Description
Embedding trained for ~1200 steps on ‘v1-5-pruned-emaonly’ checkpoint, so it should works well with most of v1.5 forks and mixes. I used dataset of 48 images with 680×680 resolution, and learning rate: “0.0125:10, 0.0025:60, 0.0005:360, 0.0001”. Personal likeness was reached at 350 steps.
Preview images were rendered on checkpoint: pirsusEpicRealism_v12 (hash: 00d4f7a3be)
If you are going to remake all preview images you should have:
checkpoint: pirsusEpicRealism_v12
LoRas:
- LowRA
- jah (by sd_storm)
- RSERomantic_RSESofiko_RSEEmma-v1
- ww1ger_v0.1
- tangbohu-detailer_1.0
- xiaoshazi
Embeddings:
- BadDream
- FastNegativeV2
- UnrealisticDream
- badhandv4
- kkw-Extreme-Neg
- ng_deepnegative_v1_75t
- kkw-ph1
- AIDA_valenss
- AS-Young-neg
- kkw-old
Download link to AIDA_valenss embedding will be available for you after purchase. For your comfort I packed AIDA_valenss.pt into .zip archive with AIDA_valenss.preview.png and AIDA_valenss.txt , preview and description are compatible with AUTOMATIC1111 extra networks menu.
Also you will get .zip archive with all preview images and generation data for them.
Purchasing this asset you will achieve rights for selling images generated with AIDA_valenss embedding. If you want say special thanks to me, you can add additional amount to your payment.
Please contact me if you need some extended rights for sharing or selling AIDA_valenss, merging AIDA_valenss with other embedding, using AIDA_valenss in generation services and so on.
Reviews
There are no reviews yet.