Ganyu AI Image Prompts: 5 Distinct Poses and Results
Generate Ganyu in five deliberately different poses, settings, and camera systems. Includes exact English prompts, Japanese translations, a shared negative prompt, and result analysis.
This experiment designs five non-overlapping scenes for a social-ready Ganyu AI illustration series.
What this article covers
- 1A reusable identity prompt for Ganyu
- 2Five non-overlapping poses, settings, and camera systems
- 3English prompts with Japanese translations
- 4A shared negative prompt
- 5Actual outputs and social-thumbnail analysis
1What stayed fixed and what changed for Ganyu
Blue hair, red-black qilin horns, and the blue-white outfit remain fixed. Aerial jumping, curled sleeping, roof sliding, frontal standing, and one-hand hanging create five unrelated silhouettes from intense action to comedy.
- Keep recognizable hair, eyes, outfit, and signature ornaments fixed
- Give every concept a different body axis and large silhouette
- Change setting, time, and key-light direction on every run
- Separate low angle, aerial view, profile, symmetry, and lateral tracking
- Keep the face and action readable at social-media thumbnail size
Shared negative prompt for all five concepts
This shared avoid list targets duplicate subjects, anatomy failures, bad crops, unwanted text, and a return to repetitive compositions.
text, logo, watermark, signature, duplicate character, extra limbs, duplicate limbs, extra fingers, fused fingers, malformed hands, distorted anatomy, cropped face, hidden horns, muddy colors, low detail, photorealism, 3D render, sexualized pose3Five Ganyu image prompts and results
The prompt panel opens in English and can be switched to Japanese. On desktop it scrolls inside a rounded panel matched to the adjacent image height; on mobile it expands so normal page scrolling continues.
Result 1: dawn ice-arrow leap
Aerial thumbnail
Liyue aerial-leap prompt
Premium vertical anime key visual of Ganyu from Genshin Impact, faithful official blue hair, red-black qilin horns, blue-white outfit. She leaps between floating ice arrows above Liyue Harbor at dawn, extreme low angle, dynamic split pose, cyan frost and peach sky, crisp face. No text, watermark, duplicate, extra limbs, bad hands, sexualized pose.Result 2: moonlit glazed-lily sleep
Quiet intimacy
Moonlit sleeping prompt
Premium vertical anime illustration of Ganyu from Genshin Impact, faithful official design. She quietly sleeps seated beneath a giant glazed lily in a moonlit mountain meadow, close overhead camera, curled gentle pose, silver-blue mist, peaceful intimate mood, no combat effects. No text, watermark, duplicate, extra limbs, bad hands, sexualized pose.Result 3: blue-hour roof slide
Diagonal speed
Snow-roof slide prompt
Premium vertical anime action art of Ganyu from Genshin Impact, faithful official design. She slides sideways down a steep snow-covered tiled roof while firing a bow backward, lateral tracking view, blizzard at blue hour, long S-curve snow trail, focused expression. No text, watermark, duplicate, extra limbs, bad hands, sexualized pose.Result 4: circular noon rain
Graphic symmetry
Mirror-lake rain prompt
Premium vertical anime poster of Ganyu from Genshin Impact, faithful official design. Standing ankle-deep in a mirror-still lake at noon as a circular rain shower falls only around her, strict frontal symmetry, distant full-body composition, turquoise mountains and white clouds, serene authority. No text, watermark, duplicate, extra limbs, bad hands, sexualized pose.Result 5: bridge document rescue
Comedic fisheye
One-hand bridge prompt
Premium vertical anime key visual of Ganyu from Genshin Impact, faithful official design. She hangs one-handed from the underside of a stone bridge while reaching for a falling document with the other hand, comedic surprised expression, dramatic top-down fisheye toward a busy market far below, warm afternoon, wind-tossed ribbons. No text, watermark, duplicate, extra limbs, bad hands, sexualized pose.9The priority order that creates visible variety
Changing only a background noun is not enough when the subject remains upright in the center. Separate body axis and action first, then assign camera, time, light, palette, and emotion. This preserves character identity while making the series read as five independent ideas.
10Conclusion: design five differences before generation
Locking only Ganyu's identity while separating pose, setting, camera, time, and emotion produced five results that do not feel like near-duplicates. A diversity matrix is more reliable than generating a large random batch and deleting look-alikes afterward.
Frequently asked questions
QHow do I stop AI images of the same character from looking repetitive?
Assign a different body axis, action, camera height, time, and eye path before writing the scenery. Do not center an upright subject in every concept.
QWhy not run the same prompt five times?
Same-prompt batches measure consistency, but they do not guarantee scene diversity. This social series shares only the identity description and deliberately changes the scene design.
QWhich language appears first in the prompt panel?
English is the initial display. Every prompt can be switched to its Japanese translation.
