Description
Embedding trained for 2000 steps on ‘v1-5-pruned-emaonly’ checkpoint, so it should works well with most of v1.5 forks and mixes. I used dataset of 60 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”.
Preview images were rendered on Checkpoint: pirsusEpicRealism_v25 (hash: 36148395c9)
If you are going to remake preview images you should have:
Checkpoint: pirsusEpicRealism_v25
LoRA: LowRA, RSERomantic_RSESofiko_RSEEmma-v1, tangbohu-detailer_1.0, xiaoshazi, jah (by sd_storm), ww1ger_v0.1
Embeddings: badhandv4, kkw-Extreme-Neg, ng_deepnegative_v1_75t, kkw-ph1, BadDream, FastNegativeV2, UnrealisticDream, kkw-old, AS-Young-neg, AIDA_LG2022
Download link to AIDA_LG2022 embedding will be available for you after purchase. For your comfort I packed AIDA_LG2022.pt into .zip archive with AIDA_LG2022.preview.png and AIDA_LG2022.txt . Preview and description are compatible with AUTOMATIC1111 and Forge extra networks tabs.
Also you will get .zip archive with all preview images and generation data for them.
Please pay at least 1$ If you want to achieve rights for selling images generated with AIDA_LG2022 embedding. Also this way you can say me special thanks for this embedding.
Please contact me if you need some extended rights for sharing or selling AIDA_LG2022, merging AIDA_LG2022 with other embedding, using AIDA_LG2022 in generation services and so on.
Reviews
There are no reviews yet.