Lingerie All-Fours Rear View: Comparing Pose, Outfit & Angle Prompts

Lingerie All-Fours Rear View: Comparing Pose, Outfit & Angle Prompts

Key Findings

  • crawling on bed is the most stable pose description — reproduced the all-fours + butt-out composition in 2 out of 3 seeds
  • ass up risks generating two people (occurred in 1/3)
  • from behind and rear view are equivalent for angle. Adding low angle increases impact
  • slightly above induces a prone position — avoid it for butt-focused compositions
  • Lingerie type affects pose stability — details in Experiment 3

What You’ll Learn

  • The most stable pose description for rear all-fours compositions
  • Output differences between angle keywords (from behind / rear view / low angle / slightly above)
  • How lingerie type affects outfit reproduction and pose stability

Test Conditions

ParameterValue
Modelz-image-turbo (6B, photorealistic distilled model)
Steps8
Samplereuler
Schedulerddim_uniform
CFG1.0
Image Size1024×1024
Seeds42, 123, 789 (fixed)

Experiment 1: Pose Description Comparison

Base Prompt
1girl, 32yo japanese actress, {POSE}, from behind, lace lingerie set, on bed, indoor, soft warm lighting

Condition A: on all fours (3 tokens)

Condition A
1girl, 32yo japanese actress, on all fours, from behind, lace lingerie set, on bed, indoor, soft warm lighting

All fours looking back Prone rear view Side-prone rear

Observations

Only 1 out of 3 (seed 42) produced the all-fours + looking back composition. The other 2 resulted in near-prone positions. on all fours alone is unreliable when combined with rear angles.

Condition B: on all fours, arched back (5 tokens)

Condition B
1girl, 32yo japanese actress, on all fours, arched back, from behind, lace lingerie set, on bed, indoor, soft warm lighting

All fours looking back with arched back Kneeling rear with navy lace Prone with butt out

Observations

Adding arched back improves the butt-out feel. However, actual all-fours stability is similar to Condition A (1/3). The back arch was visible in all 3 outputs.

Condition C: on all fours, ass up (5 tokens)

Condition C
1girl, 32yo japanese actress, on all fours, ass up, from behind, lace lingerie set, on bed, indoor, soft warm lighting

Two people generated Kneeling rear with black lace Kneeling rear with white lace

Observations

Seed 42 generated two people despite the 1girl specification. ass up appears to destabilize composition interpretation. The remaining 2 produced kneeling rear views — butts are emphasized but not in all-fours position.

Condition D: on hands and knees, presenting (5 tokens)

Condition D
1girl, 32yo japanese actress, on hands and knees, presenting, from behind, lace lingerie set, on bed, indoor, soft warm lighting

Kneeling side with bodysuit Kneeling rear with bodysuit Kneeling looking back with white lace

Observations

All 3 produced kneeling poses instead of all-fours. presenting also caused lace lingerie set to be interpreted as a bodysuit in 2/3 seeds. Be aware this keyword influences outfit interpretation.

Condition E: crawling on bed (3 tokens)

Condition E
1girl, 32yo japanese actress, crawling on bed, from behind, lace lingerie set, indoor, soft warm lighting

Crawling with looking back in white lace Crawling looking back in navy bodysuit Prone with white lace

Observations

2 out of 3 produced natural crawling + looking back compositions. crawling on bed has the best compatibility with rear butt-out framing, and the pose feels natural. Token efficiency is also excellent at 3 tokens.

Lab Director: Crawling wins again. Telling the model to “crawl” works better than saying “get on all fours” — the action-based description produces more natural poses. Plus it adds a looking-back motion for free. Love it.

Pose Comparison Table

Seedon all fours (A)arched back (B)ass up (C)presenting (D)crawling (E)
42ABCDE
123ABCDE
789ABCDE

Experiment 2: Angle Description Comparison

Base Prompt
1girl, 32yo japanese actress, on all fours, arched back, {ANGLE}, lace lingerie set, on bed, indoor, soft warm lighting

Condition A: from behind (2 tokens)

Condition A
1girl, 32yo japanese actress, on all fours, arched back, from behind, lace lingerie set, on bed, indoor, soft warm lighting

Crawling looking back in white lace Kneeling rear in navy lace Prone in white lace

Observations

Standard rear angle. Pose variety is wide — mix of all-fours, kneeling, and prone positions.

Condition B: rear view (2 tokens)

Condition B
1girl, 32yo japanese actress, on all fours, arched back, rear view, lace lingerie set, on bed, indoor, soft warm lighting

Crawling looking back in white lace Kneeling rear in navy camisole Prone in white lace

Observations

Nearly identical output to from behind. Same token count (2 tokens). No practical difference observed.

Condition C: from behind, low angle (4 tokens)

Condition C
1girl, 32yo japanese actress, on all fours, arched back, from behind, low angle, lace lingerie set, on bed, indoor, soft warm lighting

Crawling looking back with bodysuit Kneeling rear with wider legs Prone rear in navy lace

Observations

low angle increases butt impact. Seed 123 showed wider leg spread, creating a more dynamic composition. However, outfit was interpreted as bodysuit in 1/3 cases.

Condition D: from behind, slightly above (4 tokens)

Condition D
1girl, 32yo japanese actress, on all fours, arched back, from behind, slightly above, lace lingerie set, on bed, indoor, soft warm lighting

Prone in white lace Prone in navy lace Prone from above in navy lace

Observations

slightly above produced prone positions in all 3 seeds. The overhead angle destabilizes the all-fours pose. Avoid this for butt-out compositions.

Angle Comparison Table

Seedfrom behind (A)rear view (B)low angle (C)slightly above (D)
42ABCD
123ABCD
789ABCD

Experiment 3: Lingerie Type Comparison

Base Prompt
1girl, 32yo japanese actress, on all fours, arched back, from behind, {LINGERIE}, on bed, indoor, soft warm lighting

Condition A: lace lingerie set (3 tokens)

Condition A
1girl, 32yo japanese actress, on all fours, arched back, from behind, lace lingerie set, on bed, indoor, soft warm lighting

Lace lingerie set Lace lingerie set Lace lingerie set

Observations

Bra + panties set output consistently. Lace detail reproduction is high. Color varies by seed (navy or white).

Condition B: sheer babydoll nightgown (3 tokens)

Condition B
1girl, 32yo japanese actress, on all fours, arched back, from behind, sheer babydoll nightgown, on bed, indoor, soft warm lighting

Sheer babydoll Sheer babydoll Sheer babydoll

Observations

Translucent babydoll is well reproduced. The butt view differs significantly from bra + panties sets — the gown hem drapes over the butt area.

Condition C: black thong and matching bralette (5 tokens)

Condition C
1girl, 32yo japanese actress, on all fours, arched back, from behind, black thong and matching bralette, on bed, indoor, soft warm lighting

Black thong and bralette Black thong and bralette Black thong and bralette

Observations

The thong specification maximizes butt exposure compared to other conditions. Excellent compatibility with rear compositions — butt lines are clearly defined.

Condition D: white lace bodysuit (3 tokens)

Condition D
1girl, 32yo japanese actress, on all fours, arched back, from behind, white lace bodysuit, on bed, indoor, soft warm lighting

White lace bodysuit White lace bodysuit White lace bodysuit

Observations

One-piece bodysuit output is consistent. The silhouette is elegant because it covers the entire butt. Lace transparency provides a good balance of skin visibility.

Condition E: garter belt and stockings with lingerie (6 tokens)

Condition E
1girl, 32yo japanese actress, on all fours, arched back, from behind, garter belt and stockings with lingerie, on bed, indoor, soft warm lighting

Garter belt and stockings with lingerie Garter belt and stockings with lingerie Garter belt and stockings with lingerie

Observations

Adding garter belt and stockings increases visual complexity. The garter line at the thigh-butt boundary creates a natural eye-guiding effect. Token cost is high at 6 but the visual payoff is substantial.

Lab Director: That garter line cutting across the thigh-to-butt transition? It’s like a visual arrow pointing right where you want to look. Worth every token.

Lingerie Comparison Table

Seedlace set (A)babydoll (B)thong (C)bodysuit (D)garter (E)
42ABCDE
123ABCDE
789ABCDE

Summary

Pose Description

DescriptionTokensStabilityButt-Out RateNotes
on all fours3Low1/3Tends to become prone
on all fours, arched back5Low-Med1/3Back arch is visible
on all fours, ass up5Low2/3Risk of generating 2 people
on hands and knees, presenting5Low0/3Becomes kneeling; changes outfit
crawling on bed3Med-High2/3Best pick. Natural look-back included

Angle Description

DescriptionTokensEffect
from behind2Standard rear. Stable
rear view2Equivalent to from behind
from behind, low angle4More butt impact. Wider leg spread
from behind, slightly above4Induces prone. Not recommended

Lingerie Type

DescriptionTokensButt VisibilityCharacter
lace lingerie set3Through pantiesStable. Color varies by seed
sheer babydoll nightgown3Through gown hemTranslucent. More fabric coverage
black thong and matching bralette5MaximumBest for butt line emphasis
white lace bodysuit3One-piece silhouetteElegant. Good lace transparency
garter belt and stockings with lingerie6Garter line accentEye-guiding effect. Token-heavy
Recommended: Lingerie All-Fours Back Shot
1girl, 32yo japanese actress, crawling on bed, from behind, black thong and matching bralette, on bed, indoor, soft warm lighting
  • Pose: crawling on bed (most stable, natural look-back)
  • Angle: from behind (2 tokens is enough)
  • Outfit: Choose by goal (butt emphasis → black thong, elegance → lace bodysuit)

Lab Director: Crawling wins, from behind is enough, thong seals the deal. Simple but correct. Short prompts hit harder — proven once again.