ComfyUI Tutorial Series: Ep12 - How to Upscale Your AI Images

แชร์
ฝัง
  • เผยแพร่เมื่อ 29 ธ.ค. 2024

ความคิดเห็น • 127

  • @SebAnt
    @SebAnt 3 หลายเดือนก่อน +26

    A small token of my appreciation. Thank you for taking so much time to thoroughly test, select the best, and so clearly explain comfyUI to us. The workflows on your discord work like a charm 🙏🏽

    • @pixaroma
      @pixaroma  3 หลายเดือนก่อน

      Thank you so much ☺️ glad it helped

  • @RiftWarth
    @RiftWarth 14 วันที่ผ่านมา +2

    Amazing video. Great job on this and thanks for the workflows. 🙂

    • @pixaroma
      @pixaroma  14 วันที่ผ่านมา +1

      thank you for support 🙂

  • @santhoshvasamsetti9165
    @santhoshvasamsetti9165 หลายเดือนก่อน +3

    Great work! Appreciate your time and effort.

    • @pixaroma
      @pixaroma  หลายเดือนก่อน

      Thank you so much 😊

  • @Patricia_Liu
    @Patricia_Liu 3 หลายเดือนก่อน +2

    Thanks!

    • @pixaroma
      @pixaroma  3 หลายเดือนก่อน +1

      Thank you so much for your support😊

    • @Patricia_Liu
      @Patricia_Liu 3 หลายเดือนก่อน

      @@pixaroma Thank YOU! 💖

  • @lucifer9814
    @lucifer9814 3 หลายเดือนก่อน +1

    these upscalers are absolutely amazing, thank you

  • @WanderlustWithT
    @WanderlustWithT 3 หลายเดือนก่อน +1

    Bro your tutorials and workflows are super useful, thank you!

  • @philippeheritier9364
    @philippeheritier9364 3 หลายเดือนก่อน +1

    wow finally a good upscaler, thank you very much.

  • @SumoBundle
    @SumoBundle 3 หลายเดือนก่อน +2

    Very detailed tutorial. Congrats and thank you for the effort

  • @jorgeluismontoyasolis9800
    @jorgeluismontoyasolis9800 3 หลายเดือนก่อน

    Thank you so much. Your work is amazing and highly appreciated. I usually find tutorials about this topic that doesn't show the details behind the process or the role of each node.

  • @RandMpinkFilms
    @RandMpinkFilms 26 วันที่ผ่านมา

    Man, I subbed to your channel after giving this a try. This is by far the best upscaling tutorial and workflow I've come across in the past year. I've seen about 15. No joke. A huge thank you!

    • @pixaroma
      @pixaroma  26 วันที่ผ่านมา

      Thank you so much🙂

  • @ESheridan
    @ESheridan 2 หลายเดือนก่อน +1

    Amazing! Thank you so much for your special explanation!🤩🤩🤩

  • @devon9374
    @devon9374 2 หลายเดือนก่อน

    Another banger, I love open source AI so much ❤

  • @VietnamShorts
    @VietnamShorts หลายเดือนก่อน

    very good, precise explanation. Thank you.

  • @jennifertsang6572
    @jennifertsang6572 3 หลายเดือนก่อน

    Very detailed video & great information!

  • @MarjoleinPas-interieurontwerp
    @MarjoleinPas-interieurontwerp 29 วันที่ผ่านมา

    thank you so much, this is an amazing workflow

  • @Queenbeez786
    @Queenbeez786 หลายเดือนก่อน +2

    thank you so much angel. now tell me how you get those performance bars on the right above your settings? thank you

    • @pixaroma
      @pixaroma  หลายเดือนก่อน +1

      Install the crystools node from manager

  • @eineatombombe
    @eineatombombe 2 หลายเดือนก่อน +3

    this is like the only tutorial without attractive woman clickbait thumbnail

  • @59Marcel
    @59Marcel 3 หลายเดือนก่อน

    Fantastic tutorial, Thank you.

  • @Fayrus_Fuma
    @Fayrus_Fuma 3 หลายเดือนก่อน +1

    Eeeeeeee boy! Really Thx man!

  • @aquaartistrytutorials
    @aquaartistrytutorials 3 หลายเดือนก่อน +1

    Awesome!

  • @patrickfougere0001
    @patrickfougere0001 3 หลายเดือนก่อน +3

    Great video! (Question:1.8) Where is the setting so you can see the CPU,GPU ect... On the menu gui?????

    • @pixaroma
      @pixaroma  3 หลายเดือนก่อน +2

      Is a custom node install crystools form custom nodes manager

    • @patrickfougere0001
      @patrickfougere0001 3 หลายเดือนก่อน +2

      @@pixaroma thank you! I'll check that out tonight!!

    • @patrickfougere0001
      @patrickfougere0001 3 หลายเดือนก่อน +1

      @@pixaroma I would also love to see a PROPER video on text syntax, tips and tricks for "CLIP text encode prompt". Like what is the proper format? When should I use 'underscores' how does *{(option1|option2|option3):1.2} work in an actual flow. I would love to see a video on this! Great work keep it up.

  • @MannyGonzalez
    @MannyGonzalez 3 หลายเดือนก่อน

    I am very surprised this works so well. I have done pixel space upscaling using [euler/beta] with horrible results and even with very low denoise (.20-.35) the composition changes too much.
    Using dpmpp_2m/karras seems to be the trick.
    Thank you.

  • @gameboypaul1702
    @gameboypaul1702 3 หลายเดือนก่อน

    Thank you... When you add the kSampler at @14:33, is the upscaling now using Flux? And not just the Siax?

    • @pixaroma
      @pixaroma  3 หลายเดือนก่อน +1

      Yes, i make the image larger and sharper, then is running through flux again, just like you do on image to image, just instead of uploading a new image, I take the image from the previous generation from vae decode, i mage it bigger, entering again in ksampler so basically is an image to image but with bigger image instead of a small image.

  • @eslamafifi1020
    @eslamafifi1020 3 หลายเดือนก่อน

    Great tutorial, thank you very much

    • @pixaroma
      @pixaroma  3 หลายเดือนก่อน

      Glad I could help ☺️

  • @Moral114
    @Moral114 4 วันที่ผ่านมา

    Great tutorial. One question: how could the upscaled results look similar to the first one since they go through a different seed in the second KSampler? Thanks.

    • @pixaroma
      @pixaroma  4 วันที่ผ่านมา

      You can reduce the denoise strength to make it look more similar

    • @Moral114
      @Moral114 4 วันที่ผ่านมา

      @@pixaroma Thanks for the quick response. Could feeding both Ksampler with the same seed also work?

    • @pixaroma
      @pixaroma  4 วันที่ผ่านมา +1

      It works but is using the same image and gets like super sharp or overcooked, like HDR look, I avoid using same seed

  • @АндрейАлександрович-ч7ж
    @АндрейАлександрович-ч7ж 3 หลายเดือนก่อน +2

    Thank You

  • @AnNguyen-pd2xi
    @AnNguyen-pd2xi 3 หลายเดือนก่อน

    2:40 . Hello. Can you explain how to get the result image to be exactly the same as the original image? Whenever I use this workflow, the result is always different from the original.

    • @pixaroma
      @pixaroma  3 หลายเดือนก่อน +1

      are you using the same settings I put on the workflow, just download that workflow from discord and test it, you can reduce the denoise on the Ksampler, but if is the same scheduler and sampler and model the result should be the same

    • @AnNguyen-pd2xi
      @AnNguyen-pd2xi 3 หลายเดือนก่อน

      @@pixaroma I created a workflow from a different Sampler with the same structure as your workflow. I noticed that it's basically an image-to-image process and adds upscale after the Sampler. I want to know which parameter determines the result image being similar to the original image but with more details.

    • @pixaroma
      @pixaroma  3 หลายเดือนก่อน +1

      You can't always have similar and with more detail is either similar and you don't get more details, or is less similar so is not constrained and can add more creativity and details. You can add a controll net to keep things more similar like depth and canny that way the composition is the same and lines so you can change more things between those lines. I used the setting in the video snd needed high denoise, with other schedulers it needed less denoise

    • @AnNguyen-pd2xi
      @AnNguyen-pd2xi 3 หลายเดือนก่อน

      The resulting image you created includes additional details but still retains the entire face of the character and the composition without using ControlNet. However, when I run my workflow, the result is a completely different image from the original.

    • @pixaroma
      @pixaroma  3 หลายเดือนก่อน

      @@AnNguyen-pd2xi are you using the same workflow? not sure what workflows you have there, but the workflow I use works like in the video, if you changed something can work differently, so get the same workflows and try to see if works, then see what you did different. Download the workflow from discord and try it.

  • @jonrich9675
    @jonrich9675 3 หลายเดือนก่อน +3

    Next video please make a tutorial on how to use Flux Controlnet and how to make good images with it. 👍

    • @pixaroma
      @pixaroma  3 หลายเดือนก่อน +1

      I will see what I can do ☺️

  • @Mypstips
    @Mypstips 3 หลายเดือนก่อน +2

    Thank you!

  • @CrunchyKnuts
    @CrunchyKnuts 2 หลายเดือนก่อน

    Even with my 3080Ti, I was having a lot of issues with freezing on this one. For some reason, haven't quite found out yet, Comfy isn't clearing VRAM appropriately. My solution was just to put Clean VRAM nodes after most operations. It added a couple seconds on, but prevented freezing.

    • @pixaroma
      @pixaroma  2 หลายเดือนก่อน

      Not sure, you can try to put vae encode and vae decode tiled the version with tiled in name

    • @CrunchyKnuts
      @CrunchyKnuts 2 หลายเดือนก่อน

      @@pixaroma I'll give that a try and let you know

  • @hyejinahn6305
    @hyejinahn6305 3 หลายเดือนก่อน

    I have a Lora that I trainted with Flux dev for my beauty product. Can I incorporate the lora node into the t2i upscale workflow and change the diffusion model to flux dev?

    • @pixaroma
      @pixaroma  3 หลายเดือนก่อน

      yes you can add it between load checkpoint and clip text encode

  • @lowrider6419
    @lowrider6419 3 หลายเดือนก่อน

    Impressive 👍

  • @DreamAnimate
    @DreamAnimate 3 หลายเดือนก่อน

    awesome! is there any way to reduce the grain applied after upscaling?

    • @pixaroma
      @pixaroma  3 หลายเดือนก่อน +1

      is sharpness from the model, if you can try a different uspcale model that has different sharpness maybe, I didnt find yet a solution for that, other upscaler give different results instead of siax i tried RealEsrgan x4, for some illustrations might work but is smooth things too much, 4x_Foolhardi_Remacri might work in some cases, I also tried from the was node suite custom node to add the Image Dragan Photography Filter and has ther ea field for sharpness and reduced to 0.7 or 0.5 that reduce it slight make it more blurry, but didnt find a permanent solution yet

    • @DreamAnimate
      @DreamAnimate 3 หลายเดือนก่อน

      @@pixaroma got it, thanks!

  • @大白熊-z2o
    @大白熊-z2o 27 วันที่ผ่านมา

    Why use gguf model instead of fp8 model? I'm curious

    • @pixaroma
      @pixaroma  27 วันที่ผ่านมา +1

      the quality of q8 is similar to fp16, so fp8 is lower quality compared with gguf q8,
      1. fp16 the original flux dev.
      2. The Q8
      3.Fp8

  • @yapyh2872
    @yapyh2872 หลายเดือนก่อน

    Cool. which ai voice are you using?

    • @pixaroma
      @pixaroma  หลายเดือนก่อน

      VoiceAir and they have the voices from elevenlabs. Voice is called burt us

  • @ValleStutz
    @ValleStutz หลายเดือนก่อน +1

    I‘m using a RTX 3090 but it breakes my vram, so the ksampler can’t work

    • @pixaroma
      @pixaroma  หลายเดือนก่อน

      I have included some low vram workflows on discord for that episodes, try those maybe if dont have enogh vram

  • @BryceHaymond
    @BryceHaymond หลายเดือนก่อน

    why do you scale down before scaling up? that loses resolution before upscaling.

    • @pixaroma
      @pixaroma  หลายเดือนก่อน

      because is too big for the ksampler, and the pixels are replaced anyway when is generated a new image, you can increase it to see, if you have a good video card, but flux has like 2 megapixel limit, after that it doesnt get so good results

  • @robrever
    @robrever 3 หลายเดือนก่อน

    Cool video! I'll definitely try out your approach. However, in AI Search's comfyUI tutorial, he says using tile upscaling yields far better results. Have you tried his method to compare?

    • @pixaroma
      @pixaroma  3 หลายเดือนก่อน +2

      I tried with tiles and Ultimate SD upscalers with controlnet but for me took longer time and the results wasnt as good, maybe i didnt find the right settings, i mean I played a few days, and found this settings by mistakes and just worked good enough for me. I wanted something fast. Is not perfect but for me is good enough for what I need. If I find a better way in the future I will make a new video

  • @Babubabu-f1d2y
    @Babubabu-f1d2y 3 หลายเดือนก่อน

    please make a compy ui video on using and installing mimic motion, i really appreciate your video, it is very clear compared to other TH-camrs, can mimic motion be used on comfy ui on swarm ui?

    • @pixaroma
      @pixaroma  3 หลายเดือนก่อน

      I saw there are some nodes for comfyui with mimic motion so I will check it out, but probably in kater episodes there are still more to cover in static images before i go to motion and video

  • @Dunc4n1d4h0
    @Dunc4n1d4h0 หลายเดือนก่อน

    Old good trick with second sampler works as expected... but how to deal with those "flux lines" at final step?

    • @pixaroma
      @pixaroma  หลายเดือนก่อน

      if the image is under 2 megapixel so is not too big, and the width and height is divisible with 64 you can get usually ok result without lines. You could try different upscalers, i can not use huge images in the ksampler so i need it to do a normal upscale for last step, you can drag a save image before the final upscaler and use a different uspcaler if you want, so if you do a 1024px you could get a 2048 that is over 2 megapixel, so you cand do smaller maybe so the initial image is 960 maybe and the final image would be under 2 megapixel, play with settings

    • @Dunc4n1d4h0
      @Dunc4n1d4h0 หลายเดือนก่อน

      @@pixaroma Thanks for reply, I use 0.5Mpixel with that node as in video with 16:9 ar, then model upscale 4x scaled * 0.5 downscale... so 0.5Mpix becomes 2Mpix (as it upscales in both x &y dimensions), all usual and still lines, that is why I'm asking 🙂

    • @pixaroma
      @pixaroma  หลายเดือนก่อน

      @@Dunc4n1d4h0 I only get it on some images, not sure what cause it, but most of the time I dont get any lines, maybe the prompt influence somehow or some settings, but I didnt figure it out, I usually just run it a few seeds and pick my favorite :)

  • @rufu4981
    @rufu4981 3 หลายเดือนก่อน

    I'm getting Bad Request errors when trying to install upscalers. What might I be doing wrong?

    • @pixaroma
      @pixaroma  3 หลายเดือนก่อน

      can you post some screenshot on discord with workflow and the error you get and comand window error, mention pixaroma there

  • @last-partizan
    @last-partizan 2 หลายเดือนก่อน

    Can you please put a links to downloads on some public site, like github?

    • @pixaroma
      @pixaroma  2 หลายเดือนก่อน

      Only the workflow are on discord but that is free, the rest is public like all the links to models and other stuff are linked to public sites. For me discords is easier because i have them all in same channel and i can link them in the discussion channel when people need help so they don't have to leave discord and can find all they need there.

  • @vb6code
    @vb6code 3 หลายเดือนก่อน

    فيديو جميل وشرح واضح

  • @КристинаБуняева-о3в
    @КристинаБуняева-о3в 3 หลายเดือนก่อน

    Hi (:
    Can you please tell me what is the other use of Upscale besides photoshop? Here I am doing 1280 by 720 resolution for visual novels. Even if I will use in the game is not this screen resolution and FULL HD, but still the difference is almost equal to zero. Thanks 🙂

    • @pixaroma
      @pixaroma  3 หลายเดือนก่อน +2

      i use topazgigapixel Ai is not free, but does a good job for me when i need something fast

    • @КристинаБуняева-о3в
      @КристинаБуняева-о3в 3 หลายเดือนก่อน

      @pixaroma I meant that I'm a rookie. I've read that Upscale is used mostly for photoshop users. I make art for games for VN, there resolution is 1280 by 720. So, after Upscale even in 4 times still no effect for visual novels. Or is it useless for my work? 🙂

  • @konnstantinc
    @konnstantinc 3 หลายเดือนก่อน +1

    Niice

  • @yinodiaz4290
    @yinodiaz4290 3 หลายเดือนก่อน

    Do you have any video that helps me install and set up Flux01 and Confy like for noobs, I have a 24Vram 4090

    • @pixaroma
      @pixaroma  3 หลายเดือนก่อน +1

      episode 1, 8 and 10 th-cam.com/play/PL-pohOSaL8P9kLZP8tQ1K1QWdZEgwiBM0.html

  • @anastasiiailina5044
    @anastasiiailina5044 หลายเดือนก่อน

    Cannot execute because node UpscaleModelLoader does not exist.: Node ID '#136:6' - hmmm could you pls tell me, do you have any idieas?

    • @pixaroma
      @pixaroma  หลายเดือนก่อน

      did you download and load the model? can you post a screenshot with workflow and error on discord on comfyui channel? discord.com/invite/gggpkVgBf3

  • @AlexanderGarzon
    @AlexanderGarzon 3 หลายเดือนก่อน

    Personally I prefer to let the model-upscaler step for the last step, and have the latent img2img upscale as the second, that way you can make a good use of your VRAM, speed up the process and the result ends up the same. so, TLDR: from your workflow, I will swap the generations 2 3

    • @pixaroma
      @pixaroma  3 หลายเดือนก่อน

      I didn't get the right setting with the latent img2img, the image had some artifacts with latent compared to pixel method can you share how you did it on discord? Thanks

  • @hlyanhtet7120
    @hlyanhtet7120 2 หลายเดือนก่อน

    i have nvidia graphic card 2060 super, can i try flux?

    • @pixaroma
      @pixaroma  2 หลายเดือนก่อน +1

      i have that one too on older pc with 64gb of ram also, i use flux schnell, for flux dev takes too much time for me. flux gguf q4 version

  • @saarhadad
    @saarhadad 2 หลายเดือนก่อน

    tnx alot :D

  • @danysvay
    @danysvay 3 หลายเดือนก่อน

    i get an error Install failed: 4x-AnimeSharp Bad Request

    • @pixaroma
      @pixaroma  3 หลายเดือนก่อน

      try to download it manually and put it in the ComfyUI_windows_portable\ComfyUI\models\upscale_models folder from the models manager if you click on model name a page will open from where you can download it

  • @EntaFahemGhalat
    @EntaFahemGhalat 3 หลายเดือนก่อน

    I cant join discord , it says invalid invitation or expired link .

    • @pixaroma
      @pixaroma  3 หลายเดือนก่อน +1

      thanks for letting me know, not sure what happened, here is the new link discord.gg/gggpkVgBf3

    • @EntaFahemGhalat
      @EntaFahemGhalat 3 หลายเดือนก่อน

      @@pixaroma you are very welcome

  • @Daniel-fo6rv
    @Daniel-fo6rv หลายเดือนก่อน

    👏

  • @djwhispers3157
    @djwhispers3157 4 วันที่ผ่านมา

    i think you are awesome

    • @djwhispers3157
      @djwhispers3157 4 วันที่ผ่านมา

      i downloaded and tried out the workflow. You are a saint, an angel from above of workflow heaven. Thank you so much.

    • @djwhispers3157
      @djwhispers3157 4 วันที่ผ่านมา +1

      also, i modded the workflow a little bit to generate image to image. magnifique.

    • @djwhispers3157
      @djwhispers3157 3 วันที่ผ่านมา

      do you have a workflow on how to change clothing on character models?

    • @pixaroma
      @pixaroma  3 วันที่ผ่านมา +1

      I don't have, there is online something with "try on", but it didn't work for me as expected

    • @djwhispers3157
      @djwhispers3157 3 วันที่ผ่านมา

      @@pixaroma right many clothing swap videos out there but do not work. ok we will wait.

  • @timelesshardcore6551
    @timelesshardcore6551 7 ชั่วโมงที่ผ่านมา

    I made a 4608x3072p image with this method. My gpu (RXT3080) and cpu was at its limit and they are not happy with me, but I must say the image is really nice. I think it is way to much, but I found the limit of my pc. From now I make them half size and upscale them without the sampler to get 4k 🤣

    • @pixaroma
      @pixaroma  6 ชั่วโมงที่ผ่านมา +1

      You can also try to use vae decode tiled instead of vae decode maybe that help with lowvram

    • @timelesshardcore6551
      @timelesshardcore6551 6 ชั่วโมงที่ผ่านมา

      With tiles I get some lines in the image, so I was looking for a new solution. I will give it a try. Thanks ✌🏻

  • @jigneshparmar678
    @jigneshparmar678 3 หลายเดือนก่อน

    👏🏻💯🙏🏻

  • @MichaelErickson-i8y
    @MichaelErickson-i8y 3 หลายเดือนก่อน

    Your discord link is unfortunately invalid

    • @pixaroma
      @pixaroma  3 หลายเดือนก่อน

      I changed on the channel description yesterday, but in comments and descriptions some remained unchanged, try discord.com/invite/gggpkVgBf3

    • @rezvansheho6430
      @rezvansheho6430 3 หลายเดือนก่อน

      ​@@pixaromahiii. still invalid link :((

    • @pixaroma
      @pixaroma  3 หลายเดือนก่อน +1

      @@rezvansheho6430 I just test it, it works for me click on it and then click on go to site discord.com/invite/gggpkVgBf3

    • @rezvansheho6430
      @rezvansheho6430 3 หลายเดือนก่อน

      ​@@pixaromaI used a VPN, and now it worked ♥️

  • @fernandohildebrand6319
    @fernandohildebrand6319 17 วันที่ผ่านมา

    Thank you. I can't help financially. I hope the likes and comments bring attention to your channel

    • @pixaroma
      @pixaroma  17 วันที่ผ่านมา

      Thank you, yes that like and comments really helps 😊

  • @m3mee2010
    @m3mee2010 19 วันที่ผ่านมา

    Your videos are great, but it would help if you slowed down your voice er..you talk very fast..

    • @pixaroma
      @pixaroma  19 วันที่ผ่านมา

      Sorry but the AI voice I use doesnt have yet a speed option, it generate the voice from the text I give it, but I dont have a way to make it talk slower :(

  • @chipjohansen8132
    @chipjohansen8132 3 หลายเดือนก่อน +1

    I felt like I have followed along the steps closely and installed everything correctly, but when I try to queue the image I get the following error message. Can you help me figure out what I am missing? I downloaded your Flux Dev Q8 GGUF IMG2IMG with Upscaler workflow and my screen looks exactly like yours in the TH-cam video. Many thanks!
    Prompt outputs failed validation
    UnetLoaderGGUF:
    - Value not in list: unet_name: 'flux1-dev-Q8_0.gguf' not in []
    DualCLIPLoaderGGUF:
    - Value not in list: clip_name1: 't5-v1_1-xxl-encoder-Q8_0.gguf' not in ['clip_l.safetensors', 't5xxl_fp16.safetensors']

    • @chipjohansen8132
      @chipjohansen8132 3 หลายเดือนก่อน

      Never mind. I started with this Ep12. I needed to go back to Ep 10 for the proper GGUF installation.

    • @pixaroma
      @pixaroma  3 หลายเดือนก่อน

      Glad you figured it out, just woke up, you can always mention me on discord and give a screenshot ☺️

  • @FemmeResonance
    @FemmeResonance 2 หลายเดือนก่อน

    I'm so impressive with your work and all the afford you have given here (and in your discord), It really helps beginner like me a lot really. I'm appreciated. And your like button should be OVER 30K. For people who read this message, pls gives a LIKE!!!!! it do not cost you anything! thank you love and respect. ❤❤❤

    • @pixaroma
      @pixaroma  2 หลายเดือนก่อน

      thank you 🙂

  • @chipjohansen8132
    @chipjohansen8132 3 หลายเดือนก่อน

    Thanks!

    • @pixaroma
      @pixaroma  3 หลายเดือนก่อน

      Thank you so much ☺️