We had an outage July 5th where users were not compensated, a fix has gone out.

July 5th Compensation

Krea 2 LoRA training is 50% off, and we're running a Krea 2 Training Contest with 1.8 million Buzz in prizes across four LoRA categories.

⚡ Krea 2 Training Contest + 50% Off Training

This is a simple workflow with refiner for the <a target="_blank" rel="ugc" href="https://civitai.com/models/1513492?modelVersionId=1943922">GonzaLomo</a> and <a target="_blank" rel="ugc" href="https://civitai.com/models/1854124?modelVersionId=2159501">MoP</a> SDXL models.

I finally got around to creating a new image workflow to share. I've tried to hide a lot of the complexity in a subgraph and only expose the necessary parameters.The workflow creates three images: the base generation, the upscaled and refined generation and an optional face enhancer using my <a target="_blank" rel="ugc" href="https://civitai.red/models/2192562/gonzalomo-zpop">GonzaLomo ZPop v4.0</a> model. I think it does result in a better image because SDXL faces are not perfect. The face detailer requires some special detection models which you can get <a target="_blank" rel="ugc" href="https://civitai.red/models/2172100/gonzalomo-z-image-refiner-workflow?modelVersionId=2543959">here</a>.The workflow also has a simple IPAdapter integration. So it can take a reference image and incorporate that into the image generation.

v4.0

The only real difference between this version and v3.0 is the addition of the Self-Attention Guidance node on the base image generation. This is especially useful with the MoP (Mixture of Perverts) v2.0 model.

v3.1

This workflow is similar to my other SDXL workflows, except that it incorporates IPAdapter to allow you to style the generation with an image. That image could be a face that you want the generation to be based on or it could be an artistic image with a style that you want the generation to replicate.This is a fun tool that has a lot of uses!

IPAdapter

I've cleaned this up a bit, added some helpful notes and an eye detailer. For best results, use this workflow with any photorealistic SDXL checkpoint. The showcase images were created with my own GonzaLomo v5.0 FluXL checkpoint. Note: If the checkpoint you choose is not a DMD2 checkpoint then you'll either need to use the DMD2 LoRA or change the sampler settings to match what the checkpoint works best with.

v3.0

This is very similar to my v3.0 SDXL Workflow except that it doesn't generate a new image from scratch. This workflow will take an existing image that you copy/load in and upscale and refine it. I use this frequently to improve old images I had forgotten about and never published.Most of the images in this workflow's gallery are old Flux images that were dated and lacked detail. I used this workflow to spruce them up and add the additional detail that only SDXL can provide.For photorealistic results, I would suggest using either <a target="_blank" rel="ugc" href="https://civitai.com/models/1854124?modelVersionId=2117960">MoP (Mixture of Perverts)</a> or <a target="_blank" rel="ugc" href="https://civitai.com/models/1513492?modelVersionId=1943922">GonzaLomo v4.0</a>. Either will do a very good job of adding detail. The only setting you may want to tinker with is the sampler denoise. A higher denoise will add more detail but might also change the image more than you'd like. I find between 0.15 and 0.30 is ideal.

v3.0 Standalone Refiner

This is very similar to my BigASP2.5 refiner but it is meant for my <a target="_blank" rel="ugc" href="https://civitai.com/models/1513492?modelVersionId=2032014">LittleASP</a> model, containing the settings that seem to work best. As usual, it does the refining with the <a target="_blank" rel="ugc" href="https://civitai.com/models/1513492?modelVersionId=1943922">GonzaLomo v4.0 Unity</a> model.

v3.0 LittleASP Refiner

This workflow is tailored to generate images using <a target="_blank" rel="ugc" href="https://civitai.com/models/1789765/bigasp-v25">BigASP v2.5</a> and refine them using my GonzaLomo v4.0 model, although any SDXL could be used for that purpose. The settings and explanations for them are in the workflow. Note that BigASP 2.5 is unlike other SDXL models so it requires a couple of extra nodes to work properly.

v3.0 BigASP2.5 Refiner

Updated this similar to my Flux refiner. I also noticed that earlier version of this workflow produced images that Civit couldn't parse the positive prompt from. This version seems to be Civit-friendly in that regard.

v2.0

This workflow works with my v4.0 Unity XL Non-DMD model, basically refining the initial generation with higher detail using my DMD model.

v1.0 Non-DMD

Added the ability to change the clip skip.

v1.1

v1.0

GonzaLomo SDXL Workflows

1-256.png

physical violence

weapon violence

wide hips

revealing clothes

downblouse

convenient censoring

pg-13

corpses

suggestive

oral invitation

pg13

sexy

huge breasts

thick thighs

sexual situations

male nudity

disturbing

male swimwear or underwear

female swimwear or underwear

partial nudity

undressed

female nudity

breasts out

exposed female nipple

breast out

lingerie

male underwear

hair over breasts

female swimwear

gigantic breasts

no panties

graphic violence or gore

covered nipples

huge butt

strapless leotard

sitting on face

emaciated bodies

one breast out

female underwear

nude

nsfw

graphic male nudity

adult toys

illustrated explicit nudity

nudity

graphic female nudity

hentai

futanari

porn

sexual intent

genitals

peeing

vore

oral

sexual activity

anal

blowjob

dildo riding

incest

hanging

hate symbols

nazi party

white supremacy

diapers

scat

self injury

hate speech

urine

extremist

child on child

latex clothing

swimwear

bukkake

fellatio

cumshot

implied fellatio

eat_cum

cumdrip

cum in pussy

cum on face

after fellatio

cum on hair

cum on body

cum on tongue

cum on hands

cum in mouth

triple fellatio

autofellatio

fucked silly

cum on pussy

Creators (SDXL)