AI Image Prompt Generator
Pick fragments from the library. The output panel builds Positive / Negative / Parameters and marks possible conflicts while still allowing copy.
pose
Core body poses such as standing, walking, sitting, kneeling, looking back, and dynamic stance.
This set includes: body-position prompts that control how the character is placed in the image.
A relaxed full-body standing pose with a balanced silhouette.
Natural forward movement with readable arms and stride.
An upright seated posture with calm hand placement.
One-knee kneeling pose with a stable body balance.
A three-quarter body twist with an elegant over-shoulder look.
A stronger action-ready stance with one foot forward.
Model notes for choosing checkpoints before copying the prompt into ComfyUI.
checkpointmain anime sample library / pose cards / outfit examples / clean character prompts
Use Danbooru-style short tags plus plain English structure. Good first choice for standing/walking/sitting pose cards.
checkpoint2.5D anime look / lighting comparison / stylized portraits / model comparison cards
Works well with anime character tags, lighting words, and camera framing. Keep realism tags moderate.
checkpointrealistic portrait comparison / camera tests / lighting tests / semi-photo examples
Use natural language prompts, explicit camera/lens/lighting, and fewer anime tags.
checkpointJapanese realistic style / soft portrait samples / realistic clothing materials / model comparison cards
Use natural language with Japanese street/interior styling notes. Avoid piling anime-only tags.
checkpointoptional XL quality tests / high detail anime examples / later premium sample cards
Use XL-friendly prompts with clear subject, pose, style, and quality. Avoid using it for every first-pass sample.
checkpointimage editing / variation cleanup / turning approved samples into refined variants
Treat as an edit/refine tool rather than the main prompt library generator.lorapose control / whole-body reference guidance / standing/walking/sitting consistency
Use alongside OpenPose / pose reference workflows when you want the exact body pose to stay stable.Add fragments from the library, then review the generated prompt. A strong prompt usually follows this order: subject, pose or action, clothing, scene, camera angle, lighting, mood, style direction, and quality tags.
The cart is saved in localStorage, so your fragments remain available after refreshing the page. Conflict checks are suggestions, not rules.