L5: Magical Img2Img Render + WD14 in ComfyUI - Comfy Academy
ฝัง
- เผยแพร่เมื่อ 25 ม.ค. 2024
- I built a magical Img2Img workflow for you. In the first workflow, we explore the benefits of Image-to-Image rendering and how it can help you generate amazing AI images. In the second workflow, I created a magical Image-to-Image workflow for you that uses WD14 to automatically generate the prompt from the image input. This is fantastic!
Find my Workflow here: openart.ai/workflows/oliviosa...
Other Lesson Videos:
• L1: Using ComfyUI, EAS...
#### Join and Support me ####
Buy me a Coffee: www.buymeacoffee.com/oliviotu...
Join my Facebook Group: / theairevolution
Joint my Discord Group: / discord
AI Newsletter: oliviotutorials.podia.com/new...
Support me on Patreon: / sarikas - แนวปฏิบัติและการใช้ชีวิต
Indeed amazing!
Thank you for the amazing lectures as always!!!
Thank you for this tutorial video!
Thanks Olivio. Love you.
great work Olivio kepp going on 💪
Thank you Olivio for this Series,, so many tool for creativity --- i scream!
Thank you for making these vids! They really help me get into Comfy without feeling too overwhelmed
This is an amazing technique. I'm getting great results with it.
Thanks for your lesson, it helps a lot, thanks !
I'm already using WD14 for magic prompting lol but I would use concatenate text which is not as nice as this String Function node. So thanks for the trick, I'm gonna update my workflow again ^^ it never stops really
amazing
As I read "WD14" I thought this was some kind of motor oil - but it's quite handy indeed 👍
Hey Dude, your videos are great. I hope if you could make one on 3d model texturing with comfy Ui texture.
Díky!
this could be applied to have congruent detailed styles in animated generations
Hi Olivio, like the WD14 tagger node, is there a node which can get you the BLIP captioning of an image? Would ideally like to use that as input to a segmentation model for swapping things.. TIA! 😊
Next you could do controlnet to make the pose that you want, by another picture you have
I have a short question regarding Automatic 1111. While some checkpoints give fast results, why other check points don't work the same.
Can we get an explanation as to why all of these videos load different VAE's for the decoding? Why is it constant that the vae is never the one from the initial model???
How to download the WD14 in ComfyUI model and which folder to install it in?
6:42 here I'm not able to find string function.
👋
how would you add latent upscale in this type of workflow, where you are using low denoise to get close to input image result. I tried to do latent upscale with low denoise on second K-sampler, but end with a poor image quality. If I increase denoise it changes image which is not I want.
Man I m stuck with this same issue, have you figured a solution yet?
For those of us who are trying to construct these from scratch (following along) I don't see where/how we are supposed to be able to find this "Image Resize" node. There's no "search node" and I don't see it on the node options. Where do these things come from and how are we supposed to know what node collections we need to load down?
The workflow is linked below the Video. This is part 5. If you don't know how to find nodes, watch the other videos. For node search you double click on the background and a search pops up. Use the workflow i provide and install the packs i use via the manager (watch the other videos to learn how to install and use the manager)
Gracias Olivioooooooo
How to fix problem with install imageResize+?
On the window that lets you load and save workflows. go to manager and click install missing custom nodes
the problem is not so easily solved :)@@MrStronghole
@@ingabuga me too, but i find upscale image , its the very similar and work. later i dont find string function...i dont find it
How ai read and convert prompt, i mean who write the code to interpret english words .
the model is trained to create a english word description
I can't find Image Resize node :(
me too, but i find upscale image , its the very similar and work. later i dont find string function...
@@guille1935 I've found the node, calls image-resize-comfyui on github :)
Olivio - Did you give up on A1111 ?
You have to give up on a1111 too,
Comfyui is the future.
Yep comfy is way better.
InvokeAI is better for me)
Thank you so much for your work, I'm learning a lot, a little remark part5 and part7 are missing in the Comfy Academy playlist ;)