"]["parameters"] = params
if settings:
for _f in ("Steps", "Sampler", "Schedule type", "CFG scale", "Seed"):
_fm = _re.search(
r"(?i)(?:^|,\s*)" + _re.escape(_f) + r":\s*([^,]+)", settings
)
if _fm:
result["parameters"][_f.lower().replace(" ", "_")] = _fm.group(
1
).strip()
# If no A1111 format found, proceed with ComfyUI parsing
if result["positive_prompt"] is None:
# Check for direct prompt field
if "prompt" in metadata:
try:
prompt_data = json.loads(metadata["prompt"])
result["prompt"] = prompt_data
except json.JSONDecodeError:
result["prompt"] = metadata["prompt"]
# Check for workflow
if "workflow" in metadata:
try:
workflow_data = json.loads(metadata["workflow"])
result["workflow"] = workflow_data
except json.JSONDecodeError:
result["workflow"] = metadata["workflow"]
# Check for other common ComfyUI fields
common_fields = [
"positive",
"negative",
"steps",
"cfg",
"sampler",
"scheduler",
"seed",
]
for field in common_fields:
if field in metadata:
try:
result["parameters"][field] = json.loads(metadata[field])
except json.JSONDecodeError:
result["parameters"][field] = metadata[field]
return result
def _extract_readable_prompt(self, parsed_data):
"""Extract human-readable prompt text from ComfyUI/A1111 data."""
def safe_to_string(value):
if isinstance(value, str):
return value
elif isinstance(value, list):
return " ".join(str(item) for item in value if item)
elif value is not None:
return str(value)
return None
# First check if we already extracted a positive prompt (A1111 format)
if parsed_data.get("positive_prompt"):
return parsed_data["positive_prompt"]
# Check if prompt is already a string
if isinstance(parsed_data.get("prompt"), str):
return parsed_data["prompt"]
# Check if prompt is a simple value that can be converted
if parsed_data.get("prompt") and not isinstance(
parsed_data.get("prompt"), dict
):
return safe_to_string(parsed_data["prompt"])
prompt_data = parsed_data.get("prompt")
if isinstance(prompt_data, dict):
# Use the enhanced logic from parse-metadata.py
positive_prompt = self._extract_positive_prompt_from_comfyui_data(
prompt_data
)
if positive_prompt:
return positive_prompt
# Check workflow data if available
workflow_data = parsed_data.get("workflow")
if isinstance(workflow_data, dict):
positive_prompt = self._extract_positive_prompt_from_comfyui_data(
workflow_data
)
if positive_prompt:
return positive_prompt
# Check parameters for positive prompt
if parsed_data.get("parameters", {}).get("positive"):
return safe_to_string(parsed_data["parameters"]["positive"])
return None
def _get_node_inputs(self, node):
"""Safely get inputs from a node, handling both dict and list formats.
Old format: inputs is a dict with direct key-value pairs
inputs = {"text": "my prompt", "seed": 123}
New format: inputs is a list of connection objects
inputs = [
{"name": "text", "type": "STRING", "link": null,
"widget": {"name": "text"}},
{"name": "clip", "type": "CLIP", "link": 11}
]
"""
if not isinstance(node, dict):
return {}
inputs = node.get("inputs", {})
# If inputs is already a dict, return it
if isinstance(inputs, dict):
return inputs
# If inputs is a list, convert to dict format
if isinstance(inputs, list):
inputs_dict = {}
for input_item in inputs:
if isinstance(input_item, dict) and "name" in input_item:
name = input_item["name"]
inputs_dict[name] = input_item
return inputs_dict
return {}
def _find_text_in_node(self, node):
"""Try to find text content in a node using various strategies.
Handles both old and new workflow formats.
"""
if not isinstance(node, dict):
return None
# Strategy 1: Check normalized inputs for 'text' field
inputs = self._get_node_inputs(node)
if "text" in inputs and isinstance(inputs["text"], str):
return inputs["text"]
# Strategy 2: For text encoder nodes, check widgets_values
class_type = node.get("class_type", node.get("type", ""))
text_encoder_types = [
"CLIPTextEncode",
"CLIPTextEncodeSDXL",
"CLIPTextEncodeSDXLRefiner",
"CLIPTextEncodeFlux",
"PromptManager",
"PromptManagerText",
"BNK_CLIPTextEncoder",
"Text Encoder",
"CLIP Text Encode",
]
if any(
encoder_type.lower() in class_type.lower()
for encoder_type in text_encoder_types
):
widgets_values = node.get("widgets_values", [])
if widgets_values and len(widgets_values) > 0:
if isinstance(widgets_values[0], str) and widgets_values[0].strip():
return widgets_values[0]
return None
def _extract_positive_prompt_from_comfyui_data(self, data):
"""Extract positive prompt from ComfyUI data.
Handles both old and new formats.
"""
if not isinstance(data, dict):
return None
# Build nodes dictionary
nodes_by_id = {}
if "nodes" in data:
# Handle nodes array format
for node in data["nodes"]:
if isinstance(node, dict):
nid = node.get("id")
if nid is not None:
nodes_by_id[nid] = node
else:
# Handle flat dictionary format (node_id -> node_data)
for nid_str, node in data.items():
try:
nid = int(nid_str)
except (ValueError, TypeError):
nid = nid_str
if isinstance(node, dict):
if "id" in node:
nid = node["id"]
nodes_by_id[nid] = node
if not nodes_by_id:
return None
# First, try to find positive/negative connection pattern
pos_id = None
for node in nodes_by_id.values():
if isinstance(node, dict):
inputs = self._get_node_inputs(node)
if "positive" in inputs and "negative" in inputs:
try:
pos_input = inputs["positive"]
if isinstance(pos_input, list) and len(pos_input) > 0:
pos_id = int(pos_input[0])
break
except (ValueError, TypeError, IndexError):
continue
# Get text from the positive node
if pos_id is not None and pos_id in nodes_by_id:
text_val = self._find_text_in_node(nodes_by_id[pos_id])
if text_val:
return text_val
# Fallback: find any text encoder node with text content
text_nodes = []
for node in nodes_by_id.values():
if isinstance(node, dict):
text_val = self._find_text_in_node(node)
if text_val:
# Try to determine if this is positive or negative
node_title = node.get("title", "").lower()
if "neg" not in node_title and "negative" not in node_title:
# Prioritize non-negative prompts
text_nodes.insert(0, text_val)
else:
text_nodes.append(text_val)
# Return the first positive-looking prompt
if text_nodes:
return text_nodes[0]
return None