ComfyUI: Style Aligned via Shared Attention (Tutorial)

This tutorial includes 4 Comfy UI workflows using Style Aligned Image Generation via Shared Attention. The tutorials focus on workflows for Text2Image with Style Aligned in Batches, Reference & Target Image Style Aligned along with the use of multi ControlNet with Style Aligned.

------------------------

------------------------

TimeStamps:

0:00 Intro.
0:48 Requirements.
2:39 Batch.
10:01 Batch, ControlNet.
12:06 Reference Image.
15:22 Reference Image, ControlNet.

[controlaltai]

Update 2: ComfyUI will create batches based on available VRAM. If Batches of 8 is breaking the Style Align (i.e. style align applies up to "x" number images then resets), Reduce the batch size. If the entire batch is not loaded in VRam and batches are load in batches via ComfyUI, style aligned will not work as intended. Solution is to reduce the batch size. So do in batches of 2-4 and keep repeating the first image changing other images prompts. The VRAM in the tutorial was 24 GB. On lower VRAM reduce batch size, approx 4 for 12 GB and 2 for 6GB.

Update: Ignore step at 2:10, The dev master branch has been updated. You should now get the node via default Comfy Manager install.

[Shisgara]

OMG 🤩 I'll have to re-watch this video over and over again until I can realise something 🙈Unbelievable! Thanks for sharing ❤

[WiLDeveD]

Impressive Tutorial ❤❤❤ very useful and informative 💯💯💯 Thanks

[bh]

This is something I was looking forward to since the paper was released. Thanks so much for letting us know, and for the great tutorial.

[g-grizzle]

i have found your videos extremely helpful thank you for the effort and time you have put into making these.

[cgartist]

Amazing! thank you! it is really mind blowing! God, where do you get all this? thank you for sharing this treasure!

[LuxElliott]

Another wonderful video. You are great teachers and I'm learning a lot from what you're doing. If it is OK, I'd love to make a request. I'm becoming frustrated with nearly anything I create the subjects are looking and posing for the camera/viewer. I know there are lots of techniques, and I plan to explore them; however, I'd love to see ways to create scenes where the subject/s is not posing for the camera. I want to see shots as if I were out with my camera taking pictures of the real world in action - or general creative scenes, but still have some control of what is happening in the scene. Thanks again for all you do.

[damsotaku]

Amazing tutorial, thanks a lot for sharing ^^

[goor]

nice! I copied the workflow, and added control net but with softedge using an already created image so simpler, but working in the same way more or less. I found an interesting "bug?" With ControlNet included it creates an error if the batch number is an odd number. So I can do a batch of 2, 4, 6 etc. But 3, 5, 7, etc gives an error... scratching my head on this one.

[freshlesh]

Thanks for the tutorial. I am using your Style aligned with controlnet workflow and the Blip analyzer gives a: The size of tensor a (6) must match the size of tensor b (36) at non-singleton dimension 0
I've tried updating and doing a clean install but it looks like the Blip analyze image node breaks the workflow. I bypassed and it works but doesn't actually produce a mask like in the example. Can you suggest a work around or similar node that might resolve it?

[valorantacemiyimben]

5:25 Hello. The boxes with this prompt do not appear for me. How can I open them?

[KINGLIFERISM]

Odd I dont have the style aligned Reference Latent. I have the other two though. Nevermind... I had to go to the github not just using Comfy Manager

[qkrxodls]

Hello Seth, sent you an email regaring making the thread-car you demoed on the last part of this session. sent my workflow, and the result. I tried various controlnet values and style align parameters, but was not able to achieve close to your's. Would deeply appreciate if you guide me with the matter. Best,

[ywy-vn]

bro, thanks for your brilliant tutorial, is there any chance to use an existed img instead of generating an img, because I want the result has a face I have, not random

[chrisfromthelc]

If I have one (or more) Loras that I want to use on the styled image, where should that go in the Reference Image flow?

[jayolay]

I followed your workflow for "referance image" but the "StyleAligned Reference Sampler" seems to only output a black image... any idea what i'm missing?
thx a ton!

[CerbyBite]

Any idea why the node "StyleAligned Sample Reference Latents" doesn't show up for me?

[AnimeDiff_]

maybe i'm missing something, i wanted to try to use this with animate diff to create style aligned video. I'm also wondering, is there a way to use this with img2img? if this could work with animate diff, it would be possible to run CN from a source vid to make some very interesting vid2vid. thank you

[dflfd]

is there a way to provide a reference style image rather than generating on the fly?

[Steve.Jobless]

bro why mine doesn't have style aligned sample reference latents node, i was follow all the requirements