Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
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
15 changes: 12 additions & 3 deletions comfy_execution/jobs.py
Original file line number Diff line number Diff line change
Expand Up @@ -56,6 +56,9 @@ def validate_job_id(value) -> str:
# 3D file extensions for preview fallback (no dedicated media_type exists)
THREE_D_EXTENSIONS = frozenset({'.obj', '.fbx', '.gltf', '.glb', '.usdz'})

# Text file extensions for preview fallback (the formats SaveText can produce)
TEXT_EXTENSIONS = frozenset({'.txt', '.md', '.json'})


def has_3d_extension(filename: str) -> bool:
lower = filename.lower()
Expand Down Expand Up @@ -143,9 +146,10 @@ def is_previewable(media_type: str, item: dict) -> bool:
Maintains backwards compatibility with existing logic.

Priority:
1. media_type is 'images', 'video', 'audio', or '3d'
1. media_type is 'images', 'video', 'audio', '3d', or 'text'
2. format field starts with 'video/' or 'audio/'
3. filename has a 3D extension (.obj, .fbx, .gltf, .glb, .usdz)
4. filename has a text extension (.txt, .md, .json, ...)
"""
if media_type in PREVIEWABLE_MEDIA_TYPES:
return True
Expand All @@ -156,10 +160,12 @@ def is_previewable(media_type: str, item: dict) -> bool:
if fmt and (fmt.startswith('video/') or fmt.startswith('audio/')):
return True

# Check for 3D files by extension
# Check for 3D and text files by extension
filename = item.get('filename', '').lower()
if any(filename.endswith(ext) for ext in THREE_D_EXTENSIONS):
return True
if any(filename.endswith(ext) for ext in TEXT_EXTENSIONS):
return True

return False

Expand Down Expand Up @@ -255,6 +261,10 @@ def get_outputs_summary(outputs: dict) -> tuple[int, Optional[dict]]:
Preview priority (matching frontend):
1. type="output" with previewable media
2. Any previewable media

Text content entries (strings under 'text') are preview-only metadata,
matching the frontend's METADATA_KEYS: they can serve as the fallback
preview but are not counted as outputs.
"""
count = 0
preview_output = None
Expand All @@ -275,7 +285,6 @@ def get_outputs_summary(outputs: dict) -> tuple[int, Optional[dict]]:
if normalized is None:
# Not a 3D file string — check for text preview
if media_type == 'text':
count += 1
if preview_output is None:
if isinstance(item, tuple):
text_value = item[0] if item else ''
Expand Down
132 changes: 129 additions & 3 deletions comfy_extras/nodes_bounding_boxes.py
Original file line number Diff line number Diff line change
@@ -1,3 +1,5 @@
import json

import numpy as np
import torch
from PIL import Image, ImageDraw, ImageEnhance, ImageFont
Expand Down Expand Up @@ -166,6 +168,111 @@ def boxes_to_regions(boxes, width: int, height: int) -> list:
return regions


def normalize_incoming_boxes(bboxes) -> list:
if isinstance(bboxes, dict):
frame = [bboxes]
elif not isinstance(bboxes, list) or not bboxes:
frame = []
elif isinstance(bboxes[0], dict):
frame = bboxes
else:
frame = bboxes[0] if isinstance(bboxes[0], list) else []
boxes = []
for box in frame:
if not isinstance(box, dict):
continue
norm = {
"x": box.get("x", 0),
"y": box.get("y", 0),
"width": box.get("width", 0),
"height": box.get("height", 0),
}
meta = box.get("metadata")
if isinstance(meta, dict):
norm["metadata"] = meta
boxes.append(norm)
return boxes


def _looks_like_element(box: dict) -> bool:
bbox = box.get("bbox")
return isinstance(bbox, (list, tuple)) and len(bbox) == 4


def _looks_like_bbox(box: dict) -> bool:
return all(key in box for key in ("x", "y", "width", "height"))


def elements_to_boxes(elements: list, width: int, height: int) -> list:
boxes = []
for element in elements:
if not isinstance(element, dict):
continue
bbox = element.get("bbox")
if not (isinstance(bbox, (list, tuple)) and len(bbox) == 4):
raise ValueError("bboxes element is missing a valid 'bbox' [ymin, xmin, ymax, xmax]")
try:
ymin, xmin, ymax, xmax = (float(v) / 1000.0 for v in bbox)
except (TypeError, ValueError):
raise ValueError("bboxes element 'bbox' must contain four numbers")
etype = "text" if element.get("type") == "text" else "obj"
boxes.append({
"x": round(min(xmin, xmax) * width),
"y": round(min(ymin, ymax) * height),
"width": round(abs(xmax - xmin) * width),
"height": round(abs(ymax - ymin) * height),
"metadata": {
"type": etype,
"text": element.get("text", "") if etype == "text" else "",
"desc": element.get("desc", ""),
"palette": element.get("color_palette", []) or [],
},
})
return boxes


def boxes_from_input(data, width: int, height: int) -> list:
if data is None:
return []
if isinstance(data, str):
text = data.strip()
if not text:
return []
try:
data = json.loads(text)
except (ValueError, TypeError) as exc:
raise ValueError(f"bboxes string input is not valid JSON: {exc}") from exc
if isinstance(data, dict):
if _looks_like_element(data):
return elements_to_boxes([data], width, height)
if _looks_like_bbox(data):
return normalize_incoming_boxes(data)
raise ValueError(
"bboxes dict must be a bounding box (x, y, width, height) or an element (with a 'bbox')"
)
if not isinstance(data, list):
raise ValueError(
"bboxes input must be bounding boxes, elements, or a JSON string, "
f"got {type(data).__name__}"
)
if not data:
return []
first = data[0]
if isinstance(first, list):
return normalize_incoming_boxes(data)
if isinstance(first, dict):
if _looks_like_element(first):
return elements_to_boxes(data, width, height)
if _looks_like_bbox(first):
return normalize_incoming_boxes(data)
raise ValueError(
"bboxes items must be bounding boxes (x, y, width, height) or elements (with a 'bbox')"
)
raise ValueError(
f"bboxes list must contain bounding boxes or elements, got {type(first).__name__}"
)


def _norm_bbox(region: dict) -> list[int]:
def grid(value: float) -> int:
return max(0, min(1000, round(value * 1000)))
Expand Down Expand Up @@ -217,29 +324,48 @@ def define_schema(cls):
optional=True,
tooltip="Optional image used as background in the canvas and preview.",
),
io.MultiType.Input(
"bboxes",
[io.BoundingBox, io.Array, io.String],
optional=True,
tooltip="Bounding boxes, elements, or a JSON string to initialize the canvas. A new upstream value initializes the canvas; edits made on the canvas take priority and are kept until the upstream value changes again.",
),
io.Int.Input("width", default=1024, min=64, max=16384, step=16,
tooltip="Width of the canvas and the pixel grid for the bounding boxes."),
io.Int.Input("height", default=1024, min=64, max=16384, step=16,
tooltip="Height of the canvas and the pixel grid for the bounding boxes."),
editor_state,
io.BoundingBoxes.Input(
"last_incoming",
optional=True,
tooltip="Internal state managed by the canvas: the upstream bboxes value that last initialized it. Leave empty to re-initialize the canvas from the bboxes input on the next run.",
),
],
outputs=[
io.Image.Output(display_name="preview"),
io.BoundingBox.Output(display_name="bboxes"),
io.Array.Output(display_name="elements"),
],
is_output_node=True,
is_experimental=True,
)

@classmethod
def execute(cls, width, height, editor_state=None, background=None) -> io.NodeOutput:
regions = boxes_to_regions(editor_state, width, height)
def execute(cls, width, height, editor_state=None, last_incoming=None, background=None, bboxes=None) -> io.NodeOutput:
incoming = boxes_from_input(bboxes, width, height)
applied = last_incoming if isinstance(last_incoming, list) else []
upstream_changed = bool(incoming) and incoming != applied
source = incoming if upstream_changed else (editor_state or [])
regions = boxes_to_regions(source, width, height)
preview = render_preview(regions, width, height, _bg_from_image(background))
ui = {"dims": [width, height]}
if incoming:
ui["input_bboxes"] = incoming
return io.NodeOutput(
preview,
fractions_to_bbox_frame(regions, width, height),
build_elements(regions),
ui={"dims": [width, height]},
ui=ui,
)


Expand Down
158 changes: 156 additions & 2 deletions comfy_extras/nodes_save_3d.py
Original file line number Diff line number Diff line change
Expand Up @@ -13,7 +13,7 @@

import folder_paths
from comfy.cli_args import args
from comfy_api.latest import ComfyExtension, IO, Types
from comfy_api.latest import ComfyExtension, IO, Types, UI


def pack_variable_mesh_batch(vertices, faces, colors=None, uvs=None, texture=None, unlit=False):
Expand Down Expand Up @@ -406,10 +406,164 @@ def execute(cls, mesh: Types.MESH | Types.File3D, filename_prefix: str) -> IO.No
return IO.NodeOutput(ui={"3d": results})


def _save_file3d_to_output(model_3d: Types.File3D, filename_prefix: str) -> str:
full_output_folder, filename, counter, subfolder, filename_prefix = folder_paths.get_save_image_path(
filename_prefix, folder_paths.get_output_directory()
)
ext = model_3d.format or "glb"
saved_filename = f"{filename}_{counter:05}.{ext}"
model_3d.save_to(os.path.join(full_output_folder, saved_filename))
return f"{subfolder}/{saved_filename}" if subfolder else saved_filename


def execute_save_3d_advanced(model_3d, viewport_state, width, height, filename_prefix, kwargs) -> IO.NodeOutput:
model_file = _save_file3d_to_output(model_3d, filename_prefix)
camera_info_input = kwargs.get("camera_info", None)
camera_info = camera_info_input if camera_info_input is not None else viewport_state['camera_info']
model_3d_info_input = kwargs.get("model_3d_info", None)
model_3d_info = model_3d_info_input if model_3d_info_input is not None else viewport_state.get('model_3d_info', [])
return IO.NodeOutput(
model_3d,
model_3d_info,
camera_info,
width,
height,
ui=UI.PreviewUI3DAdvanced(model_file, camera_info, model_3d_info),
)


class Save3DAdvanced(IO.ComfyNode):
@classmethod
def define_schema(cls):
return IO.Schema(
node_id="Save3DAdvanced",
display_name="Save 3D (Advanced)",
search_aliases=["save 3d", "export 3d model", "save mesh advanced"],
category="3d",
is_experimental=True,
is_output_node=True,
inputs=[
IO.MultiType.Input(
"model_3d",
types=[
IO.File3DGLB,
IO.File3DGLTF,
IO.File3DFBX,
IO.File3DOBJ,
IO.File3DSTL,
IO.File3DUSDZ,
IO.File3DAny,
],
tooltip="3D model file from an upstream 3D node.",
),
IO.String.Input("filename_prefix", default="3d/ComfyUI"),
IO.Load3D.Input("viewport_state"),
IO.Load3DModelInfo.Input("model_3d_info", optional=True, advanced=True),
IO.Load3DCamera.Input("camera_info", optional=True, advanced=True),
IO.Int.Input("width", default=1024, min=1, max=4096, step=1),
IO.Int.Input("height", default=1024, min=1, max=4096, step=1),
],
outputs=[
IO.File3DAny.Output(display_name="model_3d"),
IO.Load3DModelInfo.Output(display_name="model_3d_info"),
IO.Load3DCamera.Output(display_name="camera_info"),
IO.Int.Output(display_name="width"),
IO.Int.Output(display_name="height"),
],
)

@classmethod
def execute(cls, model_3d: Types.File3D, viewport_state, width: int, height: int, filename_prefix: str, **kwargs) -> IO.NodeOutput:
return execute_save_3d_advanced(model_3d, viewport_state, width, height, filename_prefix, kwargs)


class SaveGaussianSplat(IO.ComfyNode):
@classmethod
def define_schema(cls):
return IO.Schema(
node_id="SaveGaussianSplat",
display_name="Save Splat",
search_aliases=["save splat", "save gaussian splat", "export gaussian", "export splat"],
category="3d",
is_experimental=True,
is_output_node=True,
inputs=[
IO.MultiType.Input(
"model_3d",
types=[
IO.File3DSplatAny,
IO.File3DPLY,
IO.File3DSPLAT,
IO.File3DSPZ,
IO.File3DKSPLAT,
],
tooltip="A gaussian splat 3D file.",
),
IO.String.Input("filename_prefix", default="3d/ComfyUI"),
IO.Load3D.Input("viewport_state"),
IO.Load3DModelInfo.Input("model_3d_info", optional=True, advanced=True),
IO.Load3DCamera.Input("camera_info", optional=True, advanced=True),
IO.Int.Input("width", default=1024, min=1, max=4096, step=1),
IO.Int.Input("height", default=1024, min=1, max=4096, step=1),
],
outputs=[
IO.File3DSplatAny.Output(display_name="model_3d"),
IO.Load3DModelInfo.Output(display_name="model_3d_info"),
IO.Load3DCamera.Output(display_name="camera_info"),
IO.Int.Output(display_name="width"),
IO.Int.Output(display_name="height"),
],
)

@classmethod
def execute(cls, model_3d: Types.File3D, viewport_state, width: int, height: int, filename_prefix: str, **kwargs) -> IO.NodeOutput:
return execute_save_3d_advanced(model_3d, viewport_state, width, height, filename_prefix, kwargs)


class SavePointCloud(IO.ComfyNode):
@classmethod
def define_schema(cls):
return IO.Schema(
node_id="SavePointCloud",
display_name="Save Point Cloud",
search_aliases=["save point cloud", "save pointcloud", "export point cloud"],
category="3d",
is_experimental=True,
is_output_node=True,
inputs=[
IO.MultiType.Input(
"model_3d",
types=[
IO.File3DPointCloudAny,
IO.File3DPLY,
],
tooltip="Point cloud file (.ply)",
),
IO.String.Input("filename_prefix", default="3d/ComfyUI"),
IO.Load3D.Input("viewport_state"),
IO.Load3DModelInfo.Input("model_3d_info", optional=True, advanced=True),
IO.Load3DCamera.Input("camera_info", optional=True, advanced=True),
IO.Int.Input("width", default=1024, min=1, max=4096, step=1),
IO.Int.Input("height", default=1024, min=1, max=4096, step=1),
],
outputs=[
IO.File3DPointCloudAny.Output(display_name="model_3d"),
IO.Load3DModelInfo.Output(display_name="model_3d_info"),
IO.Load3DCamera.Output(display_name="camera_info"),
IO.Int.Output(display_name="width"),
IO.Int.Output(display_name="height"),
],
)

@classmethod
def execute(cls, model_3d: Types.File3D, viewport_state, width: int, height: int, filename_prefix: str, **kwargs) -> IO.NodeOutput:
return execute_save_3d_advanced(model_3d, viewport_state, width, height, filename_prefix, kwargs)


class Save3DExtension(ComfyExtension):
@override
async def get_node_list(self) -> list[type[IO.ComfyNode]]:
return [SaveGLB]
return [SaveGLB, Save3DAdvanced, SaveGaussianSplat, SavePointCloud]


async def comfy_entrypoint() -> Save3DExtension:
Expand Down
Loading
Loading