Type | |
Stats | 581 |
Reviews | (38) |
Published | Jul 24, 2023 |
Base Model | |
Training | Steps: 20,600 Epochs: 332 |
Trigger Words | futuraalex20600v52 |
Hash | AutoV2 7B00200E75 |
My rating vs expectation: 85%
(Read "about this version" for changes. The separation of the eyes bothers me. Will retrain in near future.)
All TIs I make depict real adults. Please apply it with good judgement. If you're the model and want this removed reach out to me via link below. I welcome all criticisms and suggestions with curiosity. If you like my work, buy me a house:
https://ko-fi.com/futurafree
This TI was trained in sd1.5 base with 5 vectors, 62 images, 20600 steps, and 332 epochs. This was finetuned for epiCRealism evo3 and Realistic Vision V4.0, but may work on others.
TIPS:
MUST be the first word in the prompt for likeness and consistency.
Example: futuraalex20600v52, portrait of a woman, long dress etc.
Not: Portrait of futuraalex20600v52, etc.
Recommended strength:
(0.98-1.0)
May produce red and purple artifacts with DPM++ 2M Karras at LOW sampling steps.
Fix: raise sampling steps above 25 always.
I use adetailer for all images, with mediapipe_face_full, blank pos and neg, 1024x1024, inpaint mask blur: 20, inpaint noise strength: 0.45.
Again, prompt in adetailer is left blank most of the time; (*exception*: if Loras/Lycoris is used and has significant impact on the appearance of the model's face, copy paste pos prompt without Loras/Lycoris into adetailer).
Upscaler I use: 4x_NMKD-Siax_200k.