download model and install tutorial: https://comfyanonymous.github.io/ComfyUI_examples/z_image/
Description
added upscale
FAQ
Comments (35)
Thanks for sharing!
I can't get the workflow to work lol, but anyway, I managed to install everything without any problems and that's rare!
um 1.1 has no workflow... just a png..
You need to download it.
Drag it into your comfyui
@DrakulValmont666 I did dude and the contents is literally just a picture. Am I misunderstanding something??
@StellarFlower You then need to drag it onto your Comfyui interface, so that the workflow and the names of the missing nodes are displayed.
after installing missing custom nodes and running i get error
RuntimeError: Cannot use bleh_preset_0 - present not defined. Ensure BlehSetSamplerPreset runs before sampling.
fixed in newest version. a link was missing.
@DonutsDelivery Ah, great! I can't wait to test the new version then, because I managed to get 1.1 working last night, but by working around the bleh node and modifying the samplers. Thanks for the update!
yes workflow does not work
fixed in newest version. a link was missing.
Good workflow. Bit complicated, I had to re-organize it and replace a couple of missing nodes, download bbox models, but it works well. Thanks.
Version 1.2 works perfectly. Now I just need to get to grips with it and understand it better. Thank you.
Have fun! If the image it first generated isn't as good as the preview it is because I improved the prompt. The settings are the same.
There is no WF for 1.2?
I'll have to re-upload it when I get home in a few hours, sorry for the inconvenience.
Good framework for SDX/Z-Image work flow. Number of things hidden behind nodes that aren't needed like the BlehSetSamplerPreset. The third facedetailer for the nsfw fix doesn't work due to the default 'clip' input from the anywhere node which needs to be hard wired to the SDXL checkpoint. I would suggest for anyone to scrub through the logic and modify to your likening. Still a good starting point for a Z-Image/SDXL refinement workflow at least until the support ramps up for Z-Image.
Ive uploaded a new file with the sdxl clip hard Wired. Sorry for the inconvenience
Hello, since you seem so well-informed, why not collaborate with the creator of the process to publish the final version? This isn't a criticism, I should clarify, but a suggestion, as I'm eager to fully utilize Z's capabilities. Sincerely.
@DonutsDelivery Hi there I just tried to download this workflow again but i still have the same issue with the third facedetailer. Do I need to wait for the new download link to become available?
@madmannebruz813 strange, ill double check
@madmannebruz813 it should be fixed now. added download links for the models in a note above it.
@DrakulValmont666 I was actually thinking the same. I'll reach out...
@DonutsDelivery all working thanks man.
How can I generate a man’s penis”
use a penis lora and replace pussy detection model with a penis detection model.
@DonutsDelivery Where should I download penis lora? Its format is .pt. I'm a novice and it's very complicated.
@DonutsDelivery It has been solved. Your workflow is so easy to use. I love you. It would be better if there was an anal test.
Lacks everything, too complex to use, unsuitable for newbies
Newbies gen with chatgpt
@DonutsDelivery no newbie here, but your tiled upscale node doesn't seem to update. any ideas? I was thinking maybe a pip update or something. not sure tbh
@MysticMindAi strangely enough my comfy registry says the latest version is 1.0.35, but my manager says the latest is 1.0.29... altho im using nightly (since i make the node). a few options: make sure comfy is up to date. change to nightly if you can. if that dosent work, clone the repo directly into your custom nodes the old way. https://github.com/DonutsDelivery/ComfyUI-DonutNodes/tree/main
@DonutsDelivery Updating Comfy worked! Much thanks!