Type | |
Stats | 225 15 |
Reviews | (31) |
Published | Dec 30, 2024 |
Base Model | |
Training | Steps: 1,860 Epochs: 30 |
Trigger Words | standing leaning back against |
Hash | AutoV2 19EDBD8B79 |
Version 2.0 update:
after I connected the grid pattern sometimes visible in bright or dark parts of the images with the fp4 training with OneTrainer, I switched to fp8 training, which got rid of the pattern. But I have to redo all my LoRAs to fix them all. Nothing changed, except the tag is now <lora:LeaningBackStanding-step01860:1>.
This is the last one from the poses series - leaning back, but standing. Also a classic in portrait photography. There is not much variation in the dataset, most are three-quarter angle or side angle shots - for front angle shots, you can't really see the leaning part. It is also a mix from full-body to half-body portraits. And in most cases, one leg ist lifted up. The prompting is simple: "standing" and then "leaning back against ...". For consistency, use the LoRA-tag <lora:LeaningBackStanding-60:1>.
The captioning scheme for face, body and camera angles is the same as in my other pose LoRAs, but as mentioned above, only a few matter for this one:
Face angles:
Full face view | Three-quarter face view | Two-third face view | Profile face view
Body angles:
Front angle shot | Three-quarter angle shot | Side angle shot | Three-quarter rear angle shot
Camera angle:
High camera angle | Eye level shot | Low camera angle | Shoulder level shot | Cowboy shot | Ground level shot
Image area:
Full-body portrait | Three-quarter-body portrait | Half-body portrait | Quarter-body portrait