Conclusion
- No step-by-step difference by adjective strength was observed — All conditions of big/huge/massive/enormous/oversized landed at the same level (★★★☆☆)
- No systematic difference by noun choice (butt/ass/booty) either — Results were equivalent regardless of which noun was used
- Unlike breast size experiments, single-word adjectives alone don’t produce a dramatic size increase — Butt responds more weakly to adjectives than breasts
massive assandhuge assare the most stable — Effects confirmed in 3/3 for both
We compared 10 combinations of size adjectives (big / huge / massive / enormous / oversized) and nouns (butt / ass / booty) to test which makes a larger butt in AI image generation.
This article is Part 1 of the Butt Size Testing Summary.
- Part 1: Step-by-Step Size Adjective Comparison (this article)
- Part 2: Effect of Body Type Modifiers
- Part 3: Stacking + Shape Expressions
Experiment Conditions
| Item | Value |
|---|---|
| Model | z-image-turbo (6B, photorealism-focused distilled model) |
| Steps | 8 |
| Sampler | euler |
| Scheduler | ddim_uniform |
| CFG | 1.0 |
| Image size | 1024×1024 |
| Seed | 3 seeds used across all conditions |
| Angle | Front and back views generated per condition |
Base Prompt
Only the {VARIABLE} part was swapped. A low-coverage thong bikini was used to make size differences easy to see. Both back view and front view were generated for all conditions.
Control (no adjective)
back view
 |  |  |
front view
 |  |  |
Baseline. All 3 seeds are slim to average build with modest buttock volume. ★★☆☆☆.
butt Series
big butt — ★★★☆☆ (slight increase, effect in 2/3)
| back | back | back |
|---|---|---|
 |  |  |
| 
| 
|huge butt — ★★★☆☆ (slight increase, effect in 2/3)
| back | back | back |
|---|---|---|
 |  |  |
| 
| 
|massive butt — ★★★☆☆ (slight increase, effect in 3/3)
| back | back | back |
|---|---|---|
 |  |  |
| 
| 
|enormous butt — ★★★☆☆ (slight increase, effect in 2/3)
| back | back | back |
|---|---|---|
 |  |  |
| 
| 
|oversized butt — ★★★☆☆ (slight increase, effect in 1/3. Hair style change as side effect in s3)
| back | back | back |
|---|---|---|
 |  |  |
| 
| 
|ass Series
big ass — ★★★☆☆ (slight increase, effect in 2/3)
| back | back | back |
|---|---|---|
 |  |  |
| 
| 
|huge ass — ★★★☆☆ (slight increase, effect in 3/3)
| back | back | back |
|---|---|---|
 |  |  |
| 
| 
|massive ass — ★★★☆☆ (slight increase, effect in 3/3. Most stable single word)
| back | back | back |
|---|---|---|
 |  |  |
| 
| 
|booty Series
big booty — ★★★☆☆ (slight increase, effect in 1/3)
| back | back | back |
|---|---|---|
 |  |  |
| 
| 
|huge booty — ★★★☆☆ (slight increase, effect in 1/3. Body slimming side effect in s3)
| back | back | back |
|---|---|---|
 |  |  |
| 
| 
|Size Adjective Summary
All conditions stayed at ★★★☆☆, with no step-by-step difference by adjective strength (big < huge < massive < enormous < oversized). Unlike breast size experiments, single-word adjectives alone don’t produce a dramatic size increase.
No systematic difference by noun choice (butt / ass / booty) was observed. For stability, massive ass (3/3 effect) and huge ass (3/3 effect) are the most reliable.
![[Verified] Image Generation Prompt Best Practices](/tips/prompt-best-practices/cover_0_0000_4517457392071889496.webp)
