My rating vs expectation: 95%
(See"about this version" for changes. See TIPS to get best result. Very happy with the likeness. This is the final version for Anna Ralphs.)
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, 100 images, 50200 steps, and 502 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: futuraanna50200v52, portrait of a woman, long dress etc.
Not: Portrait of futuraanna50200v52, etc.
Recommended strength:
(0.98-1.0)
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.
Description
FAQ
Comments (2)
Hi! Hello, I'm currently learning to train embeddings, but I always encounter various issues when attempting to train using models other than the v1.5-pruned. I'd like to inquire about how the fine-tuning based on Epic model is achieved, as mentioned in your introduction. This problem has been bothering me for a long time, if you can answer it, I would be very grateful.
Love how your characters are looking so real,
May I ask if you can do Ellie Kemper https://instagram.com/elliekemper?igshid=MzRlODBiNWFlZA==
Thank you very much