Install ComfyUI - Revision history

Root: /* Loading assets on your workflow */

2025-11-03T14:42:29Z

Loading assets on your workflow

← Older revision		Revision as of 15:42, 3 November 2025
Line 128:		Line 128:

	If comfyUI stops abruptly, it's probably due to an excessive usage of memory. You will have to reduce the size of the assets you are using.		If comfyUI stops abruptly, it's probably due to an excessive usage of memory. You will have to reduce the size of the assets you are using.

			== Installing custom nodes ==
			Users can create their very own custom nodes. To install them:

			# get the url of the repository, for example <nowiki>https://github.com/SeanScripts/ComfyUI-Unload-Model</nowiki>
			# go to the custom_nodes folder, open a terminal and execute git clone <nowiki>https://github.com/SeanScripts/ComfyUI-Unload-Model.git</nowiki>
			# restart comfyUI server
			#

	= Troubleshooting =		= Troubleshooting =

Root at 13:24, 3 November 2025

2025-11-03T13:24:49Z

← Older revision		Revision as of 14:24, 3 November 2025
Line 10:		Line 10:
	Make sure you have '''Python 3.10 or higher''' and '''git''' installed:		Make sure you have '''Python 3.10 or higher''' and '''git''' installed:

	<syntaxhighlight lang="bash">		<syntaxhighlight lang="bash">sudo apt install python3 python3-venv python3-pip git</syntaxhighlight>
	sudo apt install python3 python3-venv python3-pip git
	</syntaxhighlight>

	Clone the ComfyUI repository:		Clone the ComfyUI repository:
Line 162:		Line 160:
	'''IMPORTANT:''' LoRAs are trained using specific Models (Wan, Flux, SD, etc). Make sure that the LoRAs you download use your base model. Otherwise, change your base model to use LoRA's.		'''IMPORTANT:''' LoRAs are trained using specific Models (Wan, Flux, SD, etc). Make sure that the LoRAs you download use your base model. Otherwise, change your base model to use LoRA's.
	[[index.php?title=Category:AI: Generate media locally]]		[[index.php?title=Category:AI: Generate media locally]]
			[[Category:AI: Generate media locally]]

Root: /* Loading assets on your workflow */

2025-11-03T08:59:51Z

Loading assets on your workflow

← Older revision		Revision as of 09:59, 3 November 2025
Line 130:		Line 130:

	If comfyUI stops abruptly, it's probably due to an excessive usage of memory. You will have to reduce the size of the assets you are using.		If comfyUI stops abruptly, it's probably due to an excessive usage of memory. You will have to reduce the size of the assets you are using.

			= Troubleshooting =

			* Do not try to generate videos longer than 100 frames, models start hallucinating and generate random content.

	= Assets resources =		= Assets resources =

Root: /* What workflows are */

2025-11-03T08:40:14Z

What workflows are

← Older revision		Revision as of 09:40, 3 November 2025
Line 53:		Line 53:

	== What workflows are ==		== What workflows are ==
	A '''workflow''' in ComfyUI is a graph that defines how data (text prompts, models, images, etc.) flows between nodes to generate an ~~image~~.		A '''workflow''' in ComfyUI is a graph that defines how data (text prompts, models, images, etc.) flows between nodes to generate an output media.

	Example workflow of image to video:		Example workflow of image to video:
Line 157:		Line 157:

	'''IMPORTANT:''' LoRAs are trained using specific Models (Wan, Flux, SD, etc). Make sure that the LoRAs you download use your base model. Otherwise, change your base model to use LoRA's.		'''IMPORTANT:''' LoRAs are trained using specific Models (Wan, Flux, SD, etc). Make sure that the LoRAs you download use your base model. Otherwise, change your base model to use LoRA's.
	[[Category:AI: Generate media locally]]		[[index.php?title=Category:AI: Generate media locally]]

Root at 08:26, 3 November 2025

2025-11-03T08:26:35Z

← Older revision		Revision as of 09:26, 3 November 2025
Line 134:		Line 134:

	== Previous examples resources ==		== Previous examples resources ==



	'''Wan GGUFs (Models). Destiny folder: models/unet'''		'''Wan GGUFs (Models). Destiny folder: models/unet'''
Line 159:		Line 157:

	'''IMPORTANT:''' LoRAs are trained using specific Models (Wan, Flux, SD, etc). Make sure that the LoRAs you download use your base model. Otherwise, change your base model to use LoRA's.		'''IMPORTANT:''' LoRAs are trained using specific Models (Wan, Flux, SD, etc). Make sure that the LoRAs you download use your base model. Otherwise, change your base model to use LoRA's.
			[[Category:AI: Generate media locally]]

Root: /* Loading assets on your workflow */

2025-11-03T08:12:36Z

Loading assets on your workflow

← Older revision		Revision as of 09:12, 3 November 2025
Line 126:		Line 126:
	** Text Encoder umt5_xxl_fp8_e4m3fn_scaled.safetensors: 6,7GB		** Text Encoder umt5_xxl_fp8_e4m3fn_scaled.safetensors: 6,7GB
	* ComfyUI processing and temporary data: 10-20% of assets		* ComfyUI processing and temporary data: 10-20% of assets



	With this configuration, we would fit the requirements, as we have 56GB of memory and the process requires less than 50GB.		With this configuration, we would fit the requirements, as we have 56GB of memory and the process requires less than 50GB.
Line 136:		Line 134:

	== Previous examples resources ==		== Previous examples resources ==

Root: /* What workflows are */

2025-11-03T08:11:31Z

What workflows are

← Older revision		Revision as of 09:11, 3 November 2025
Line 57:		Line 57:
	Example workflow of image to video:		Example workflow of image to video:
	[[File:ComfUI example i2v.png\|none\|thumb\|484x484px]]This is the file with the previous workflow in json format: [[File:ComfyUI image to video example workflow.json\|none\|thumb]]		[[File:ComfUI example i2v.png\|none\|thumb\|484x484px]]This is the file with the previous workflow in json format: [[File:ComfyUI image to video example workflow.json\|none\|thumb]]



	Each workflow is saved as a .json file that can be shared or loaded into ComfyUI. They are stored in your '''ComfyUI/user/default/workflows''' folder.		Each workflow is saved as a .json file that can be shared or loaded into ComfyUI. They are stored in your '''ComfyUI/user/default/workflows''' folder.

Root: /* Installing workflow dependencies */

2025-11-03T08:08:40Z

Installing workflow dependencies

← Older revision		Revision as of 09:08, 3 November 2025
Line 61:		Line 61:

	Each workflow is saved as a .json file that can be shared or loaded into ComfyUI. They are stored in your '''ComfyUI/user/default/workflows''' folder.		Each workflow is saved as a .json file that can be shared or loaded into ComfyUI. They are stored in your '''ComfyUI/user/default/workflows''' folder.

	~~You can import a workflow by dragging directly into the interface:~~

	* a JSON file
	* media (image or video) generated with comfyUI

	~~== Template workflows ==~~
	~~On the right sidebar, in the "Templates" menu, you can find many different workflows for all type of media.~~

	== What nodes are ==		== What nodes are ==
Line 94:		Line 86:
	You can double-click on the canvas to add new nodes or search for them by name.		You can double-click on the canvas to add new nodes or search for them by name.

	= ~~Installing workflow~~ dependencies =		= Workflow templates and dependencies =
	When loading ~~external~~ workflows, they might have nodes that are not installed yet on your system. To install them, click on "Manager" at the top right of the interface, then on "Install missing custom nodes".		You can import a workflows by:

			* dragging directly into the interface a JSON file or media (image or video) generated with comfyUI
			* On the right sidebar, in the "Templates" menu, you can find many different workflows for all type of media.
			When loading workflows, they might have nodes that are not installed yet on your system. To install them, click on "Manager" at the top right of the interface, then on "Install missing custom nodes".

	= ComfyUI folder structure =		= ComfyUI folder structure =

Root: /* What workflows are */

2025-11-03T08:06:18Z

What workflows are

← Older revision		Revision as of 09:06, 3 November 2025
Line 55:		Line 55:
	A '''workflow''' in ComfyUI is a graph that defines how data (text prompts, models, images, etc.) flows between nodes to generate an image.		A '''workflow''' in ComfyUI is a graph that defines how data (text prompts, models, images, etc.) flows between nodes to generate an image.

	Example workflow on image to video:		Example workflow of image to video:
	[[File:ComfUI example i2v.png\|none\|thumb\|484x484px]]This is the file with the previous workflow in json format: [[File:ComfyUI image to video example workflow.json\|none\|thumb]]		[[File:ComfUI example i2v.png\|none\|thumb\|484x484px]]This is the file with the previous workflow in json format: [[File:ComfyUI image to video example workflow.json\|none\|thumb]]

Root at 08:05, 3 November 2025

2025-11-03T08:05:52Z

← Older revision		Revision as of 09:05, 3 November 2025
Line 1:		Line 1:
	~~= ComfyUI overview =~~		= What is ComfyUI =

	== What is ComfyUI ==
	'''ComfyUI''' is a powerful and modular graphical interface for running and creating '''Stable Diffusion''' workflows for generating images and videos from text or images.		'''ComfyUI''' is a powerful and modular graphical interface for running and creating '''Stable Diffusion''' workflows for generating images and videos from text or images.