Save 4 hours! We auto-setup your workflow! Free!

Drop your workflow.json — we handle every dependency, custom node, and model. Just open the link and run.

Auto-Setup Workflow Json (Free) Now!
ComfyUI > Nodes > ComfyUI-OOP > OOP Pose 🧍

ComfyUI Node: OOP Pose 🧍

Class Name

OOPPoseNode

Category
Object-Oriented Prompting
Author
0xravenblack (Account age: 2253days)
Extension
ComfyUI-OOP
Latest Updated
2025-03-02
Github Stars
0.02K

How to Install ComfyUI-OOP

Install this extension via the ComfyUI Manager by searching for ComfyUI-OOP
  • 1. Click the Manager button in the main menu
  • 2. Select Custom Nodes Manager button
  • 3. Enter ComfyUI-OOP in the search bar
After installation, click the Restart button to restart ComfyUI. Then, manually refresh your browser to clear the cache and access the updated list of nodes.

Visit ComfyUI Online for ready-to-use ComfyUI environment

  • Free trial available
  • 16GB VRAM to 80GB VRAM GPU machines
  • 400+ preloaded models/nodes
  • Freedom to upload custom models/nodes
  • 200+ ready-to-run workflows
  • 100% private workspace with up to 200GB storage
  • Dedicated Support

Run ComfyUI Online

OOP Pose 🧍 Description

Builds an OOP prompt pose section from optional body, hand, and leg presets, with randomization.

OOP Pose 🧍:

OOPPoseNode builds the pose section of an object-oriented prompt. It lets you describe the body, hands, and legs separately, so you can combine pose details without writing that section by hand. You can leave a detail out when it does not matter to your image, or vary the pose between executions when exploring ideas. The resulting pose section is intended to connect to an OOP Node; it describes a pose but does not generate an image on its own.

OOP Pose 🧍 Input Parameters:

base_pose

Sets the body pose or action. It contributes the body pair to the pose section unless you choose the blank option. The default is Stand. Options are the blank option, Sitting, Stand, Squat, Groove, Lie, Jump, Run, Walk, Fly, HeadTilt, LookingBack, LookingDown, LookingUp, Smelling, Sleeping, Bathing, AimingAtViewer, Stretching, HandsOnHips, BreastsRestOnTable, HugFromBehind, LeaningForward, and Selfie. This is a preset selection, so there is no numeric minimum or maximum. When randomize is enabled, the node selects from this list instead of using your chosen value.

hand_pose

Sets the hand or arm pose. It contributes the hands pair unless you choose the blank option. The default is Stretch. Options are the blank option, HandToMouth, ArmAtSide, ArmsBehindHead, ArmsBehindBack, HandOnOwnChest, ArmsCrossed, HandOnHips, HandOnHip, HandsUp, Stretch, Armpits, LegHold, Grabbing, Holding, Fingersmile, HairPull, HairScrunchie, PeaceSymbol, Salute, ThumbsUp, MiddleFinger, CatPose, FingerGun, Waving, and SpreadArms. This is a preset selection with no numeric minimum or maximum. When randomize is enabled, the node selects from this list instead of using your chosen value.

leg_pose

Sets the leg position or related lower-body pose. It contributes the legs pair unless you choose the blank option. The default is AgainstWall. Options are the blank option, SpreadLegs, CrossedLegs, FetalPosition, LegLift, LegsUp, LeaningForward, AgainstWall, OnStomach, Seiza, Wariza, Yokozuwari, IndianStyle, LegHug, Straddling, Kneeling, ArmSupport, FeetUp, OneKnee, StandingOnOneLeg, and KneesUp. This is a preset selection with no numeric minimum or maximum. When randomize is enabled, the node selects from this list instead of using your chosen value.

randomize

Controls whether the node uses your selected pose presets or chooses a value for each of the three pose categories. The default is False. The available values are False and True; there is no numeric range. With False, your selections determine the pose section. With True, the node chooses separately from each category’s options, including its blank option, and requests re-evaluation on each execution. This is useful for exploring variations, but it means a category may be omitted from a randomized result.

OOP Pose 🧍 Output Parameters:

pose

The single OOP_POSE output contains the assembled pose section, ready to connect to an OOP Node. It is formed from the selected or randomized body, hands, and legs values, using the pair names body, hands, and legs in that order. A blank option leaves its corresponding pair out. The exact punctuation and spacing of the formatted section are determined by the shared formatting function, whose implementation is not included in the provided source.

OOP Pose 🧍 Usage Tips:

  • Keep randomize set to False when you need a specific, repeatable pose. Choose a body pose first, then add hand and leg details that fit the scene.
  • Select the blank option for any pose category you do not need. For example, you can specify a body pose without adding a hand or leg instruction.
  • Turn randomize on when you want pose variations across executions. Your visible preset selections will not control the randomized result while it is enabled.
  • If a randomized result lacks a body, hand, or leg detail, remember that the blank option is among the choices. Turn off randomize and select the required details when they must always appear.
  • Connect pose to an input that accepts OOP_POSE, such as the intended OOP Node connection. This output is a pose section, not an image.

OOP Pose 🧍 Common Errors and Solutions:

Invalid value for base_pose, hand_pose, or leg_pose

  • Explanation: An invalid-choice message may appear if a saved workflow or external connection supplies a value outside the corresponding preset list. The source does not specify the exact wording of a validation error.
  • Solution: Reopen the affected dropdown and choose one of its listed options, then run the workflow again.

Type mismatch when connecting pose

  • Explanation: A connection error may occur if you attach the OOP_POSE output to an input expecting a different data type. The source does not specify the exact wording of this error.
  • Solution: Connect pose to a compatible OOP_POSE input, such as the intended input on an OOP Node.

A selected pose does not appear in the result

  • Explanation: This is expected when randomize is True: the node replaces all three selected pose values with independently chosen values before assembling the result.
  • Solution: Set randomize to False to use the presets shown in the dropdowns.

A pose category is missing from the result

  • Explanation: The blank option leaves its category out of the pose section. It can be selected directly or chosen during randomization; this behavior is not an error.
  • Solution: Set randomize to False and choose a nonblank option for every category you need.

The result has no pose details

  • Explanation: If all three categories use the blank option, none contributes a pose pair. The same combination may be selected during randomization. The exact appearance of the formatted result is not established by the provided source.
  • Solution: Choose at least one nonblank pose option. For a guaranteed detail, keep randomize set to False.

OOP Pose 🧍 Related Nodes

Go back to the extension to check out more related nodes.
ComfyUI-OOP
RunComfy
Copyright 2025 RunComfy. All Rights Reserved.

RunComfy is the premier ComfyUI platform, offering ComfyUI online environment and services, along with ComfyUI workflows featuring stunning visuals. RunComfy also provides AI Models, enabling artists to harness the latest AI tools to create incredible art.