ComfyUI simple Inpainting image to image

Поделиться
HTML-код
  • Опубликовано: 2 фев 2025

Комментарии • 90

  • @OutOfWards
    @OutOfWards 8 часов назад

    Thank you, Inpainting has always given me anxiety. You healed me. Thank you.

  • @robbiepacheco753
    @robbiepacheco753 11 месяцев назад +12

    Having experimented with various ways of using inpainting in Comfyui I have to admit this tutorial was the better one with great results, I'm only new to this platform and I do struggle with custom nodes. Glad to have found this channel though.

    • @PixelEasel
      @PixelEasel  11 месяцев назад

      thanks for the comment! glad to hear!

    • @GrimGrin94
      @GrimGrin94 10 месяцев назад +1

      I feel like there are a ton of ways to do inpainting in comfy, its just more or less what you prefer, and I assume they all give pretty good results

  • @claudioestevez61
    @claudioestevez61 11 месяцев назад +12

    Thanks for providing the workflow! Massive Like

    • @PixelEasel
      @PixelEasel  11 месяцев назад +1

      thx for providing the comment 😇

    • @gingercholo
      @gingercholo 8 месяцев назад

      @@PixelEasel your a truee G ninja you got discord?

  • @astafzciba
    @astafzciba 10 месяцев назад

    wow, finally someone willing to share their knowledge. very rare. thank you sir you earned a new subscriber

    • @PixelEasel
      @PixelEasel  10 месяцев назад

      Welcome aboard!

    • @gingercholo
      @gingercholo 8 месяцев назад

      its free software and there are so many resources if you LOOK.

  • @yiluwididreaming6732
    @yiluwididreaming6732 11 месяцев назад +2

    subbed for the free work flow.....nice video too!!

  • @jahinmahbub8237
    @jahinmahbub8237 4 месяца назад +1

    I appreciate the simplicity of this workflow. Also How to the point you are. Tutorial video should be more like this.

    • @PixelEasel
      @PixelEasel  4 месяца назад +1

      thanks 😊

    • @jahinmahbub8237
      @jahinmahbub8237 3 месяца назад

      @@PixelEasel I just used this workflow last week. Still works.

  • @bandybuddy
    @bandybuddy 2 месяца назад

    Hey, I really appreciate the effort you put into this tutorial-great content! That said, the TTS voiceover could use some tweaks for better clarity and engagement. TTS systems, like the ones on ElevenLabs, need scripts that are carefully formatted to produce natural-sounding inflection.
    Here’s a tip: try feeding your script into an LLM like ChatGPT and ask it to rewrite the text phonetically for TTS purposes. You can prompt it to use ellipses, commas, and full stops strategically to create natural pauses and emphasis. For technical terms and shortcuts (like 'CTRL+SHIFT+X'), rewrite them phonetically-e.g., 'Control Shift Ex'-to ensure they're spoken correctly. Words like 'inpainting' might need to be split, like 'in... painting,' to sound more accurate.
    Lastly, please bring back the full stops! They’re not just grammar rules-they’re essential for making spoken language easier to follow. Almost every language uses them for a reason. Trust me, these tweaks will make your content not just good but great! But there’s nothing more disheartening than someone who clearly knows their stuff sabotaging their own content with poor delivery.

  • @ghostsupreme1389
    @ghostsupreme1389 11 месяцев назад +3

    Is it possible to run the second KSampler node only for the img2img part and not the first one. This workflow is not practical if the first KSampler node generates multiple images. I just recently started ComfyUI and been using A1111 web ui.

    • @PixelEasel
      @PixelEasel  11 месяцев назад +1

      yep. you can do the second pass only for the img2img

    • @ghostsupreme1389
      @ghostsupreme1389 11 месяцев назад +1

      @@PixelEasel Got it! I just learned about CTRL+M to activate/deactivate node

  • @eddieyu80
    @eddieyu80 4 месяца назад +1

    Change partial area is different from remove partial area. So the action taken require different workflow, correct?

    • @PixelEasel
      @PixelEasel  4 месяца назад

      yes. when you remove something, you need to fill the area with something else

  • @Vansafe0
    @Vansafe0 9 месяцев назад

    Thanks. Simple and easy.

  • @davidmanas95
    @davidmanas95 4 месяца назад +1

    When running your workflow I have this errror: KSampler
    Given groups=1, weight of size [320, 4, 3, 3], expected input[2, 16, 256, 256] to have 4 channels, but got 16 channels instead

    • @doomer66
      @doomer66 2 месяца назад

      I had this error. The problem was that I was using an SDXL model with an incompatible VAE one. I fixed it by switching the VAE model to an SDXL one.

  • @FusionDeveloper
    @FusionDeveloper 9 месяцев назад +1

    At 1:00 maybe change "VAE Encode" to "VAE Encode (for inpainting)" and ALSO attach the mask output from the "Load Image" to the "VAE Encode (for inpainting)"
    You will now have 2 wires coming out of Load Image "MASK".
    Otherwise it may not make changes or make almost no changes, as in my situation.
    The problem with this though, is that if I do less than 1.00 it sees the mask as being gray and I get a gray mouth or gray whatever.

    • @PixelEasel
      @PixelEasel  9 месяцев назад

      you should use only one of them

    • @Airbender131090
      @Airbender131090 7 месяцев назад

      @@PixelEasel one of what?

  • @beeports
    @beeports 4 месяца назад +1

    Thank you for the tutorial, may I know how we can erase the mask, that we accidentally messed up?

  • @amorgan5844
    @amorgan5844 10 месяцев назад +1

    Can you add a lora to the bottom workflow or does it interfere with the inpaint

    • @amorgan5844
      @amorgan5844 10 месяцев назад +1

      Aaah never mind I see the copy paste already makes the lora connections!

    • @PixelEasel
      @PixelEasel  10 месяцев назад +1

      this workflow is good only for small changes, i'm working on another one for large areas

  • @Radarhacke
    @Radarhacke 9 месяцев назад

    Well done!

  • @HereForASeason
    @HereForASeason 6 месяцев назад

    How are you running the queue without the other ksampler firing? Are you bypassing it but just not showing that step in the video? I see so many videos where it looks like they're just clicking the queue button and it ignores the entire top half of the workflow.

    • @PixelEasel
      @PixelEasel  6 месяцев назад

      If you use fix seed and don't change anything else. it's the same output so the k sampler does not fire

  • @daryladhityahenry
    @daryladhityahenry 6 месяцев назад

    What is the LORA that you use? And... Is lcm sampler is great if for inpainting? Thanks.

    • @PixelEasel
      @PixelEasel  6 месяцев назад

      it's lcm lora. that why I use lcm sampler. and you more than welcome 🙏

    • @daryladhityahenry
      @daryladhityahenry 6 месяцев назад

      @@PixelEasel I see! Thank you :) Will find out more about that LORA.

  • @Gabey05
    @Gabey05 11 месяцев назад +1

    What if I just want to use a previous generated image? Just load it and inpaint directly, I dont want to generate a new image

    • @PixelEasel
      @PixelEasel  11 месяцев назад

      you can upload any image

  • @smert_rashistskiy_pederacii
    @smert_rashistskiy_pederacii 8 месяцев назад +1

    This is a very easy to understand guide. Thank you. But to make it really easy and repeatable you had to add models in VAE and checkpoints because 1st run of your workflow shows a lot of errors. And for some reason 1st run made some plate out of nowhere which is pretty much confused me.

    • @PixelEasel
      @PixelEasel  8 месяцев назад

      thanks. I will update the workflow

  • @alirezaraisi-h4t
    @alirezaraisi-h4t 4 месяца назад

    Hello
    I downloaded the vae file and put it in the vae folder, but it gave me an error again

  • @0x0abb
    @0x0abb 3 месяца назад

    Must it work with Lora?

  • @walagg
    @walagg 3 месяца назад

    what browser is that?

  • @dfgoijoi
    @dfgoijoi 4 месяца назад

    is this possible with flux dev ? thanks

  • @AmandaFessler
    @AmandaFessler 9 месяцев назад +1

    Thanks for the tutorial! I had no idea I could inpaint in ComfyUI! Does this work with highres pics/Pony XL? I just wanted to adjust a character's face but I keep getting something that looks lowres... Kind of reminds me of what happens when you inpaint on a1111 without selecting "only masked". Idunno....

    • @PixelEasel
      @PixelEasel  9 месяцев назад

      thanks for commenting! Maybe this workflow will suit you better ruclips.net/video/_LuPU5woth0/видео.html

    • @AmandaFessler
      @AmandaFessler 9 месяцев назад +1

      @@PixelEasel Just went through the tutorial, and I'll admit it looks pretty daunting. I've only been on CUI for less than a week. That said, from the way you explained the problem there, it definitely sounds like just what I need. I'll try to implement it. I hope you don't mind if I ask follow-up questions (perhaps on the new tutorial?). Thanks for directing me there!

    • @PixelEasel
      @PixelEasel  9 месяцев назад

      you more than welcome!

  • @SejalDatta-l9u
    @SejalDatta-l9u 8 месяцев назад +1

    Great video. @pixeleasel Is it possible to automatically the load image in the second workflow to automatically pick up the first image generated/changed without copying and pasting clipspace like in your video?
    I want the OUTPUT of the FIRST flow to become the INPUT of the SECOND flow.
    (excuse the caps, it's there to make it easier to read/understand) :)

    • @PixelEasel
      @PixelEasel  8 месяцев назад

      simple. just connect the output directly to the vae encode

    • @SejalDatta-l9u
      @SejalDatta-l9u 8 месяцев назад +1

      Thank you for the quick answer. Always easy when you know how!! Keep up the great work

  • @backhandsmack1358
    @backhandsmack1358 7 месяцев назад

    0:54 How did you load the Output into the "loadpicture node" so fast

    • @PixelEasel
      @PixelEasel  7 месяцев назад

      probably copy paste

  • @smert_rashistskiy_pederacii
    @smert_rashistskiy_pederacii 8 месяцев назад

    how to get rid of this error?
    Error occurred when executing VAEEncode:
    Could not allocate tensor with 2147483648 bytes. There is not enough GPU video memory available!

    • @PixelEasel
      @PixelEasel  8 месяцев назад

      I would try different vae... but it seems you don't have enough memory

    • @smert_rashistskiy_pederacii
      @smert_rashistskiy_pederacii 8 месяцев назад

      @@PixelEasel yes, this is a strange problem 'cause having 8 GB VRAM I can see only 1024 MB in the CMD of ComfyUi. And that's not my only case but a common problem VRAM.

  • @SejalDatta-l9u
    @SejalDatta-l9u 6 месяцев назад

    Great video - is it possible to close a specific eye?
    Or get the model to wink with a specific eye, for example, the left eye?

    • @PixelEasel
      @PixelEasel  6 месяцев назад

      you'll need to use the mask to choose the eye you want to close, and if it doesnt work with this workflow you can try this one ruclips.net/video/_LuPU5woth0/видео.html

    • @SejalDatta-l9u
      @SejalDatta-l9u 6 месяцев назад

      @PixelEasel I'll give it a go. Thanks for thr suggestion. I can make one eye shut, but no wink.

  • @leonardovidalcorialopez5124
    @leonardovidalcorialopez5124 5 месяцев назад

    Hello bro, im new on this
    i have the next troubles. can help me please
    Prompt outputs failed validation
    VAELoader:
    - Value not in list: vae_name: 'None' not in []
    LoraLoader:
    - Required input is missing: lora_name

  • @damned7583
    @damned7583 9 месяцев назад

    How do I download your load checkpoint?

    • @PixelEasel
      @PixelEasel  9 месяцев назад +1

      you can find it on civitai

    • @damned7583
      @damned7583 9 месяцев назад

      @@PixelEasel how to install in comfyui for colab?

  • @-dimar-
    @-dimar- 10 месяцев назад +1

    I got bad results, maybe try to update the guide

    • @PixelEasel
      @PixelEasel  10 месяцев назад +1

      this workflow is good for small changes. I'm working on an inpainting workflow for bigger changes, I'll upload it in the near future

  • @huiAPPOAJ
    @huiAPPOAJ 6 месяцев назад

    when changing face expressions it is better to use other methods since different expressions change the whole face, not just parts of it

    • @jensenkung
      @jensenkung 6 месяцев назад

      I agree, can you share what the other methods are?

    • @PixelEasel
      @PixelEasel  6 месяцев назад +1

      you can try this workflow ruclips.net/video/VwEcGIBwsyw/видео.html

  • @RuinDweller
    @RuinDweller 7 месяцев назад

    This isn't working for me. :( I think I've set everything up exactly as you have, but I cannot find "pytorch_lora_weights_SD.safetensors", I can only find "pytorch_lora_weights.safetensors". Does that even matter? I'm not getting an error message, It's just not changing the image at all. :( I have the denoise set to a higher value, also - still nothing. :(

  • @thebuniverse6739
    @thebuniverse6739 3 месяца назад

    might as well use midjourney, too many errors and frustrations

  • @ismgroov4094
    @ismgroov4094 8 месяцев назад

    thx

  • @ThoughtFission
    @ThoughtFission 11 месяцев назад +3

    Really good video. Unfortunate that your AI voice is so bad.

    • @PixelEasel
      @PixelEasel  11 месяцев назад +1

      thx. working on it... I think it's getting better in the last videos! I'll try to make it better and better

  • @MarkMartin-k6s
    @MarkMartin-k6s 5 месяцев назад

    Aurelia Land

  • @ekot0419
    @ekot0419 5 месяцев назад

    I am sorry, I have to stop watching your channel. Nothing works... Not even this simple one... I think you are very skilled. But you are very bad at explaining things. Not to mention about the ai voice. Even with AI voice, you can still make it more comprehensive... But you choose to make this 5 minutes...

  • @sarpogartis
    @sarpogartis 6 месяцев назад

    outdated content

    • @PixelEasel
      @PixelEasel  6 месяцев назад +1

      you can try this method for inpainting ruclips.net/video/_LuPU5woth0/видео.html

  • @davidf67
    @davidf67 11 месяцев назад +2

    horrible voice generator

    • @PixelEasel
      @PixelEasel  11 месяцев назад +1

      sorry to hear! still working on it

  • @Andreas-gh6is
    @Andreas-gh6is 5 месяцев назад

    Text to speech? Immediate downvote...

  • @ChenYenger
    @ChenYenger 11 месяцев назад +2

    Plzz make a video about "How to install comfy ui With "chackpoint & lora"

    • @PixelEasel
      @PixelEasel  11 месяцев назад +1

      will make one soon!!!

  • @-Kurokawa-
    @-Kurokawa- 11 месяцев назад

    getting "- Value not in list: lora_name: 'pytorch_lora_weights_SD.safetensors' not in []" error is there a link to aquire this currently useing picx model

    • @PixelEasel
      @PixelEasel  11 месяцев назад

      it the name of lcm lora. if u didnt install the model yet you can find it here
      huggingface.co/latent-consistency/lcm-lora-sdv1-5/tree/main