วีดีโอ

image - [ˈɪmɪdʒ]

Thanks for the video. However InstantIR is no where nearly as good as Supir.

do you use the ui manager?

you're an excellent teacher, and thats coming for a 10+ years c++ dev who watched thousands of hours of YT tutorials lol. thanks a lot, subscribed

The InstantIR node appears in the Manager: / Custom Nodes Manager. (Button) - search and you will find it. Using MANAGER - I installed the nodes and all the folders automatically, including the '\ComfyUI\models\InstantIR\models' Folder. - Did not need to create them myself. I only needed to get the models and put them there. Maybe there is no need to install this node manually - but hey, do so if you like to! 😅 I really like restoring old photos - THANK you much!! And as always.

Another great video. Thank yoy sir.

great one

Hi! I am loving your content! I follow all the instructions and I keep encountered this error. "KSampler forward_orig() takes from 7 to 9 positional arguments but 10 were given" Has anyone encountered something similar, if someone can provide me with a solution I would really appreciate it!

Seriously, I’m fed up with people constantly pushing ComfyUI on us! I get that it’s more flexible, but I can’t stand the endless nodes and settings. It’s time-consuming and just not for me. All I need is a simple setup: install a Conda environment, run prompt commands, and use Gradio for the UI. That’s it!

what is that dino repo do we need to change anything there. Or leave that as it is.

Thanks for another great video! Do you know if InstantIR can repair those white "cracks" you often get in old photos. Most photo restoration tools I have seen can't do it and refer you Photoshop or similar to fix those type of issue. Thanks!

Hi Im using ComfyUI via Stability Matrix. Can you tell me how to add the Python Dependencies because Stability Matrix does not have a Python Embed folder?

oohh.... this thing just completely destroyed my Comfyui installation!!!! I can't even start it anymore!! D:\comfyui>.\python_embeded\python.exe -s ComfyUI\main.py --windows-standalone-build No pyvenv.cfg file

The only youtuber i always like the video before watching because you know it will be good 👍👍

Hey there ! Thank you for explaining this is such great detail. I have a question How would you go about doing this for ArchViz renders ? I’ve seen people post renders remastered with krea on so many archviz creators. If you could enlighten me on this :)

Very useful…. many thanks amigo!❤️🇲🇽❤️

A masterclass presentation, well done and thank you.

👍

It is cool man! I did it but only with your help. Thanks. P.S. To install insightface , i needed to put whl file in to python_embeded folder.

Missing Node Types When loading the graph, the following node types were not found PulidEvaClipLoader PulidInsightFaceLoader PulidModelLoader ApplyPulid pls help

One of the best tutorials I found, thanks!

When I try to use your workflow, the "Load Image" option isn't appearing. Am I missing something? Thanks!

Can we please talk about the fact that all the the Roman numbers on the clock are correct???!!!! That is nuts!!!!!

So if I use multiple realistic images of a person as reference and I want the the result to look as similar as possible to that person which tool should I use please?

its crazy how un-intuitive this whole process is, despite the people that make it being master coders. Like even Roblox games have mod loading managers.

Wow You saved me.

Thanks you, I can't believe all the trouble I had just because of one duplicate folder. Really appreciate your effort!

Nice tutorial

This is awesome, I struggled for ages to get this installed. Very clear guide, thanks man

Legend! Thanks Sir <3

i m getting math 1and math 2 not compatable error can you helpme to fix this

Thank you SO much!!! Beautifully explained!!! I was going through rabbit hole after rabbit hole of "tutorials" - all of which came to no good use - and as a beginner, it can get overwhelming to the point where you start to second guess your own capabilities!😣 Luckily I came across this video! As a coding illiterate, I was able to follow along easily, and accomplish what was taking me ages before! Again, thank you! 🙏🙏Subscribing now!!!

hey i am getting an error message saying that the gpu is large or something

Just a note: I struggled for hours trying to install the insightface_0.7.3-cp31x-cp31x-win_amd64.whl. Turned out I needed to check to make sure not only that my version of python on the system matched the one comfyui was using - they didn't, had to fix that - but also that the path statement was correct... and after all that, I was still getting an "the [insightface_0.7.3-cp31x-cp31x-win_amd64.whl] is invalid" error. If this happens to you, it's because right-clicking on the name of the file and saving as will not give you the file you need. You need to click on it, and then you'll see - top righthand corner - the RAW option with a download button to the right of it. Use that and you'll get a file that works. You'll notice that the newly downloaded file has a completely different file size. BTW, this issue in mentioned in the Issues section for this github page.

Thanks you for Detailed videos.

Thanks so much, Sharvin! I really appreciate your detailed explanation of things and your openly sharing the workflows. One thing: how can one add Loras to these workflows, for those of us who still find ComfyUI confusing? Can you share this information or do a quick demo of what to do/where to insert it? If that's too much to ask, I certainly understand and still thank you for your informative videos.

I'm getting a lot of all black images, do you know why? 40 steps, CFG scale 5.4, Euler, SGM Uniform, CLIP + T5, Clip l, Clip G, and T5XXL loaded, 1440x1440. Rendered in SwarmUI(uses comfyui background)

Thank you, very well explained and summarized, I will link it again under my latest video.

I'm getting an error in the DualClipLoader: required input is missing. I don't have either of your clip_names 1 and 2. How do I get them and in what folder should I put them? Thanks in advanced

Thanks, Sharvin , pls can you talk about the new InstantIR and how to install it?

thks for uploading also the images to your Github. May I suggest a topic for you: RUNPOD : making a comprehensive usage tutorial with a low cost hourly PC to showcase the most important Unix commands to customize, navigate, import-export files, storage usage and so forth within an environment with per-installed ComfyUi. Many of us cannot afford an expensive local PC, but to finalize in high quality locally tested prompts for text2img, img2img, text2vid and img2vid it would be great to showcase a workflow from an expert as yourself. Others out there with a similar wish?

Thanks for this great information!

Great explanation dude as usual . Thanks for sharing

Thanks, Sharvin - excellent, detailed video as always.

hi Sharvin, excellent. The images on Github? Not yet uploaded?

Another well crafted excellent educational video and a great set of resources sure to be useful to many! Thank you!

👍👍👍

Thank you very much for the information on where to download the T5-XXL and CLIP files! A couple of days ago, it took me about an hour of searching on Google to find out what they were and where to get them)

Hi, nice video. I have a question. for dev original you put load diffusers and for dev fp8 load checkpoint. why dev original is not on checkpoint or viceversa? i'm using mostly Forge, lately im trying Confy and i share my checkpoint folder from forge but there is not diffuser folder to share with. so....is there a way to make work dev original placed in forge? ...there are 2 questions...lol....thanks

Your the best buddy. Thank you for the ridiculous detail!!! 🎉🎉🎉 You Rock!