An ideal workflow for people who are just starting to use ComfyUI and don't have much knowledge (I'm a newbie too), but want a simple UI with a big potential to generate images.
V2.6 Update
-I finally had time to fix it, now everything should be working normally again.
Best regards, and sorry for the delay :/
V2.5.1 Update
-Error fixes :D
V2.5 Update
-Added a Refiner*.
-Fixed a bug caused because the Compact Ksampler (it was a fusion of Efficiency Nodes and some basic nodes) didn't recognize the Scheduler Selector imput after an update, after the workflow upload :/
-The original V2 has been updated to fix the Ksampler bug as well. In case you are not interested in 2.5. You must download the new V2 version (or redo the Ksampler yourself).
*The Refiner is optional, if you don't usually use Refiner in your creations, and you think you don't need it, you can simply delete the whole Refiner group without any problem and the workflow will continue working perfectly :D
V2 is here!
Improvements:
-You can now add and remove LoRa from the same node, or even disable them with a switch.
-You can now select the aspect ratio of your future artwork worth millions.
-Now it's even more compact!
LoRa
It works as it should, I think that in V1 the LoRa didn't work properly. That's not a problem anymore :D
This is the new selector:
By clicking the +Add Lora button you can add as many as you want. With the switches you can deactivate and activate them individually (or press Toggle All). To remove a LoRa from the list, simply right click on it and this menu will appear:
Aspect Ratio
It may seem a minor addition... but for me it's something very useful, especially when you change a lot, because manually typing ALL the time "1024x1024" or "512x768" is quite boring. This is how the loader looks now:
And when you click on the Aspect Ratio button:
It is almost orgasmic.
The prompt
I keep the same goal in mind: Simplify the prompt and get what I want. That's all I wrote in the prompt. 1girl, apo in the positive, and absolutely nothing in the negative (yes, I'm lazy, I know), I chose a LoRa from Marcille (Dungeon Meshi) and a couple of styles in the Styler node and this is the result:
Obviously it's not perfect, but I mean... I literally wrote 2 words.... And with the Save Image With Metadata node, Civitai recognizes the metadata when uploading an image created with this workflow (not all, the LoRa, for example, I still can't get it to recognize them, but meh, it's fine, for now). Here is an example:
As you can see, the selected styles are also saved in the Styler node at the prompt. I will continue to work on figuring out a way to get absolutely all the metadata as well as A1111 does.
That's all for now. If you have any advice or suggestions, don't be shy :D
Description
Added Refiner :D (Redbible's suggestion)
Fixed a bug with the Compact Ksampler. That Ksampler was part of the custom node called Efficiency Nodes, to which I added other nodes and merged them, but there was an update after my upload, in which if I put the Scheduler as imput, and tried to connect the Scheduler selector, it was not possible. So I made another Ksampler and this one should work correctly now (thanks to Varies for warning about the error :D).
FAQ
Comments (12)
I have a problem with the workflow....in both"Save Image w/Metadata" glow red!!!modelnamethe option is in red.
Connect "ckpt_name" from Loader node to Save Image W/Metadata, then refresh
Love the workflow! I'm a total n00b with Comfy and this makes it much easier! Is there a way to turn on/off the upscaler? Most of the time I don't want to use it. Thanks!
Hey! thx thx for ur words <3! Yes, you can turn off the Upscaler by selecting it and pressing CTRL+B, this will bypass it and will not affect connections to other nodes, so everything will work fine. You can do this with any node you don't need, to reactivate it press CTRL+B again :D
@AquAI Thank you!
Works pretty well but what is the refiner actually doing here? Is it a post process after the image is done? Typically a refiner switches checkpoints at a certain step from the original but by testing with other ui's you can tell it's not actually doing that.
Hmm... I don't really understand too much about how refiners work, but according to the guides I was looking at, everything should work correctly. I'll keep researching and working on fixing it (might take a while). I'm still a noob with ComfyUI, so any help and/or advice is welcome :D
@AquAI idk if you use another ui like fooocus or stableswarm but you can compare exactly the function of refiners, in those. stableswarm even allows you to import the wokflow directly into its comfy backend so you can see how it's set up node-wise for them. But in general it just switches to another checkpoint at a given step.
@redbible would be something like this? https://freeimage.host/i/d3tiNt9 in that screenshot you can see 2 different checkpoints, the images are similar, but it is still a post process, because the first Ksampler is connected to a Save Img with metadata node, and before jumping to the next sampler, it has to go through that node, then load the checkpoint and continue where the previous image left off. So far that's what I understood, now I'm going to try those UI's you told me to see if there's something I'm doing wrong. BTW there were a couple of nodes that weren't connected properly, and the "cliptextEncode SDXL" were missing xDD so I'm going to re-upload this one, try downloading it again and let me know if it works fine :D
Ok, this makes more sense, I have been looking on yotube, and I have tried other workflows with Refiner and in theory everything is fine, the problem was these parameters: https://ibb.co/F8JnPjS set the denoise of the Ksampler refiner below 0.5 (to your liking) and with that everything should work perfectly. When you can test it let me know if it worked :D
@AquAI I put a workflow via stableswarm here, you can see how the initial model has a step count of like 50 and ends at 40 something, then the refiner starts at 40 and finishes the job. https://freeimage.host/i/d3D0XN1
@redbible I have checked that workflow and mine is exactly the same connected (now), what happens is that many nodes are merged, so the imputs and outputs are grouped together. But in theory, now with V2.5.1 everything works fine, there are no errors. :D