An Image from Start to Finish using Photoshop and ComfyUI

  Рет қаралды 1,645

Rob Adams

Rob Adams

4 ай бұрын

I thought I would do an AI video with all the bits people usually edit out... where it all goes wrong and show how to change tack and sort out unexpected problems. It's not often mentioned that making AI images which fit your intention is slightly like herding cats.

Пікірлер: 11
@jaimeortega8939
@jaimeortega8939 4 ай бұрын
Love this video because it demystifies that notion that one gets what one looks for just by one clever prompt
@robadams2451
@robadams2451 4 ай бұрын
The problem is AI can produce a nice-looking image from any set of words. So people type in some daft prompt with "masterpiece" and "trending on Artstation" in it and a great image appears. They then think "I did that!" but they didn't, they only did typing which was mostly ignored.
@Mehdi0montahw
@Mehdi0montahw 4 ай бұрын
@mick7727
@mick7727 4 ай бұрын
Curious, but did you try creating the AI image first without adding all those little nitty gritty details just to see what happens? Reason I ask is, I'm not very creative on that spectrum of detail so I'm wondering if this method would be worth the effort. Cheers! Oh, I really enjoyed the video about the red-dressed girl and the effects of adding styles and artists.
@robadams2451
@robadams2451 4 ай бұрын
Not in this case, occasionally I get a prompted image I want to take further but they are mostly very generic and I don't feel any connection to them. The art style thing is quite amusing at present because the images used to train are very hit or miss and the captioning poor. Lots of internet scraped imagery has unconnected words associated with the image. I believe there are advances in the pipe line as ChatGPT 4 and others can caption more precisely.
@user-dj3rd4my5k
@user-dj3rd4my5k 4 ай бұрын
There is a photoshop to comfy ui node... seems like it would make great for your use cases.
@user-dj3rd4my5k
@user-dj3rd4my5k 4 ай бұрын
It allows for you to use photoshop as a front end.
@robadams2451
@robadams2451 4 ай бұрын
Yes, I've looked at it, I don't have the hardware unfortunately. It's main use seems to be that Comfy iterates as you edit. @@user-dj3rd4my5k
@maximood-tired
@maximood-tired 4 ай бұрын
very interesting. maybe i missed the info, but do you run SD on a different machine?
@robadams2451
@robadams2451 4 ай бұрын
No I quit out of Photoshop as it makes ComfyUI slow due to taking a chunk of GPU band width. There is a plugin where you can automatically feed information to nodes from Photoshop but it won't work on my set up at present.
@maximood-tired
@maximood-tired 4 ай бұрын
does SD run on macos? as far as I knew it only runs on cuda hardware efficiently@@robadams2451
An Illustration in ComfyUi From Start to Finish in One Workflow
41:34
Controlling Framing Composition in ComfyUI
26:57
Rob Adams
Рет қаралды 1,7 М.
OMG😳 #tiktok #shorts #potapova_blog
00:58
Potapova_blog
Рет қаралды 3,3 МЛН
Please be kind🙏
00:34
ISSEI / いっせい
Рет қаралды 146 МЛН
She ruined my dominos! 😭 Cool train tool helps me #gadget
00:40
Go Gizmo!
Рет қаралды 56 МЛН
OMG🤪 #tiktok #shorts #potapova_blog
00:50
Potapova_blog
Рет қаралды 17 МЛН
Fixing the Seams from a Tiled Upscaler in ComfyUI
8:17
Rob Adams
Рет қаралды 428
ComfyUI Scribbles to Masterpieces Workflow!
12:06
Grafting Rayman
Рет қаралды 3,5 М.
Beginner's Guide to ControlNets in ComfyUI
16:02
Rob Adams
Рет қаралды 1 М.
Building Planets and Spaceships in ComfyUI
16:23
Rob Adams
Рет қаралды 678
L4: Img2Img Painting in ComfyUI  - Comfy Academy
10:41
Olivio Sarikas
Рет қаралды 33 М.
ComfyUI - Live Stream!  Let's make some amazing art with Stable Diffusion!
1:48:05
Groups, Templates and Workflows in ComfyUI
10:59
Rob Adams
Рет қаралды 341
Complex InPainting using ComfyUI
23:50
Rob Adams
Рет қаралды 1,4 М.
OMG😳 #tiktok #shorts #potapova_blog
00:58
Potapova_blog
Рет қаралды 3,3 МЛН