Description
Embedding trained for 1000 steps on ‘v1-5-pruned-emaonly’ checkpoint, so it should works well with most of v1.5 forks and mixes. I used dataset of 36 images with 680×680 resolution, and learning rate: “0.05:10, 0.02:20, 0.01:60, 0.005:200, 0.002:500, 0.001”. Personal likeness was reached at 150 steps.
Preview images were rendered on checkpoint: pirsusEpicRealism_v12 (hash: 00d4f7a3be)
If you are going to remake preview images you should have:
checkpoint: pirsusEpicRealism_v12
lora: LowRA, RSERomantic_RSESofiko_RSEEmma-v1, tangbohu-detailer_1.0, xiaoshazi.
embeddings: badhandv4, kkw-Extreme-Neg, ng_deepnegative_v1_75t, kkw-ph1, AIDA_hannah
Download link to AIDA_hannah embedding will be available for you after purchase. For your comfort I packed AIDA_hannah.pt into .zip archive with AIDA_hannah.preview.png and AIDA_hannah.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_hannah 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_hannah, merging AIDA_hannah with other embedding, using AIDA_hannah in generation services and so on.
Reviews
There are no reviews yet.