Motion — what separates it from a pose
Does an action tag change the pose, or make movement?
A pose tag sets the shape of the body; an action tag puts time into it — carried by cloth, hair, and how far the feet leave the ground.
Every cut below shares one seed, one base prompt and one sampler setting, and differs only by the tag marked in amber.
What each cut shows
walking- One foot forward and the weight shifts. The quietest of the four.
running- The torso pitches forward and the back foot leaves the ground — the clearest of the four.
jumping- The arms open wide, but the toes sit right above the shadow, so there is almost no height — closer to tiptoe than a jump.
flying- Did not work — an ordinary standing figure. Getting airborne needs the setting and the viewpoint too: sky, clouds,
from below.
How these were made
Shared prompt
masterpiece, best quality, amazing quality, very awa, 1girl, solo, mature female, adult woman, short black hair, white blouse, blue jeans, full body, <tag slot>
Tap a tag to carry it over to the builder
Negative prompt
nsfw, nude, topless, bikini, swimsuit, lingerie, underwear, cleavage, suggestive, school uniform, pleated skirt, child, loli, teenage, bad quality, worst quality, worst detail, censor, jpeg artifacts, watermark, signature, text, extra limbs, bad hands, bad anatomy
Model
rinFlanimeIllustrious_v30 · euler_ancestral/normal · steps 28 · CFG 5 · 896×1152 · seed 777031
Takeaway
Actions that happen on the ground work from one tag; actions that leave it do not. Escaping gravity takes a change of setting as well.
How far this result reaches
Action tags need full-body framing. At portrait you cannot tell running from standing.
Measured on a single Stable Diffusion family checkpoint. The same tags can behave differently on NovelAI, Midjourney or another checkpoint. This is a reference point, not a verdict.