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:Reclined-step01260:1>. It still works with lying on ... back, and then leaning on the elbow, or a backrest, cushion, driftwood .. whatever. Lying flat on back is another LoRA with a complete different dataset.
Flux is notoriously bad at creating anything which is lying down. The only pose I got was lying on the stomach and then the feet are wrong. I tried first to do a all-in-one solution, but after a lot of testing I had to hammer each pose into a separate LoRA. For example because you cannot really differentiate between lying flat on the back and a recumbent or reclined position - if you mention something with sitting, you'll get sitting, and the reclined images will taint the flat on the back ones.
I also noticed that you have to use a <lora:Reclined-80:1> tag, otherwise it is more or less chance if it will influence your image. The trained sentence is "in a reclined position" and "She is lying on her back, her upper body elevated by leaning on ..." - the leaning can happen on the elbows or something else like backrests, cushions ... The distinction between the next one is that the arms are not straight, that elevates the upper body more and you have a sitting position, that is the Leaning back LoRA. This LoRA has a lot less steps, because it seems to be a bit more trained naturally that way. I haven't extensively tested the reclined part of the caption, it seems to work more reliable with "lying".
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!
Version 2.0 is trained with fp8, getting rid of the grid pattern sometimes visible in the images.
1. Dieses Modell dient nur Lernzwecken. Urheber- und Auslegungsrechte liegen beim Originalautor.
2. Bist du der Originalautor eines Modells, kontaktiere uns bitte zur Authentifizierung über unsere offiziellen Kanäle. Wir schützen die Rechte aller Schöpfer. Hier klicken, um es zu verifizieren.
