Visual Style Prompting
Added 2024-03-17 22:20:01 +0000 UTCVisual Style prompting allows you to use an image as a style without the need for any additional fine-tuning or training. Just drop and go! One of the best so far, I think :)
You can find the two ComfyUI workflows I use in my Visual Style Prompting video attached here. They're both the same, just one is set up with stable diffusion 1.5 model names and the other is with SDXL ones.
The original repo can be found at https://github.com/naver-ai/Visual-Style-Prompting
The ComfyUI custom node is over at https://github.com/ExponentialML/ComfyUI_VisualStylePrompting
Update: Also added a version with canny at the end instead :)
Update: New IP Adapter and Visual Style Prompting Nodes in v4 :)
Update: Node now requires latent rather than image input
Comments
This is super old now and they never fixed the node, meaning only the older version worked back then - https://github.com/ExponentialML/ComfyUI_VisualStylePrompting/tree/712a41579e730c5db87d68c2dcde4e92c48ab2cc - the IPAdapter node is better supported these days
Nerdy Rodent
2024-09-17 19:35:15 +0000 UTCi have error in V4: Failed to validate prompt for output 98: * ApplyVisualStyle 94: - Required input is missing: reference_latent - Required input is missing: clip Output will be ignored --- Help me pls
Xuân Nguyên
2024-09-17 05:09:52 +0000 UTCOne place is here - https://civitai.com/models/191053/poltergeist-xl
Nerdy Rodent
2024-09-10 11:51:22 +0000 UTCwhere can i download the model SDXL/poltergeistXL_v12 ?
David Garcia
2024-09-07 06:30:59 +0000 UTChello mr @nerdyrodent. if it's not too much trouble, can you please include a link to your Patreon with the video-specific information in the description of the accommodating video? I'm lazy and I don't want to scroll through and find your resource files on Patreon after watching your YouTube video separately. Thank you, either way.
Chariti Canny
2024-06-01 04:23:06 +0000 UTCAs they've not fixed their updated node, it's best to stick to the version old version (like I used in the video) - https://github.com/ExponentialML/ComfyUI_VisualStylePrompting/tree/712a41579e730c5db87d68c2dcde4e92c48ab2cc
Nerdy Rodent
2024-05-30 11:20:00 +0000 UTCis it possible to get an updated version? getting lost in this one. maybe from @Birdfingers?
brian van montfoort
2024-05-28 20:32:02 +0000 UTCLooks like it got an update which broke it - https://github.com/ExponentialML/ComfyUI_VisualStylePrompting/issues/29 - fingers crossed it gets a fix soon!
Nerdy Rodent
2024-04-25 14:07:37 +0000 UTChey - just downloaded the v4 but i am getting an error with the apply visual style prompting, i believe the latest update changed the 'reference_image' to 'reference_encode' so now the image needs to be vae encoded and then plugged into the reference_encode would you be able to look at this, as the outputs im getting are not good
Jack Kirby
2024-04-25 00:09:19 +0000 UTCAdded a v4 thanks to the brand new IP Adapter and Visual Style Prompting nodes
Nerdy Rodent
2024-03-25 22:30:02 +0000 UTCUnfortunetly it looks like the latest IPAdapterPlus removed parts of the workflow, specifically IPAdapterApply. I'm working to get a version working without it
Exiled Rogue
2024-03-25 11:59:23 +0000 UTCThis is epic NR. It took a fair while to reconnect it all (I'm not the hugest fan of UE - it makes large workflows easier yet more confusing somehow?). For anyone else playing at home you might need to re-add and reconnect all the Apply Visual Style Prompting nodes because it seems that an update they have done recently has changed things. I also reconnected everything that was using the Use Everywhere nodes and changed the canny map to a suitable one for SDXL and while it looks like an explosion at the spaghetti factory it runs like a dream... like a dream I tells ya!
Birdfingers
2024-03-24 05:53:05 +0000 UTCNice "update" or should I say improvement to the ipadapter no lora style you did last year.
KING LIFER
2024-03-20 07:11:16 +0000 UTCThank you!
ED-3D
2024-03-18 17:28:49 +0000 UTC
![[HOPE]](https://nokimo.com/istorage/100331.jpg)
