ComfyUI simple Inpainting workflow using latent noise mask to change specific areas of the image #comfyui #stablediffusion #inpainting #img2img follow me @ / pixeleasel workflow: drive.google.com/file/d/1Y_53...
Пікірлер: 53
@claudioestevez613 ай бұрын
Thanks for providing the workflow! Massive Like
@PixelEasel3 ай бұрын
thx for providing the comment 😇
@gingercholo22 күн бұрын
@@PixelEasel your a truee G ninja you got discord?
@robbiepacheco7533 ай бұрын
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.
@PixelEasel3 ай бұрын
thanks for the comment! glad to hear!
@grimgrin72452 ай бұрын
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
@yiluwididreaming67323 ай бұрын
subbed for the free work flow.....nice video too!!
@PixelEasel3 ай бұрын
thanks! good to know!
@astafzciba2 ай бұрын
wow, finally someone willing to share their knowledge. very rare. thank you sir you earned a new subscriber
@PixelEasel2 ай бұрын
Welcome aboard!
@gingercholo22 күн бұрын
its free software and there are so many resources if you LOOK.
@FusionDeveloperАй бұрын
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.
@PixelEaselАй бұрын
you should use only one of them
@Vansafe0Ай бұрын
Thanks. Simple and easy.
@PixelEaselАй бұрын
thanks!
@RadarhackeАй бұрын
Well done!
@PixelEaselАй бұрын
thanks!
@PixelEaselАй бұрын
thanks 😊!
@jbnrusnya_should_be_punished19 күн бұрын
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.
@PixelEasel19 күн бұрын
thanks. I will update the workflow
@user-pn6ey5dn4y4 күн бұрын
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) :)
@PixelEasel4 күн бұрын
simple. just connect the output directly to the vae encode
@user-pn6ey5dn4y4 күн бұрын
Thank you for the quick answer. Always easy when you know how!! Keep up the great work
@ismgroov409423 күн бұрын
thx
@AmandaFesslerАй бұрын
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....
@PixelEaselАй бұрын
thanks for commenting! Maybe this workflow will suit you better kzbin.info/www/bejne/lX3YgYhrrNSnnpI
@AmandaFesslerАй бұрын
@@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!
@PixelEaselАй бұрын
you more than welcome!
@user-xf8wr8ml4e3 ай бұрын
Plzz make a video about "How to install comfy ui With "chackpoint & lora"
@PixelEasel3 ай бұрын
will make one soon!!!
@ghostsupreme13893 ай бұрын
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.
@PixelEasel3 ай бұрын
yep. you can do the second pass only for the img2img
@ghostsupreme13893 ай бұрын
@@PixelEasel Got it! I just learned about CTRL+M to activate/deactivate node
@amorgan58442 ай бұрын
Can you add a lora to the bottom workflow or does it interfere with the inpaint
@amorgan58442 ай бұрын
Aaah never mind I see the copy paste already makes the lora connections!
@PixelEasel2 ай бұрын
this workflow is good only for small changes, i'm working on another one for large areas
@Gabey053 ай бұрын
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
@PixelEasel3 ай бұрын
you can upload any image
@mick77273 ай бұрын
In the 'load image' node you can select whatever you want. PixelEasel simply edited out that part for privacy's sake maybe.
@damned7583Ай бұрын
How do I download your load checkpoint?
@PixelEaselАй бұрын
you can find it on civitai
@damned7583Ай бұрын
@@PixelEasel how to install in comfyui for colab?
@jbnrusnya_should_be_punished19 күн бұрын
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!
@PixelEasel19 күн бұрын
I would try different vae... but it seems you don't have enough memory
@jbnrusnya_should_be_punished19 күн бұрын
@@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.
@-dimar-2 ай бұрын
I got bad results, maybe try to update the guide
@PixelEasel2 ай бұрын
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
@ThoughtFission3 ай бұрын
Really good video. Unfortunate that your AI voice is so bad.
@PixelEasel3 ай бұрын
thx. working on it... I think it's getting better in the last videos! I'll try to make it better and better
@davidf673 ай бұрын
horrible voice generator
@PixelEasel3 ай бұрын
sorry to hear! still working on it
@-Kurokawa-3 ай бұрын
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
@PixelEasel3 ай бұрын
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