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 > VideoX-Fun > Load Wan Lora

ComfyUI Node: Load Wan Lora

Class Name

LoadWanLora

Category
CogVideoXFUNWrapper
Author
aigc-apps (Account age: 1192days)
Extension
VideoX-Fun
Latest Updated
2026-11-14
Github Stars
2.34K

How to Install VideoX-Fun

Install this extension via the ComfyUI Manager by searching for VideoX-Fun
  • 1. Click the Manager button in the main menu
  • 2. Select Custom Nodes Manager button
  • 3. Enter VideoX-Fun 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

Load Wan Lora Description

Adds a selected LoRA file, strength, and cache setting to a Wan workflow configuration.

Load Wan Lora:

LoadWanLora adds a selected LoRA to the configuration carried through a Wan workflow. A LoRA is an add-on that can influence a model’s results; this node records which local LoRA file to use and how strongly to apply it. You can add more than one by placing multiple LoadWanLora nodes in sequence. The node prepares this information for later workflow steps; its source code does not show it loading LoRA weights or generating an image or video.

Load Wan Lora Input Parameters:

funmodels

The required FunModels configuration from an earlier node. LoadWanLora makes a copy of this configuration, preserves its existing information, and adds the selected LoRA to any LoRAs already recorded there. Connect a compatible FunModels output so the configuration can continue through the workflow. No default, minimum, or maximum is specified.

lora_name

The LoRA file to add. Its choices are discovered from your local loras folder at runtime, so the available names depend on the files in your installation. The source specifies a default of None; it does not provide a fixed list of file choices. When the value is None, the node returns a copy of the incoming configuration without adding a LoRA or changing its LoRA cache setting. When you select a file, the node records that file’s full path for later use.

strength_model

The strength value recorded alongside the selected LoRA for later workflow steps. Its default is 1.0, its minimum is -100.0, its maximum is 100.0, and its adjustment step is 0.01. This node stores the number but does not itself apply the LoRA, so the exact visual effect depends on how a later node uses the configuration. The value is added only when lora_name is selected.

lora_cache

A setting recorded in the configuration when a LoRA is selected. The available options are False and True, with False as the default. This node stores the choice but does not itself perform or demonstrate caching, so any performance effect depends on later workflow steps. If lora_name is None, this setting is not changed by the node.

Load Wan Lora Output Parameters:

funmodels

The updated FunModels configuration for the next node in your workflow. It retains the incoming configuration’s existing information. If you selected a LoRA, it also contains that file’s full path appended to the existing LoRA list, its corresponding strength_model value appended to the existing strength list, and the chosen lora_cache setting. If no LoRA was selected, it contains no additions from this node. The output is configuration data, not a rendered result or proof that the LoRA was successfully applied.

Load Wan Lora Usage Tips:

  • Select lora_name from the files actually shown in your local loras list. If the file you expect is absent, check that it is installed in the folder your setup uses for LoRAs and refresh the available choices.
  • Start with the default strength_model value of 1.0 and change it in small steps while comparing results from the same later workflow. This makes it easier to judge the effect of each change without assuming a particular value will suit every LoRA.
  • To configure multiple LoRAs, connect LoadWanLora nodes in sequence. Each selected file and strength is appended to the lists received from the previous node; the cache setting recorded in the configuration is the one set by the last node that adds a LoRA.
  • Leave lora_name unselected when you want this node to pass the configuration through without adding another LoRA. Changing the strength or cache setting alone will have no effect in that case.

Load Wan Lora Common Errors and Solutions:

No LoRA files appear in the selection list

  • Explanation: The node gets its choices from the local loras folder at runtime. The supplied source does not define a specific error message for an empty list.
  • Solution: Check that the intended LoRA file is in the folder your installation uses for LoRAs, then refresh the choices or restart the application if needed.

Selected LoRA file cannot be found

  • Explanation: A selected name is resolved to a full path from the loras folder. If the file was moved or removed, this node or a later step may fail; the exact error text depends on the surrounding application.
  • Solution: Confirm that the file still exists in the LoRA folder, refresh the selection list, and select an available file.

No LoRA effect is visible

  • Explanation: This node records a LoRA path and strength but does not itself apply weights or render a result. It also adds nothing when lora_name is None.
  • Solution: Confirm that a file is selected and that the updated funmodels output reaches a later workflow step that uses the recorded LoRA. Compare results using the same later workflow while adjusting strength_model.

Error when processing funmodels

  • Explanation: The implementation copies funmodels as a dictionary and, when a LoRA is selected, reads its existing LoRA and strength lists. Incompatible incoming data may cause processing to fail. The supplied source does not specify an exact error string.
  • Solution: Connect a compatible FunModels output from the appropriate earlier node. If the problem occurs after several LoRA nodes, check the configuration passed between them.

Caching does not improve performance

  • Explanation: LoadWanLora only records the lora_cache choice when a LoRA is selected. The supplied implementation does not show whether a later step uses it or how much time it could save.
  • Solution: First confirm that lora_name is selected. Then check whether the later node in your workflow supports this recorded setting; do not rely on this node alone to change performance.

Load Wan Lora Related Nodes

Go back to the extension to check out more related nodes.
VideoX-Fun
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.

Load Wan Lora