
Fantasy Sky Train Attendant Instruction
A highly structured system prompt for maintaining character consistency while placing a subject into various luxury fantasy sky train environments.
Ini adalah contoh kasus GPT Image 2 untuk Potret & Karakter . Gunakan contoh siap salin di bawah ini untuk menghasilkan visual serupa, dan tinjau atribusi Awesome GPT Image 2 Prompts serta hak penggunaan komersial sebelum digunakan kembali.
Free 1K preview
Generate one preview image instantly, no sign-up required.
Free text preview doesn’t preserve reference-image consistency.
Mengingatkan
Prompt siap salin
[Goal]
Using one full-body reference image of the attached person, create one high-quality photorealistic image of the protagonist wearing a fixed uniform of the selected type, standing inside the observation carriage of a fixed luxury sky train.
[Input Items]
Aspect Ratio: [{argument name="aspect ratio" default="1:1 / 9:16"}]
Type: [{argument name="style type" default="Classic / Oriental / Desert"}]
If not entered, use "1:1" and "Classic".
[Person Reference - Common to all types]
Image A = One full-body reference image of the person attached with this instruction. Use Image A as the sole person reference and maintain the same person in the finished image. Do not change the features, eyes, contours, nose, mouth, hairstyle, hair color, hair length, bangs, parting, age feel, skin tone, height, shoulder width, ribcage, torso length, waist position, hip width, leg length and thickness, body type, head-to-body ratio, and overall body proportions of Image A. Do not beautify, rejuvenate, age, slim the face, generalize the face, change into a different person, change hairstyle, reduce shoulder width, shorten the torso, raise the waist position, extend or thin the legs, or change the body type. Do not inherit the outfit, shoes, pose, limb positions, body and face orientation, gaze, background, lighting, or composition from Image A. Only change the uniform, footwear, fixed pose, interior, window view, time of day, light, and atmosphere based on the type specification.
[Common Composition]
Natural photorealistic full-body 3/4 front composition. The camera is slightly higher than the person's waist, shot with a standard angle of view that does not distort the body. The protagonist is slightly to the right of the center, large continuous observation windows are on the left, the aisle extends to the far right, and seats are placed on the right and far left. The entire figure from the top of the head to the bottom of the boots is visible without being cut off, clearly showing the person, uniform, interior, and window view. 1:1 shows more of the window view and seats on the left and right. 9:16 maintains the same person scale and positioning while expanding the ceiling and floor vertically. Do not enlarge the person or cut off the feet. The uniform is clearly separated from the floor and background by brightness and color.
[Type-Specific Fixed Specifications]
(Descriptions for Classic, Oriental, and Desert styles...)
[Common Prohibitions]
Changing the person's face, hair, body type, head-to-body ratio, or proportions; inheriting the pose or background from the reference image; changing the interior layout; merging the person with the background; cutting off the face or feet; wide-angle distortion; toy-like appearance; cheap theme park feel; emphasized exposure; cosplay feel; text, titles, logos, or watermarks.Variabel perintah
Placeholder argumen yang dapat diedit ditemukan dalam prompt, beserta nilai defaultnya.
Best for
- - Potret & Karakter visual exploration
- - Image generation and reference-image edits
- - Reusable briefs that keep source attribution visible
Change these parts
- - Subject, product, character, or scene
- - Aspect ratio, camera, lighting, and background
- - Brand, text, color, and output constraints
Recommended model and settings
- - Model: gpt-image-2
- - Input mode: Gambar ke Gambar
- - Aspect ratio: source
- - Commercial status: review original source
How to use this prompt
- 1. Copy the prompt and preserve its structure for the first test.
- 2. Replace the subject, context, and publishing channel.
- 3. Change one camera, lighting, or style variable per iteration.
- 4. Inspect the output, source, text, and rights before reuse.
Limitations, source, and reuse cautions
- - Generated output is an editable draft, not factual, legal, or rights evidence.
- - Review the linked source, people, brands, logos, text, and third-party media before commercial use.
Lebih banyak kasus dalam kategori ini
Diprioritaskan berdasarkan kategori, kompatibilitas mode input, kualitas, dan risiko yang lebih rendah.
Catatan penggunaan kembali dan sumber
Gunakan perintah ini dengan aman setelah melihat pratinjau kasus.
- 1.Salin perintah tersebut atau buka langsung di Dovoo dengan tombol pembuatan.
- 2.Sesuaikan variabel, rasio aspek, dan gambar referensi untuk kebutuhan Anda sendiri.
- 3.Sebelum mempublikasikan atau menggunakan untuk tujuan berbayar, verifikasi hak sumber, persyaratan atribusi, dan risiko merek atau citra.





