Now with “only masked” and a smaller target like eyes you get a little more freedom so your denoise can be 0.54-0.57 With “whole picture” selected for larger inpaint target aka faces (or hands) you may need the denoise to be lower to pick up more of the original image. Masked content = fill / inpaint area = only masked = for eyes Masked content = fill / inpaint area = whole picture = for faces This will get you a pretty good base image to work with.Īfterwards… You can always send your txt2img picture to inpaint on the bottom right under the result area > select the face or eyes > lower the denoise strength to 0.5-0.57. Latent (nearest or exact) upscale / denoise 0.4-0.7 ( Complete variable - depends on the type and complexity of the image. But a few are.įirst off when you run txt2img ALWAYS use HIRES FIX! I was asked recently how to get higher quality images like the examples and about blurred eyes and faces:īlurred eyes, or sometimes warped faces are not that uncommon in SD and sometimes require an inpaint to pull off. □ PLEASE NOTE: All of the originals have their own attributions so these must be followed to use this. There are pruned & non pruned versions available if you use the pulldown. *** THESE SHOULD BE EASILY REPRODUCIBLE RESULTS! IF YOU HAVE QUESTIONS PLEASE ASK □ In most cases untouched other than mild inpainting for the eyes or face in a few examples. *** Note: that the example images are provided as a basis of reference and raw output. There is no embedded VAE in this (other than ones included in the merges) but one of these should work fine: (click the links) If you want darker more detailed environments and detailed shading choose 2.0 or 2.2 but realize that 2.0 & 2.2 are a little more demanding from the prompt maker in order to get the exact result you want. I still use 1.6 for some things from time to time. If you find yourself asking “which is the right version?” If you’re new to SD and want an easy ride choose version 1.0 or 1.6 both are consistent and work quite well. (I tried to illustrate this in the example images if you flip between versions.) Yes, they both produce good results but the result you get will be different. Keep in mind this merged model has been evolving… So the 1.6 version is not very similar to the 2.2 version or visa-versa. Works best from 7-13.5 CFG and up 20-70 STEPS imho. Specializes in painterly, semi realistic to realistic illustration, and artists based prompts, but can do design work, vector illustrations, logos, and a bit of anime as well. I’ve yet to find what this can’t handle❗□ Should serve as a bit of a swiss army knife / multi-tool to create any and all fantasy art, character concepts, portraits, designs, locations, & even a bit of n00ds. GO TRY DREAMSCAPES & DRAGONFIRE! IT'S BETTER THAN DNW & WAS DESIGNED TO BE DNW3.0!□Ī handpicked and curated merge of the best of the best in fantasy world, character & creature design.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |