Type | |
Stats | 1,327 0 |
Reviews | (99) |
Published | Jul 21, 2023 |
Base Model | |
Training | Steps: 9,775 Epochs: 376 |
Trigger Words | futuramadison9775v5 |
Hash | AutoV2 780E2D3D5A |
My rating vs expectation: 93%
(High quality dataset. Likeness is good, but not perfect and there's room for improvement. Perhaps I could push the training to 500 epochs.)
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
Yes, another one of Madison. But I trained this TI with the goal of achieving a more natural look. Her photos in recent memories are typically makeup heavy and exaggerated. The dataset used for this contains many no-makeup photos from younger years (18, 19, 20) to aid with that.
This TI was trained in sd1.5 base with 5 vectors, 26 images, 9775 steps, and 376 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: futuramadison9775v5, portrait of a woman, long dress etc.
Not: Portrait of futuramadison9775v5, 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.