Futura hannahowo版本v2.0 (ID: 125284)

My rating vs expectation: 95%

(Low quality dataset but we nailed it I think. See "about this version" for changes. Check TIPS to get best result with this TI.)

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, 26 images, 14100 steps, and 542 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: futurahannahowo14100v52, portrait of a woman, long dress etc.

  • Not: Portrait of futurahannahowo14100v52, etc.

• Recommended strength:

  • (0.98-1.0)

• Optional:

  • Negative: (((nose rings)))

    • (Lack of nose ring may make her nose appear shorter)

• 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.

• Shurik had already created an excellent Lora of this model. I highly recommend that if you do not like textual inversions.

描述:

Same dataset as before but retrained with my new go-to training method. Results came out good. Likeness is far better than previous version (her jaw isn't as massive anymore). Flexibility is ok. Although her makeup and hairstyle are pretty much baked after 14k steps unless your prompt is long enough to dilute those features.

训练词语: futurahannahowo14100v52