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:LeaningBackAgainst-step0800:1>.
The next pose of the portrait photographers 101 is sitting on the ground and leaning back against ... something. I don't know how they trained Flux, but you can't get that with prompting - the model will always sit in front of the background, not actually touch it. The prompt is simple "leaning back against ..." and I trained it to the strength that is works with a <lora:LeaningBackAgainst-50:1> tag.
Something I started here but had to be placed too in separate LoRAs to work is a finer control over face angles, body angles, camera angles and image area. But starting with this one, the captions are consistent as a preparation, even if they do not (yet) work standalone. The scheme is:
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
It would be great if I get this to work!
描述:
训练词语: leaning back against,sitting
名称: LeaningBackAgainst-50.safetensors
大小 (KB): 25641
类型: Model
Pickle 扫描结果: Success
Pickle 扫描信息: No Pickle imports
病毒扫描结果: Success
