ComfyUI Workflow
visit this guy hes doin some awesome images, models and workflows too :)
the images in the preview are all created with SDXL (just saying)
After playing a while with his workflow i did the usual things and added the stuff i have in my other workflows. (with his permission xd) but don't worry there are no fancy nodes in here^^
there are 2 more detailers (B & V) (you know why)
added sd3 support
you can choose either to use the standard model or the one with the included text encoder. the tripple clip loader can be bypassed.
added a lot of options to enable/bypass things
it should be obvious but i'll say it anyway: only one of the two groups should be activated, either sd15/sdxl or sd3
i usually don't build single image workflows but this was kind of fun to do... Well it's a rebuild not a build from scratch.
Description
added "custom resolution" (2 fields where you can enter the size for sd1.5)
sd15/sdxl/sd3 groups are merged into one group so you can use everything on all 3 model versions
image generation informations are saved into the image file (checkpoint, steps... except loras -.^)
added wildcard processor, prompt styler
changed the ksampler (inpire) allows to generate the seed on the gpu (a1111 style)
added 4 upscalers (each of them has a quite low upscale factor)
added LUTs (requested by Jadewind)
added some nodes to post production e.g. image style filter and a node to lower the strength of it by blending both the original image and the filtered image)
added a custom watermark for those who don't have a finished one. its text based (for images you can use the other one^^). choose your font and text, position it, add glow or a drop shadow or both.
added a new group to down scale the final image
2 groups to save the image, one regular (was node) and one that saves the generation data within the image file.
the skin/person detailer are not working with sd3 they produce crap on the bottom of the image. hand/hair/face/eye should work.