You can find out more about realism settings and workflows here: https://civarchive.com/articles/32409/realism-how-to-achieve-it-a-generation-guide-workflow-examples-included
I decided to start from scratch and took two days to build a workflow to block merge, then merge, then inject💉, then finetune.
and then failed...
V3.1
Welp.... after exhaustive testing, I think I've delivered a hell of a model. Read all about the journey and the testing Here: https://civarchive.com/articles/35724/model-same-face-syndrome-how-to-fix-it-without-retraining-test-sheets-included
V1.0
Trained on somethin like 3200 images for two weeks straight.
semantic tuned to get that SDXL look
All images I uploaded are Euler/ simple, 10-12 steps, no LoRAs, using my Pro workflow here: https://civarchive.com/models/2726952/krea-2-pro-grade-w-image-edit-style-transfer-moodboard-controlnet-multi-reference-sam3-detailers-and-low-vram-options
Instagram: https://www.instagram.com/synth.studio.models/
Buy me a☕ https://ko-fi.com/lonecatone
This represents many hours of work that I give away for free. If you enjoy it, Please make sure to 👍like and post to my models & workflows. That is how you support me!! Also, feel free to ⚡tip 😉
Description
V3.1
Fixed face lock
I tired merges, images, messing with block swaps, epochs, etc. I finmally used a mix of all of them.
slightly more responsive to NSFW (not my goal. There are LoRAs for that)
better prompt adherence.
Better asthetics (I think)
Let's hope thie version measures up