Searge-SDXL: EVOLVED v4.3.2
Version 4.x is here.
I made a convenient install script that can install the extension and workflow, the python dependencies, and it also offer the option to download the required models.
Please read the install instructions in the readme file for more information about the install script and how to use it.
Description
Some custom nodes for ComfyUI and an easy to use SDXL 1.0 workflow. A detailed description can be found on the project repository site, here: Github Link
Installing
Detailed install instruction can be found here: Link to the readme file on Github
Usage Notes
The workflow is in the workflow folder, please load it from the JSON files to make sure you are using the latest versions of it.
The images in the examples folder have workflows embedded.
How to use this workflow
Here is an amazing Youtube video that Nerdy Rodent made about version 3.4 of the workflow. Many things have changed in v4.0 but the basics still apply. And while you are watching it, don't forget to subscribe to the channel.
Link to the Nerdy Rodent video
Updates
What's new in v4.3.2?
This is a minor update to make the workflow and custom node extension compatible with the latest changes in ComfyUI.
What's new in v4.3.1?
This is a minor update to make the workflow and custom node extension compatible with the latest changes in ComfyUI.
What's new in v4.3?
This update added support for FreeU v2 in addition to FreeU v1.
New Features
Support for FreeU v2 has been added and is included in the v4.3 workflow
Added more presets for FreeU and a selector to switch between v1 and v2
Updated the example images to embed the v4.3 workflow
What's new in v4.2?
This update contains bug fixes that address issues found after v4.0 was released.
Bug Fixes
A recent change in ComfyUI conflicted with my implementation of inpainting, this is now fixed and inpainting should
work again
New Features
Support for FreeU has been added and is included in the v4.2 workflow
Note: the images in the example folder are still embedding v4.1 of the workflow, to use FreeU load the new
workflow from the.jsonfile in theworkflowfolder
What's new in v4.1?
This update contains bug fixes that address issues found after v4.0 was released.
Bug Fixes
The high resolution latent detailer was not properly set up in the processing pipeline and did nothing
The debug printer node was broken - I didn't notice that because it was not connected in any of the v4.0 workflows
A bug related to generating with batch sizes larger than 1 has been fixed, it's now working properly
Other Changes
The images in the
examplesfolder have been updated to embed the v4.1 workflow
What's new in v4.0?
A complete re-write of the custom node extension and the SDXL workflow
Highly optimized processing pipeline, now up to 20% faster than in older workflow versions
Support for Controlnet and Revision, up to 5 can be applied together
Multi-LoRA support with up to 5 LoRA's at once
Better Image Quality in many cases, some improvements to the SDXL sampler were made that can produce images
with higher qualityImproved High Resolution modes that replace the old "Hi-Res Fix" and should generate better images
... many more things, too many to mention them all here
Description
Searge SDXL v3.0 - "Truly Reborn"
(this file was updated to the v3.0a hot fix)
A workflow and custom node extension for ComfyUI and the SDXL 1.0 base & refiner models. Now everything is included in a single workflow .json file, make sure to update the custom node extension to the latest version to run this workflow.
FAQ
Comments (10)
Getting this error during the HiRes Fix. I have ran the update_comfy.bat just to make sure. Installed your custom nodes via git pull as described.
full error: https://i.imgur.com/SmmSSf9.png
"Error occurred when executing SeargeSDXLImage2ImageSampler:
SeargeSDXLImage2ImageSampler.sample() got an unexpected keyword argument 'softness'"
Hey Sarge, thanks for this awesome workflow, you are a genius.
I'm getting an error after upgrading comfyui, and then your custom nodes via git. If you could point me in the right direction, I'd really appreciate it. Thanks in advance! <3
Error occurred when executing SeargeSDXLImage2ImageSampler: SeargeSDXLImage2ImageSampler.sample() got an unexpected keyword argument 'softness' File "E:\AI\Apps\StableDiffusionWebUI\ComfyUI\ComfyUI\execution.py", line 144, in recursive_execute output_data, output_ui = get_output_data(obj, input_data_all) File "E:\AI\Apps\StableDiffusionWebUI\ComfyUI\ComfyUI\execution.py", line 74, in get_output_data return_values = map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True) File "E:\AI\Apps\StableDiffusionWebUI\ComfyUI\ComfyUI\execution.py", line 67, in map_node_over_list results.append(getattr(obj, func)(**slice_dict(input_data_all, i)))
I see that there are already source image and mask nodes added. How do those work? Are they just disregarded until I add images? It looks like there are already images in there but it seems to be ignoring them.
I downloaded this through the Manager, loaded the workflow, and then restarted ComfyUI. I ran into this error after hitting queue prompt.
Error occurred when executing SeargeImageSave: 'Namespace' object has no attribute 'disable_metadata' File "D:\AI\ComfyUI_windows_portable\ComfyUI\execution.py", line 144, in recursive_execute output_data, output_ui = get_output_data(obj, input_data_all) File "D:\AI\ComfyUI_windows_portable\ComfyUI\execution.py", line 74, in get_output_data return_values = map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True) File "D:\AI\ComfyUI_windows_portable\ComfyUI\execution.py", line 67, in map_node_over_list results.append(getattr(obj, func)(**slice_dict(input_data_all, i))) File "D:\AI\ComfyUI_windows_portable\ComfyUI\custom_nodes\SeargeSDXL\searge_sdxl_sampler_node.py", line 640, in save_images if not args.disable_metadata:
error is showing.
!!! Exception during processing !!! Traceback (most recent call last): File "/content/ComfyUI/execution.py", line 145, in recursive_execute output_data, output_ui = get_output_data(obj, input_data_all) File "/content/ComfyUI/execution.py", line 75, in get_output_data return_values = map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True) File "/content/ComfyUI/execution.py", line 68, in map_node_over_list results.append(getattr(obj, func)(**slice_dict(input_data_all, i))) File "/content/ComfyUI/custom_nodes/SeargeSDXL/searge_sdxl_sampler_node.py", line 640, in save_images if not args.disable_metadata: AttributeError: 'Namespace' object has no attribute 'disable_metadata'
I don't quite understand how you shift between modes? I have already updated the custom node to it's lates version.
Error occurred when executing SeargeImageSave:
'Namespace' object has no attribute 'disable_metadata' File
"E:\ComfyUI_windows_portable\ComfyUI\execution.py", line 144, in recursive_execute output_data, output_ui = get_output_data(obj, input_data_all) File
"E:\ComfyUI_windows_portable\ComfyUI\execution.py", line 74, in get_output_data return_values = map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True) File
"E:\ComfyUI_windows_portable\ComfyUI\execution.py", line 67, in map_node_over_list results.append(getattr(obj, func)(**slice_dict(input_data_all, i))) File
"E:\ComfyUI_windows_portable\ComfyUI\custom_nodes\SeargeSDXL\searge_sdxl_sampler_node.py", line 640, in save_images if not args.disable_metadata:
Is there any practical way to chain multiple loras together without having to edit the nodes?
It would also be nice if it was possible to finetune the model and clip strength of the loras separately.
Your latest hotfix did fix it for me, but I did have to clean install comfyui as I was still having issues. After that it's running nicely!
Really great workflow and nodes! There is one suggestion I have though: could you make it so that both the refiner and VAE can be disabled in the advanced parameters node?
Reasoning for this is that a lot of the custom checkpoints so far don't have either Refiners or VAEs as of yet, and even the base SDXL model has a version that comes with the VAE already included in the model's safetensors file.
These changes would help to potentially future-proof the work you've done.