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
Bugfix release with some minor changes.
FAQ
Comments (7)
Prompt outputs failed validation CheckpointLoaderSimple: - Return type mismatch between linked nodes: ckpt_name, CHECKPOINT_NAME != ['realisticVisionV20_v20.safetensors', 'sd_xl_base_1.0.safetensors', 'sd_xl_refiner_1.0.safetensors'] VAELoader: - Return type mismatch between linked nodes: vae_name, VAE_NAME != ['diffusion_pytorch_model.fp16.safetensors', 'diffusion_pytorch_model.safetensors', 'sdxl_vae.safetensors', 'vae-ft-mse-840000-ema-pruned.ckpt'] CheckpointLoaderSimple: - Return type mismatch between linked nodes: ckpt_name, CHECKPOINT_NAME != ['realisticVisionV20_v20.safetensors', 'sd_xl_base_1.0.safetensors', 'sd_xl_refiner_1.0.safetensors'] UpscaleModelLoader: - Return type mismatch between linked nodes: model_name, UPSCALER_NAME != ['4x-UltraSharp.pth', '4x_NMKD-Siax_200k.pth', 'ESRGAN_4x.pth'] UpscaleModelLoader: - Return type mismatch between linked nodes: model_name, UPSCALER_NAME != ['4x-UltraSharp.pth', '4x_NMKD-Siax_200k.pth', 'ESRGAN_4x.pth'] LoraLoader: - Return type mismatch between linked nodes: lora_name, LORA_NAME != ['lwmirXL-V1.0.safetensors', 'lwmirXL-V1.0fp16.safetensors', 'sd_xl_offset_example-lora_1.0.safetensors']
Are you using the latest versions of both, the extension and the workflow json from the workflow folder? This error message looks like something I'd expect if you used the wrong json file with the extension you've got installed
Is there a NSFW filter hidden in these Nodes ?
I can generate NSFW images easily on most other workflows if wanted with SDXL base/refiner but cannot seem to do it with these workflows...????
No, there are no filters or anything like that in the workflow. I'd not want to spend my time on adding something that every one would disable anyway :)
@searge I didn't think you would but it's strange how they're reacting to my prompts compared to other workflows...I love what you are doing and want to use these as my go to workflows, but occasionally I do like a little 'nudity' in the images and am struggling to achieve it in the 'reborn' workflow..👍🏻
Regarding prompt emphasis, I thought I should get clarification since this workflow uses it's own custom sampler.
The workflow information node states that sections of a prompt "can be emphasized by surrounding it with ~*~".
Does this mean that typical emphasis techniques for Stable Diffusion, namely surrounding a section of a prompt with round or square brackets, no longer work? How about keyword blending?
If they don't, does using multiple instances of "~*~" on a prompt further emphasize the section it's encompassing? Thank you!
It's not something that the SDXL models are explicitly trained on, but using ~*~ around the main style often seems to make prettier images. It's not really necessary in most cases, I just saw someone use that prompting style and tried it myself.