Update:
Added DynamoXL-txt2img
This version requires custom nodes, article here to get started
ProjectName: Filename Prefix, Stage Prefix and Blip Caption as Filename
Random Line: Accepts multiline wildcard style batch prompt
Prompt Swap: can replace captions word for word in prompt
Prompt Styler: massive collection of Prompt Wrappers
Quad Lora Stack: 4 Lora Loaders for you to use
REMBG: removes background automatically if it can
Upscaler 4X: recommended Foolhardy_Remacri
Ultrabasic Txt2Img SDXL 1.0
This version also requires no custom nodes, but has a new Lora stack bypass layout for easy enable/disable of as many lora models as you can load. If you need facedetailer, just use SDXL1.0-SuperUpscale version instead.
UltraBasic Img2Img SDXL 1.0
This version required no custom nodes, i noticed a lot of people had problem with custom node conflicts and the face detailer, so i dropped all that stuff to keep it vanilla.
You can load and image and use denoise like you would normally to create variations of the image, also there is the super upscaler as before.
You can select nodes and press ctrl+m to "mute/unmute" them. So if you mute all the nodes in the upscaler section, it can be turned on and off like that.
I'm working on an ultra Basic txt2img next so that people can still use this if they can't get the custom nodes to work :)
SDXL1.0-SuperUpscale
This is my current SDXL 1.0 Workflow.
It is based on the SDXL 0.9 facedetailer workflow by FitCorder, but rearranged and spaced out more, with some additions such as Lora Loaders, VAE loader, 1:1 previews, Super upscale with Remacri to over 10,000x6000 in just 20 seconds with Torch2 & SDP.
There is an Article here explaining how to install SDXL1.0-Super-Upscale
if you have all the custom nodes already installed, you can use it straight away
Description
This requires Custom Nodes!
instructions here: https://civitai.com/articles/1566
FAQ
Comments (14)
This is the first IU after trying most on Civ that actually makes great images out of the box. Amazing. Looking forward to better faces. PLEASE UPLOAD YOUR YOLO FACE IMPLEMENTATION
thanks for the feedback, the face detector can be hit and miss. often it does not pick up on faces, i'm sure there will be a solution and I will include it if i find one!
Super Detailer XL is coming soon, where the full Yolo Implementation is in. Body, Hands, Face.
I've been test-driving different workflows all evening, some are easier, some are more complex, some don't work out of the box. DynamoXL is the first and only workflow to actually blow my mind. It really gets my wheels turning. Very well thought out. While it will take some time to grow accustomed to what it's capable of, it is capable of great things. Thank you, great work.
thanks so much for sharing your feedback!! its great to hear you are enjoying it :)
we can build so much on these workflows so i love to share them
Don't know what kind of sorcery you baked in to spit out 4K images as if they were mere 720p but I'm all for it. Would it be possible to add dynamic wildcards from a file? I would like to have like word such as "animal" and then swap it with one the animals in a text file, or at least input a list of animals in a node, then make it pick up. As for 8K, how do we connect it so that it upscales from 4K?
Error occurred when executing BLIP Analyze Image: WAS_BLIP_Analyze_Image.blip_caption_image() got an unexpected keyword argument 'blip_model'
how to fix this?
I tried to use this after updating comfyui. I also installed the prerequisites, but on loading the workflow, I get the error that Text box and Text nodes could not be loaded.
Try to hit the refresh button!
Hi Drift, I get 2 missing plugins, text and text box, with no other information... It's not the most "unique" name, for a plugin... If only these "missing plugin" prompts included links to missing stuff...
I recently uploaded the workflow into ComfyUI and encountered some issues. After installing all the missing nodes as suggested, I still have some nodes showing up in red with the following error message:
"When loading the graph, the following node types were not found:
* MMDetDetectorProvider
* Integer
Nodes that have failed to load will show as red on the graph."
i followed this tutorial to install it:
https://civitai.com/articles/1447/sdxl-10-comfy-with-facedetailer-and-super-upscale
thanks
it might be the age of the workflow, with so many changes, this was one of my earliest SDXL 1.0 workflows. maybe time to update them ;) thanks and glad you got it working
I wish you created a more straightforward, simple workflow. There was no need to embed all the additional steps into this workflow at all, it just gets very confusing very quickly. The problem with most of these workflows is trying to embed way too much functionality in one workflow.
That's why they call it "all in one"
I have released hundreds of workflows, from these type to drop in modules and single use type workflows.
I agree with you that they get too complicated, but I just release what I use. This is quite an old release. Newer offerings are much simpler now