wooow.. can't believe my custom node 1:05 (Recommended Resolution Calculator) is shown in my favorite tutorial channel, did not expect that!

This is terrific, thanks! I'd been trying some other recommended ways to upscale, but they always resulted in weird, unsatisfying results. This works marvelously! I see that it's added some super very minor detailing along the way, but without heavily altering the image as it upscales. Color me happy :D Loving these vids, Scott, and can't thank you enough.

Scott, THANK. YOU. None of the other tutorials I watched for upscaling explains how things actually work in such detail. I really appreciate it. I aim to learn as I go along, and your videos are always super helpful.

Beautifully laid out content. Thank you!

I have tried to follow other tutorials online. Bay far, you are the best one ! ♥

Thank you Scott, great video like always. For me Upscaling/Recreating an existing image with different denoising values, different tools and so on are more exciting than creating a new image.

Thank you for these awesome videos- I now have a control net render set up for my smaller previews- followed by an amazing upscale setup.

best upscale tutorial i have ever seen for comfy ui. well done

I'm really impressed with the result i get! Thank you so much for this tuto workflow !

This is awesome... not so much for the upscaler but learning how to use ComfyUI too :D Thank you

Thank you so much for the step by step! I got great results!

Two things that were really important to me in this video to use the Ultimate SD Upscaler correctly in my workflow: (1) Use a tile size of 1024 for SDXL. Duh, in retrospect, but I hadn't thought of that. (2) Use the empty positive & negative prompts. The first time I used the upscaler, I ended up with horrific 512 tiling results (seams, non-flowing contents per tile, even w/ low denoise) along with extra stuff (little people) showing up. Both (1) and (2) fixed that for me. When I ran into the problem, this was the first place I turned to. Thank you, Scott. 🙌

really high quality tutorial, logic and clear!

Very interesting and helpful, thank you!

You're 100% right at 4:36, I had no idea. That's a handy little tip!

Thats good explanation! On my 4090 runs so fast! Thanks!

GREAT Tutorial!

Well done sir...good explanations, im greatful for this...thx

I follow the steps, and I learn each video, but tomorrow when I open the comfy again I am blank, have to go through your videos to learn and really digest each steps

thanks for this!

obrigado pela aula! achei sensacional! aprendi muito hoje!

😀 Your videos are excellent! 😀

Thank you, I got that node a few days ago and had no idea how to wire it up, now I do! Also, 300 seconds is not a long time at all when you have a 4GB GPU...I have patience. 😁

Hmmm - I tried this ... but I'm still seeing a lot of tiling artifacts - no matter which tile elimination scheme I pick. Is there a way to hook this up so that it is used in the initial creation of an image? Some way of using it so that if you generate a smaller image you like, you can reload that generation data and regenerate from scratch at the much higher resolution - to avoid the tiling issues? Or is the generation process just inherently "dirty"? I appreciate your putting these videos up :) - Thank You :)

Brilliantly explained and very educational, thank you! In my case the problem is that I’m almost exclusively working with face trained Loras and the more an image is upscaled, the more subtle likeness is lost. I tried throwing a face trained Lora into the mix here but was unable to make it change anything for the better. Possibly due to a lack of knowledge on my part.

Outstanding!

Tbh, I didn't get this video the first time I watched it. My first thought was: "The upscaler already says 'upscale by' and you can just plug in the number irrespective of the resolution of the input image. So why do these calculations?" And so I went and read more about the node, 'SDXL Resolution Calculator'. So for any beginner who comes later and gets confused, it "calculate and automatically set the recommended initial latent size for SDXL image generation and its Upscale Factor based on the desired Final Resolution output. According to SDXL paper references (Page 17), it's advised to avoid arbitrary resolutions and stick to those initial resolution, as SDXL was trained using those specific resolution. Basically, you are typing your desired target FINAL resolution, it will gives you: a) what resolution you should use according to SDXL suggestion as initial input resolution & b) how much upscale it needs to get that final resolution."

Heyho, I recently found your video series and they are awesome for beginners! Even though things tend to get dated really quick when it comes to ML utilities, which is one reason for my question: What is the difference or even the advantage of this method compared to the iterative upscaler that you showed a few videos ago? Ssecond question: what's the ComfyUI setting plugin to show where's a node "coming from"? You have those outlines with the title of the custom node package around your nodes, that's what I mean ^^ Oh and third question: do you know of a more "comfortable" / less "noodly" way to create regional prompts? I found two promising custom nodes, though the "comfortable" one (Davemane42's Visual Area Conditioning / Latent composition) that even shows the regions now is quite dated (~ 8 months without updates) and the other one (laksjdjf's attention-couple-ComfyUI) needs many more nodes and connections aswell as manual calculations for each region in question.

Great explanation on the tiling. This is the first workflow I tried, but I was still catching up on what models to use for upscaling, so I wasn't getting good results with the model I had -- I don't remember what it was, but I kept getting tiling seams, or leathery skin/freckling. You mentioned you wouldn't need to worry about seams on this one, where can I find something on the seams settings? I can only guess at what the settings are doing... lol

you are a Life Saver

wow this is awesome! is it correct to think that we can actually combine this with the iterative upscaler workflow if we are totally insane?

Comparing SDXL upscaling to StableSR quickly here: StSR "appears" sharper, but SDXL is a but more "logical". It depends on the image really. The cool thing about difussing upscaling is creation of details. SwinIR works great for very small images, and ESRGAN models have their strengths and weaknesses. Too many options!! But I'm not complaining. Looking forward to a StableSR using the SDXL model.

Thanks for the tutorial! Is this still the most up to date and efficient way to upscale loaded images? Thanks

i must stay, i didn't understand anything, but it works

Wow, thankyou so much for sharing this. Can you please explain more on upscaler models, hope menu are there, Meyer in a seperate video, or here if it's a short answer. Thankyou again.

Super!

I am learning with you and for free, thank🎉❤

Thank you! This is an excellent video and it does work great for me with my 1024 x 1024 images. I tried to upscale an SD 1.5, 512 x 512 input, but it did not work for that. It tried to generate a grid of 8 x 8 which would take all day and does not seem right. Do you how set it to upscale a 512 x 512 input image? Maybe it is better to just resize the image. Edit: I did get pretty good results from resizing the image, though I can see the lines in the tile borders in the skin tone.

Sometimes Remacri gives oversharpened edges and kills small details, then I find that BSRGAN 2x can actually work quite well for 2-3 times upscaling with denoise at 0.15 - 0.2 and steps at 8 - 16. Especially for detailed face portraits.

A great explainer, I was just trying to figure out upscaling from people’s shared workflows. Setting up my own teaches me better. This is a great series overall, thanks Scott. It arrived just as I got into using image AIs locally. I’m the proud owner of a very bored looking robot, shopping at Wallgreens. I really hope that becomes the “teapot” of image AI. 😀

Thanks, topaz is sooo much faster but this adds a little more detail.

Great video. Would using doing a little vision on the original image to provide guidance to the upscaler be beneficial?

I was the 1000th like!!!

Is there a way to set Load Image to watch a hot folder? Also is there a way to get rid of the lines that form like the one in your image about 1/4 of the way down where the tiles don't seam together properly. I get that a lot with this workflow.

Does this method use tile overlap to avoid seams? If so, could that be used to adapt between the input resolution abs SDXL's resolution?

any advice for non-integer upscaling (i.e. 1.5)? The math intBinaryOperation only accepts integers, I tried to swap it for numberBinaryOperation, but I still get a ratio of 2

Hi, thank you for the video, I’m super noob in Ai. I installed to upscale some images I have. Let me ask you if is there anyway to do a batch of images instead one by one? Thank you!

If the Checkpoint Model need to use an specific CFG, steps, sampler and scheduler on a KSampler. Does the same rules apply to the Ultimate SD Upscaler node? (DreamShaperXL Lightning for example have this specific rules)

Where do I find the Nearest SDXL Resolution node? I can't locate it in the manager. In fact, I can't seem to find any custom nodes that take an image input and have outputs for height/width.

Would it be possible to explain the function of "reverse upscale for 4x/2x" in a bit more detail? I got what they are for in theory, but can't figure out how to set that up properly. Thanks either way ^-^

Hi Scott. Great tutorial and a really nice break down. Would it be possible to get the workflow please? For some reason, after setting the whole thing up, my workflow has defaulted. Thanks.

I am new with ComfyUI. I am getting an error when I am try to install UltimateSDUpscale. "Cmd('git') failed due to: exit code(1)". I will appreciate your help, thanks!

It's Amazing work！does it mean that the tile model of controlnet has worked in sdxl. I also interest the 'save(api format)' button in panel

Could you make a tutorial about ComfyUI Outpainting or fill out the images? I saw some outpainted tutorials with A1111 but not ComfyUI. Thank you.

Thanks for all the tuts, I have used all your sdxl vids to understand and create my workflow. I have heard him say his workflows are or will be available does anyone know where that might be....thanx

where do you find the upscale models?

It would be nice to see before and after

im getting import failed on comfy math for some reason, any ideas? any other tools to use instead for the math portion?

Sir i appreciate your work. Kindly create a video about how to get consistent images in ComfyUI? Kindly make a video on it. It will help a lot. Thanks

I don't get the option to convert on any nodes, this seems like an easy fix but I cannot find anything?

Any idea what these errors might mean? Error occurred when executing UltimateSDUpscale: Given groups=1, weight of size [64, 3, 3, 3], expected input[1, 4, 512, 512] to have 3 channels, but got 4 channels instead

Is there any way to use some kind of regional prompt control with tiling upscales in ComfyUi ?

Hi scott, will you please make a video on Openpose being applied over a 2d-charecter (sketch), so that an animator could easily animate his own charecter accordingly. There are a huge number of people who are waiting for this video. Thank you ....... 🙏

Insightful. So it is possible to use Tiles with SDXL. With SD1.5 I was able to create very wide images using COntrolnet Tiles and Area Composition / Multidiffusion. Can we do the same thing with SDXL. Have a great day ahead.

Is there a trick to preventing the tiles from appearing in the final image?

I have a little problem where SDLX model hallucinates faces and hands where there was just other indistinct detail. Is there a way to mitigate that?

Thank you Scott fot this Video. Great work! After inspecting my images, i notice 1024-1024 grids in the pictures. Is this normal?

I'm unable to download the upscale model you used (the link has been moved btw), pcloud keeps telling me I'm unable to download bc of high traffic (pushing me to get premium) and Google Drive tells me the requested URL was not found... gonna have to dl a few diff options to try out but yeah, thought you might want to know.

Hi, I have a question about the math option you got under add node. If I don't have that option how do I fix it? Thank you😀

I was just wondering ... what kind of graphic card do you have. Generations at your side are way faster than over here...

I didn't understand what's the point in the NearestSDXL Resolution and Primitive Multplied and divided again to get the same 4x at the end. Upscale_by will get the same float 4.0 anyway, or did I get something wrong?

what do I need to change if i want a 2x upscale?

I don't know if this has changed, or if I did something wrong, but the upscaled photo has a bunch of obvious grids in it, and I have no clue how to fix it

The tilings is really prominent with this method.. any ideas how to fix?

sorry for the noob question, but why do we need the operation nodes and the calculator nodes, if the Ultimate SD Upscale has the "upscale by" option. I dont get why we need the binary operations nodes and the resolution calculator node to tell it to "times 4" , if in Ultimate SD Upscale i can have it set to "upscale by 4" what am i missing?

Is there a way to show the result of a calculation in ComfyUI (e.g. via a 'show current value' node or something), like in this case the result for 'upscale factor'? Thanks!

i have a question if anyone can help me , i want to upscale a 1920x1088 image what size tiles should i put in Ultimate sd upscaler , i did try 512x512 and 1024x1024 but after its done you can see the tiles in the image its visible like checkerboard + i mixed it with control net TILE but i get same result :( anyone can help ?

Is there a good way to get rid of the visible tiling of the upscaled result, apart from rendering it all at once which my GPU is not capable of? It depends on the image, but sometimes it's clearly visible where the borders of the tiles are...

Wait, why didn't you just put a primitive number to the upscale_by input in the upscaler node? It's virtually the same thing without using 3 more nodes, am i wrong?

I get some hallucination when upscaling images. I don't find this upscaler usable. :(

Please do a tutorial on doing it with controlnet tile. People say it's better but I have no idea why they never explain why it's better to combine them both.

Hello, I think I may have missed something, as I understand where to find and download upscale models, I cannot seem to find how to use them, is this a simple process? And how is it done?

Hey! Do you know why all these upscalers are in .pth and not in safetensors? Same in huggingface. I'm concerned I might be putting my system at risk since I don't know how to check for malware within pickles

I'm sorry I couldn't find the upscaler and the link didn't work. Please can somebody tell me how I can download an upscaler for this workflow? Thank you 😁.

The link for upscaler models changed and now I can’t find them.

great. I only couldNt use the "4x_foolhardy_Remacri" upscaler model, how can I install it? thx in advance!

6:04 using images' width & height X4 for desiredXSIZE, X4 equal typeing upsacele_factor's value : 4. why to add so much nodes for the same value? Primitive node = typeing upsacele_factor ：4， there are all the same, why did that?

I ran this upscaler but it's losing the details.

what the difference between this and put multiply by 4x directly

is there a way to save the upscaling node set up and then importjust that setup into an existing node flow? Say I have a complex node setup and I want to add the upscale to it with out re-creating the nodes, can i do that?

Thanks for the lessons, it would be nice if you attached a link to download the png settings file.

i have bad tiling, what can i do?

After successfully installing and refreshing Comfyui the UltimateSDUpscale isn't showing up under Image - Upscaling - _____ Any thoughts?

does anyone know why the UltimateSDUpscaler keeps returning 'import failed'? Ive tried to install it via manager, via git clone. Neither workds. I dragged in a workflow that include its to get ComfyUI to install it as a misssing node . Same error 'import failed.' Any clues? Ive looked around websites to see if anyones talking about it having an issue but not found anything so far

Any chance you can give us a link to the workflow we can drag and drop? 😅

omg my results are absolutely terrible, I guess I'll come back to this problem later.

upscaler link is out of date :[

Where i can found this workflow?

Where do I get the upscale models?

I don't understand how to make inpaint workflow. I want to set my own resolution for inpainting image like it does in automatic, but don't understand how.