InkRoom
InkRoom
Public prompt插画与 3D

个人资料 / 头像 - Anime Girl Holding Dandelion

✓Original text is publicUpdated:
GPT 8.8/10
个人资料 / 头像 - Anime Girl Holding DandelionPrompt preview
Results depend on the model, inputs and generation settings.

Full prompt

Original author text

This public page preserves the author's original prompt. Review the preview and any published evaluation, then copy the text or open it as a draft. Choose the model, references and current cost in the creation workspace before generating.

Create a delicate single-character anime-style illustration on a clean white background. Show a young woman in a three-quarter back view, turned over her shoulder toward the viewer with a calm, slightly wistful expression. She has very long {argument name="hair color" default="black"} hair gathered into a high loose ponytail, with many fine stray strands and a large {argument name="hair ribbon color" default="navy blue"} bow tied near the top. Her face is soft and pale with subtle blush, narrow gray eyes, small lips, and refined linework. She wears a romantic vintage outfit: an off-white blouse with a ruffled high collar, ruffled cuffs, loose puffed sleeves, and a deep {argument name="skirt color" default="navy blue"} high-waisted skirt or corset waist with black lace-up ties visible at the back. Her right hand is raised delicately, holding exactly 1 dandelion puff on a thin green stem beside her face. Use an airy hand-drawn manga illustration style with clean sketchy black outlines, very light watercolor-like shading, muted colors, minimal background detail, graceful proportions, and lots of negative space. Keep the composition vertical, waist-up to upper-thigh framing, the hair flowing down the left side of the image, and avoid any text, watermark, extra characters, or additional objects.

Adjust the model, settings and references before generating.

Use prompt →

Prefill first, then confirm generation and the current cost.

GPT evaluation

Overall score
8.8 / 10

GPT-6-luna

AI evaluation for creative reference

Model: GPT-6-luna Overall score: 8.8 / 10 Prompt quality: 8.7 / 10 Image quality: 9 / 10 Prompt–image alignment: 8.8 / 10 提示词清晰且示例图完成度高、核心元素吻合,适合上线;人物与蒲公英的视觉关系还可略加强。

Prompt quality8.7 / 108.7
Image quality9.0 / 109.0
Prompt–image alignment8.8 / 108.8

Community reviews

No creator reviews yet.

View and review →